2024

Arzneimittel mit KI entwickeln: Von der Idee bis zur Zulassung. Technical Report (1), Budde, Klemens; Hiltawsky, Karsten; Charton, Jean-Enno; Eskofier, Björn; Krefting, Dagmar; Lang, Maren; Nejdl, Wolfgang; Schapranow, Matthieu-P.; Zahn, Thomas (2024).
[ BibTeX ] [ DOI ]
 
@techreport{budde2024arzneimittel, author = {Budde, Klemens and Hiltawsky, Karsten and Charton, Jean-Enno and Eskofier, Björn and Krefting, Dagmar and Lang, Maren and Nejdl, Wolfgang and Schapranow, Matthieu-P. and Zahn, Thomas}, institution = {Plattform Lernende Systeme}, keywords = {myown pls}, month = {March}, number = 1, title = {Arzneimittel mit KI entwickeln: Von der Idee bis zur Zulassung}, year = 2024 }
Improving biomedical entity linking for complex entity mentions with LLM-based text simplification. Borchert, Florian; Llorca, Ignacio; Schapranow, Matthieu-P in Database (2024). 2024 baae067.
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
Large amounts of important medical information are captured in free-text documents in biomedical research and within healthcare systems, which can be made accessible through natural language processing (NLP). A key component in most biomedical NLP pipelines is entity linking, i.e. grounding textual mentions of named entities to a reference of medical concepts, usually derived from a terminology system, such as the Systematized Nomenclature of Medicine Clinical Terms. However, complex entity mentions, spanning multiple tokens, are notoriously hard to normalize due to the difficulty of finding appropriate candidate concepts. In this work, we propose an approach to preprocess such mentions for candidate generation, building upon recent advances in text simplification with generative large language models. We evaluate the feasibility of our method in the context of the entity linking track of the BioCreative VIII SympTEMIST shared task. We find that instructing the latest Generative Pre-trained Transformer model with a few-shot prompt for text simplification results in mention spans that are easier to normalize. Thus, we can improve recall during candidate generation by 2.9 percentage points compared to our baseline system, which achieved the best score in the original shared task evaluation. Furthermore, we show that this improvement in recall can be fully translated into top-1 accuracy through careful initialization of a subsequent reranking model. Our best system achieves an accuracy of 63.6% on the SympTEMIST test set. The proposed approach has been integrated into the open-source xMEN toolkit, which is available online via https://github.com/hpi-dhc/xmen.
@article{10.1093/database/baae067, abstract = {{Large amounts of important medical information are captured in free-text documents in biomedical research and within healthcare systems, which can be made accessible through natural language processing (NLP). A key component in most biomedical NLP pipelines is entity linking, i.e. grounding textual mentions of named entities to a reference of medical concepts, usually derived from a terminology system, such as the Systematized Nomenclature of Medicine Clinical Terms. However, complex entity mentions, spanning multiple tokens, are notoriously hard to normalize due to the difficulty of finding appropriate candidate concepts. In this work, we propose an approach to preprocess such mentions for candidate generation, building upon recent advances in text simplification with generative large language models. We evaluate the feasibility of our method in the context of the entity linking track of the BioCreative VIII SympTEMIST shared task. We find that instructing the latest Generative Pre-trained Transformer model with a few-shot prompt for text simplification results in mention spans that are easier to normalize. Thus, we can improve recall during candidate generation by 2.9 percentage points compared to our baseline system, which achieved the best score in the original shared task evaluation. Furthermore, we show that this improvement in recall can be fully translated into top-1 accuracy through careful initialization of a subsequent reranking model. Our best system achieves an accuracy of 63.6\\% on the SympTEMIST test set. The proposed approach has been integrated into the open-source xMEN toolkit, which is available online via https://github.com/hpi-dhc/xmen.}}, author = {Borchert, Florian and Llorca, Ignacio and Schapranow, Matthieu-P}, journal = {Database}, keywords = {nlp myown gemtex highmed}, month = {07}, pages = {baae067}, title = {Improving biomedical entity linking for complex entity mentions with {LLM}-based text simplification}, volume = 2024, year = 2024 }
Differentially-Private Federated Learning with Non-IID Data For Surgical Risk Prediction. Pfitzner, Bjarne; Maurer, Max M.; Winter, Axel; Riepe, Christoph; Sauer, Igor M.; van de Water, Robin; Arnrich, Bert in 2024 IEEE First International Conference on Artificial Intelligence for Medicine, Health and Care (AIMHC) (2024). 120–129.
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
Federated learning (FL) has emerged as a promising solution to deal with the privacy concerns which often limit access to data for training machine learning (ML) models. It encompasses the exchange of model parameters between data owners and a central model aggregation instance without the need to share sensitive data directly. Although FL does not require sharing sensitive information, it may not guarantee complete privacy, as model parameters can potentially reveal sensitive details about the underlying training data. To enhance privacy, FL approaches can additionally integrate differential privacy (DP), which entails the careful addition of noise to the model. In this paper, we investigate the relationship between FL, DP, and highly non-independent and identically distributed (non-IID) data. We present a specific real-life healthcare applica tion of predicting patient mortality and revision surgery after visceral operations. Our contributions encompass assessing the performance of FL with and without DP in the presence of highly non-IID data, analysing the fairness for individual training participants and investigating the efficacy of personalisation to alleviate the privacy-utility trade-off introduced by DP. Our findings indicate that the addition of DP into FL given non-IID datasets disparately favours participants with larger datasets, while the model has limited utility for those with less data. The addition of a subsequent model fine-tuning step can remedy this disparity and enables all participants to reach a model performance comparable to the centralised training scenario.
@article{pfitzner2024differentially, abstract = {Federated learning (FL) has emerged as a promising solution to deal with the privacy concerns which often limit access to data for training machine learning (ML) models. It encompasses the exchange of model parameters between data owners and a central model aggregation instance without the need to share sensitive data directly. Although FL does not require sharing sensitive information, it may not guarantee complete privacy, as model parameters can potentially reveal sensitive details about the underlying training data. To enhance privacy, FL approaches can additionally integrate differential privacy (DP), which entails the careful addition of noise to the model. In this paper, we investigate the relationship between FL, DP, and highly non-independent and identically distributed (non-IID) data. We present a specific real-life healthcare applica tion of predicting patient mortality and revision surgery after visceral operations. Our contributions encompass assessing the performance of FL with and without DP in the presence of highly non-IID data, analysing the fairness for individual training participants and investigating the efficacy of personalisation to alleviate the privacy-utility trade-off introduced by DP. Our findings indicate that the addition of DP into FL given non-IID datasets disparately favours participants with larger datasets, while the model has limited utility for those with less data. The addition of a subsequent model fine-tuning step can remedy this disparity and enables all participants to reach a model performance comparable to the centralised training scenario.}, author = {Pfitzner, Bjarne and Maurer, Max M. and Winter, Axel and Riepe, Christoph and Sauer, Igor M. and van de Water, Robin and Arnrich, Bert}, journal = {2024 IEEE First International Conference on Artificial Intelligence for Medicine, Health and Care (AIMHC)}, keywords = {myown bertarnrich bjarnepfitzner robinvandewater}, pages = {120-129}, title = {Differentially-Private Federated Learning with Non-IID Data For Surgical Risk Prediction}, year = 2024 }
Analyzing population-level trials as N-of-1 trials: An application to gait. Zhou, Lin; Schneider, Juliana; Arnrich, Bert; Konigorski, Stefan in Contemporary Clinical Trials Communications (2024). 101282.
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
Studying individual causal effects of health interventions is important whenever intervention effects are heterogeneous between study participants. Conducting N-of-1 trials, which are single-person randomized controlled trials, is the gold standard for their analysis. As an alternative method, we propose to re-analyze existing population-level studies as N-of-1 trials, and use gait as a use case for illustration. Gait data were collected from 16 young and healthy participants under fatigued and non-fatigued, as well as under single-task (only walking) and dual-task (walking while performing a cognitive task) conditions. As a reference to the N-of-1 trials approach, we first computed standard population-level ANOVA models to evaluate differences in gait parameters (stride length and stride time) across conditions. Then, we estimated the effect of the interventions on gait parameters on the individual level through Bayesian repeated-measures models, viewing each participant as their own trial, and compared the results. The results illustrated that while few overall population-level effects were visible, individual-level analyses revealed differences between participants. Baseline values of the gait parameters varied largely among all participants, and the effects of fatigue and cognitive task were also heterogeneous, with some individuals showing effects in opposite directions. These differences between population-level and individual-level analyses were more pronounced for the fatigue intervention compared to the cognitive task intervention. Following our empirical analysis, we discuss re-analyzing population studies through the lens of N-of-1 trials more generally and highlight important considerations and requirements. Our work encourages future studies to investigate individual effects using population-level data.
@article{zhou2024analyzing, abstract = {Studying individual causal effects of health interventions is important whenever intervention effects are heterogeneous between study participants. Conducting N-of-1 trials, which are single-person randomized controlled trials, is the gold standard for their analysis. As an alternative method, we propose to re-analyze existing population-level studies as N-of-1 trials, and use gait as a use case for illustration. Gait data were collected from 16 young and healthy participants under fatigued and non-fatigued, as well as under single-task (only walking) and dual-task (walking while performing a cognitive task) conditions. As a reference to the N-of-1 trials approach, we first computed standard population-level ANOVA models to evaluate differences in gait parameters (stride length and stride time) across conditions. Then, we estimated the effect of the interventions on gait parameters on the individual level through Bayesian repeated-measures models, viewing each participant as their own trial, and compared the results. The results illustrated that while few overall population-level effects were visible, individual-level analyses revealed differences between participants. Baseline values of the gait parameters varied largely among all participants, and the effects of fatigue and cognitive task were also heterogeneous, with some individuals showing effects in opposite directions. These differences between population-level and individual-level analyses were more pronounced for the fatigue intervention compared to the cognitive task intervention. Following our empirical analysis, we discuss re-analyzing population studies through the lens of N-of-1 trials more generally and highlight important considerations and requirements. Our work encourages future studies to investigate individual effects using population-level data.}, author = {Zhou, Lin and Schneider, Juliana and Arnrich, Bert and Konigorski, Stefan}, journal = {Contemporary Clinical Trials Communications}, keywords = {linzhou bertarnrich stefankonigorski julianaschneider}, pages = 101282, publisher = {Elsevier}, title = {Analyzing population-level trials as N-of-1 trials: An application to gait}, year = 2024 }
CognitIDE: An IDE Plugin for Mapping Physiological Measurements to Source Code. Stolp, Fabian; Stellmacher, Malte; Arnrich, Bert in FSE 2024 (2024). 592–596.
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
We present CognitIDE, a tool for collecting physiological measurements, mapping them to source code, and visualizing them directly within IntelliJ-based Integrated Development Environments (IDE)s. CognitIDE facilitates the setup and conduction of empirical studies evaluating the relationships between software artifacts and physiological parameters. Corresponding measurements enable researchers to evaluate, for example, the cognitive load software developers are experiencing. Our tool lets study participants use IDEs in a natural way while eye gaze, further body sensor data, and interactions with the IDE are collected. Furthermore, CognitIDE enables highlighting code positions according to the physiological values collected while corresponding positions were looked at. This facilitates the identification of poorly maintainable code and provides a direct way for study participants to reflect on whether the measurements mirror their perception. Moreover, the plugin has additional features for facilitating studies, such as interrupting participants and letting them answer predefined questions. Our tool supports recording measurements with the wide variety of devices supported by the Lab Streaming Layer. Video: https://youtu.be/9yLV5AdTiJw
@inproceedings{10.1145/3663529.3663805, abstract = {We present CognitIDE, a tool for collecting physiological measurements, mapping them to source code, and visualizing them directly within IntelliJ-based Integrated Development Environments (IDE)s. CognitIDE facilitates the setup and conduction of empirical studies evaluating the relationships between software artifacts and physiological parameters. Corresponding measurements enable researchers to evaluate, for example, the cognitive load software developers are experiencing. Our tool lets study participants use IDEs in a natural way while eye gaze, further body sensor data, and interactions with the IDE are collected. Furthermore, CognitIDE enables highlighting code positions according to the physiological values collected while corresponding positions were looked at. This facilitates the identification of poorly maintainable code and provides a direct way for study participants to reflect on whether the measurements mirror their perception. Moreover, the plugin has additional features for facilitating studies, such as interrupting participants and letting them answer predefined questions. Our tool supports recording measurements with the wide variety of devices supported by the Lab Streaming Layer. Video: https://youtu.be/9yLV5AdTiJw}, address = {New York, NY, USA}, author = {Stolp, Fabian and Stellmacher, Malte and Arnrich, Bert}, booktitle = {Companion Proceedings of the 32nd ACM International Conference on the Foundations of Software Engineering}, keywords = {myown bertarnrich fabianstolp}, pages = {592–596}, publisher = {Association for Computing Machinery}, series = {FSE 2024}, title = {CognitIDE: An IDE Plugin for Mapping Physiological Measurements to Source Code}, year = 2024 }
ARTEMIS: An Alarm Threshold and Policy Mining System for the Intensive Care Unit. Chromik, Jonas; Flint, Anne Rike; Arnrich, Bert in International Journal of Medical Informatics (2024). 105349.
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
Alarm fatigue is a major technology-induced hazard for patients and staff in intensive care units. Too many – mostly unnecessary – alarms cause desensitisation and lack of response in medical staff. Unsuitable alarm policies are one reason for alarm fatigue. But changing alarm policies is a delicate issue since it concerns patient safety. We present ARTEMIS, a novel, computer-aided clinical decision support system for policy makers that can help to considerably improve alarm policies using data from hospital information systems. Policy makers can use different policy components from ARTEMIS' internal library to assemble tailor-made alarm policies for their intensive care units. Alternatively, policy makers can provide even more highly customised policy components as Python functions using data the hospital information systems. This can even include machine learning models – for example for setting alarm thresholds. Finally, policy makers can evaluate their system of policies and compare the resulting alarm loads. ARTEMIS reports and compares numbers of alarms caused by different alarm policies for an easily adaptable target population. ARTEMIS can compare policies side-by-side and provides grid comparisons and heat maps for parameter optimisation. For example, we found that the utility of alarm delays varies based on target population. Furthermore, policy makers can introduce virtual parameters that are not in the original data by providing a formula to compute them. Virtual parameters help measuring and alarming on the right metric, even if the patient monitors do not directly measure this metric. ARTEMIS does not release the policy maker from assessing the policy from a medical standpoint. But as a knowledge discovery and clinical decision support system, it provides a strong quantitative foundation for medical decisions. At comparatively low cost of implementation, ARTEMIS can have a substantial impact on patients and staff alike – with organisational, economic, and clinical benefits for the implementing hospital.
@article{chromik2024artemis, abstract = {Alarm fatigue is a major technology-induced hazard for patients and staff in intensive care units. Too many – mostly unnecessary – alarms cause desensitisation and lack of response in medical staff. Unsuitable alarm policies are one reason for alarm fatigue. But changing alarm policies is a delicate issue since it concerns patient safety. We present ARTEMIS, a novel, computer-aided clinical decision support system for policy makers that can help to considerably improve alarm policies using data from hospital information systems. Policy makers can use different policy components from ARTEMIS' internal library to assemble tailor-made alarm policies for their intensive care units. Alternatively, policy makers can provide even more highly customised policy components as Python functions using data the hospital information systems. This can even include machine learning models – for example for setting alarm thresholds. Finally, policy makers can evaluate their system of policies and compare the resulting alarm loads. ARTEMIS reports and compares numbers of alarms caused by different alarm policies for an easily adaptable target population. ARTEMIS can compare policies side-by-side and provides grid comparisons and heat maps for parameter optimisation. For example, we found that the utility of alarm delays varies based on target population. Furthermore, policy makers can introduce virtual parameters that are not in the original data by providing a formula to compute them. Virtual parameters help measuring and alarming on the right metric, even if the patient monitors do not directly measure this metric. ARTEMIS does not release the policy maker from assessing the policy from a medical standpoint. But as a knowledge discovery and clinical decision support system, it provides a strong quantitative foundation for medical decisions. At comparatively low cost of implementation, ARTEMIS can have a substantial impact on patients and staff alike – with organisational, economic, and clinical benefits for the implementing hospital.}, author = {Chromik, Jonas and Flint, Anne Rike and Arnrich, Bert}, journal = {International Journal of Medical Informatics}, keywords = {bertarnrich jonaschromik}, month = {jan}, pages = 105349, title = {{{ARTEMIS}}: {{An Alarm Threshold}} and {{Policy Mining System}} for the {{Intensive Care Unit}}}, year = 2024 }
A computer vision approach to continuously monitor fatigue during resistance training. Albert, Justin Amadeus; Arnrich, Bert in Biomedical Signal Processing and Control (2024). 89 105701.
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
Monitoring fatigue during resistance training is essential to avoid injuries caused by overtraining. Fatigue can be comprehensively quantified by the external and internal load, where the external load is the work done by the athlete, and the internal load is the psychological and physiological response to the external load. This paper proposes a computer vision method to continuously monitor fatigue during resistance training by predicting external and internal parameters, namely the generated power and the rating of perceived exertion. We utilize the human pose estimation from two Microsoft Azure Kinect cameras to capture the movement of athletes while performing stationary exercises. Our method processes the obtained kinematic data, computes skeleton features to train traditional machine learning algorithms, and constructs feature maps to train convolutional neural network-based models to predict the load parameters. For evaluation, we recorded a dataset of 16 subjects who performed squat exercises on a Flywheel and rated their perceived exertion after each set. A measuring unit integrated into the Flywheel provided power readings for each repetition. The results show that our method achieves good results in predicting both parameters. Gradient Boosting Regression Trees best predicted perceived exertion with a mean absolute percentage error of 8.08% and a Spearman’s ρ=0.74. Multi-layer Perceptron performed best in predicting power with a mean absolute error of 23.13 Watts and ρ=0.79. Our findings show that our approach delivers promising external and internal load quantifications for fatigue, with great potential to provide external feedback to coaches or athletes.
@article{ALBERT2024105701, abstract = {Monitoring fatigue during resistance training is essential to avoid injuries caused by overtraining. Fatigue can be comprehensively quantified by the external and internal load, where the external load is the work done by the athlete, and the internal load is the psychological and physiological response to the external load. This paper proposes a computer vision method to continuously monitor fatigue during resistance training by predicting external and internal parameters, namely the generated power and the rating of perceived exertion. We utilize the human pose estimation from two Microsoft Azure Kinect cameras to capture the movement of athletes while performing stationary exercises. Our method processes the obtained kinematic data, computes skeleton features to train traditional machine learning algorithms, and constructs feature maps to train convolutional neural network-based models to predict the load parameters. For evaluation, we recorded a dataset of 16 subjects who performed squat exercises on a Flywheel and rated their perceived exertion after each set. A measuring unit integrated into the Flywheel provided power readings for each repetition. The results show that our method achieves good results in predicting both parameters. Gradient Boosting Regression Trees best predicted perceived exertion with a mean absolute percentage error of 8.08% and a Spearman’s ρ=0.74. Multi-layer Perceptron performed best in predicting power with a mean absolute error of 23.13 Watts and ρ=0.79. Our findings show that our approach delivers promising external and internal load quantifications for fatigue, with great potential to provide external feedback to coaches or athletes.}, author = {Albert, Justin Amadeus and Arnrich, Bert}, journal = {Biomedical Signal Processing and Control}, keywords = {justinalbert bertarnrich}, pages = 105701, title = {A computer vision approach to continuously monitor fatigue during resistance training}, volume = 89, year = 2024 }
medBERT.de: A Comprehensive German BERT Model for the Medical Domain. Bressem, Keno K.; Papaioannou, Jens-Michalis; Grundmann, Paul; Borchert, Florian; Adams, Lisa C.; Liu, Leonhard; Busch, Felix; Xu, Lina; Loyen, Jan P.; Niehues, Stefan M.; Augustin, Moritz; Grosser, Lennart; Makowski, Marcus R.; Aerts, Hugo JWL.; Löser, Alexander in Expert Systems with Applications (2024). 121598.
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
This paper presents medBERT.de, a pre-trained German BERT model specifically designed for the German medical domain. The model has been trained on a large corpus of 4.7 Million German medical documents and has been shown to achieve new state-of-the-art performance on eight different medical benchmarks covering a wide range of disciplines and medical document types. In addition to evaluating the overall performance of the model, this paper also conducts a more in-depth analysis of its capabilities. We investigate the impact of data deduplication on the model's performance, as well as the potential benefits of using more efficient tokenization methods. Our results indicate that domain-specific models such as medBERT.de are particularly useful for longer texts, and that deduplication of training data does not necessarily lead to improved performance. Furthermore, we found that efficient tokenization plays only a minor role in improving model performance, and attribute most of the improved performance to the large amount of training data. To encourage further research, the pre-trained model weights and new benchmarks based on radiological data are made publicly available for use by the scientific community.
@article{BRESSEM2023121598, abstract = {This paper presents medBERT.de, a pre-trained German BERT model specifically designed for the German medical domain. The model has been trained on a large corpus of 4.7 Million German medical documents and has been shown to achieve new state-of-the-art performance on eight different medical benchmarks covering a wide range of disciplines and medical document types. In addition to evaluating the overall performance of the model, this paper also conducts a more in-depth analysis of its capabilities. We investigate the impact of data deduplication on the model's performance, as well as the potential benefits of using more efficient tokenization methods. Our results indicate that domain-specific models such as medBERT.de are particularly useful for longer texts, and that deduplication of training data does not necessarily lead to improved performance. Furthermore, we found that efficient tokenization plays only a minor role in improving model performance, and attribute most of the improved performance to the large amount of training data. To encourage further research, the pre-trained model weights and new benchmarks based on radiological data are made publicly available for use by the scientific community.}, author = {Bressem, Keno K. and Papaioannou, Jens-Michalis and Grundmann, Paul and Borchert, Florian and Adams, Lisa C. and Liu, Leonhard and Busch, Felix and Xu, Lina and Loyen, Jan P. and Niehues, Stefan M. and Augustin, Moritz and Grosser, Lennart and Makowski, Marcus R. and Aerts, Hugo JWL. and Löser, Alexander}, journal = {Expert Systems with Applications}, keywords = {nlp myown fb-boettinger}, month = {mar}, pages = 121598, title = {medBERT.de: A Comprehensive German BERT Model for the Medical Domain}, year = 2024 }

2023

A Meta-dataset of German Medical Corpora: Harmonization of Annotations and Cross-corpus NER Evaluation. Llorca, Ignacio; Borchert, Florian; Schapranow, Matthieu-P. (2023). 171–181.
[ Abstract ] [ BibTeX ] [ URL ]
 
Over the last years, an increasing number of publicly available, semantically annotated medical corpora have been released for the German language. While their annotations cover comparable semantic classes, the synergies of such efforts have not been explored, yet. This is due to substantial differences in the data schemas (syntax) and annotated entities (semantics), which hinder the creation of common meta-datasets. For instance, it is unclear whether named entity recognition (NER) taggers trained on one or more of such datasets are useful to detect entities in any of the other datasets. In this work, we create harmonized versions of German medical corpora using the BigBIO framework, and make them available to the community. Using these as a meta-dataset, we perform a series of cross-corpus evaluation experiments on two settings of aligned labels. These consist in fine-tuning various pre-trained Transformers on different combinations of training sets, and testing them against each dataset separately. We find that a) trained NER models generalize poorly, with F1 scores dropping approx. 20 pp. on unseen test data, and b) current pre-trained Transformer models for the German language do not systematically alleviate this issue. However, our results suggest that models benefit from additional training corpora in most cases, even if these belong to different medical fields or text genres.
@inproceedings{llorca-etal-2023-meta, abstract = {Over the last years, an increasing number of publicly available, semantically annotated medical corpora have been released for the German language. While their annotations cover comparable semantic classes, the synergies of such efforts have not been explored, yet. This is due to substantial differences in the data schemas (syntax) and annotated entities (semantics), which hinder the creation of common meta-datasets. For instance, it is unclear whether named entity recognition (NER) taggers trained on one or more of such datasets are useful to detect entities in any of the other datasets. In this work, we create harmonized versions of German medical corpora using the BigBIO framework, and make them available to the community. Using these as a meta-dataset, we perform a series of cross-corpus evaluation experiments on two settings of aligned labels. These consist in fine-tuning various pre-trained Transformers on different combinations of training sets, and testing them against each dataset separately. We find that a) trained NER models generalize poorly, with F1 scores dropping approx. 20 pp. on unseen test data, and b) current pre-trained Transformer models for the German language do not systematically alleviate this issue. However, our results suggest that models benefit from additional training corpora in most cases, even if these belong to different medical fields or text genres.}, address = {Toronto, Canada}, author = {Llorca, Ignacio and Borchert, Florian and Schapranow, Matthieu-P.}, booktitle = {Proceedings of the 5th Clinical Natural Language Processing Workshop}, keywords = {nlp myown gemtex highmed nephrocage fb-boettinger}, month = {jul}, pages = {171–181}, publisher = {Association for Computational Linguistics}, title = {A Meta-dataset of {G}erman Medical Corpora: Harmonization of Annotations and Cross-corpus {NER} Evaluation}, year = 2023 }
Federated Learning for Activity Recognition: A System Level Perspective. Kalabakov, Stefan; Jovanovski, Borche; Denkovski, Daniel; Rakovic, Valentin; Pfitzner, Bjarne; Konak, Orhan; Arnrich, Bert; Gjoreski, Hristijan in IEEE Access (2023). 11 64442–64457.
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
The past decade has seen substantial growth in the prevalence and capabilities of wearable devices. For instance, recent human activity recognition (HAR) research has explored using wearable devices in applications such as remote monitoring of patients, detection of gait abnormalities, and cognitive disease identification. However, data collection poses a major challenge in developing HAR systems, especially because of the need to store data at a central location. This raises privacy concerns and makes continuous data collection difficult and expensive due to the high cost of transferring data from a user’s wearable device to a central repository. Considering this, we explore the adoption of federated learning (FL) as a potential solution to address the privacy and cost issues associated with data collection in HAR. More specifically, we investigate the performance and behavioral differences between FL and deep learning (DL) HAR models, under various conditions relevant to real-world deployments. Namely, we explore the differences between the two types of models when (i) using data from different sensor placements, (ii) having access to users with data from heterogeneous sensor placements, (iii) considering bandwidth efficiency, and (iv) dealing with data with incorrect labels. Our results show that FL models suffer from a consistent performance deficit in comparison to their DL counterparts, but achieve these results with much better bandwidth efficiency. Furthermore, we observe that FL models exhibit very similar responses to those of DL models when exposed to data from heterogeneous sensor placements. Finally, we show that the FL models are more robust to data with incorrect labels than their centralized DL counterparts.
@article{kalabakov2023federated, abstract = {The past decade has seen substantial growth in the prevalence and capabilities of wearable devices. For instance, recent human activity recognition (HAR) research has explored using wearable devices in applications such as remote monitoring of patients, detection of gait abnormalities, and cognitive disease identification. However, data collection poses a major challenge in developing HAR systems, especially because of the need to store data at a central location. This raises privacy concerns and makes continuous data collection difficult and expensive due to the high cost of transferring data from a user’s wearable device to a central repository. Considering this, we explore the adoption of federated learning (FL) as a potential solution to address the privacy and cost issues associated with data collection in HAR. More specifically, we investigate the performance and behavioral differences between FL and deep learning (DL) HAR models, under various conditions relevant to real-world deployments. Namely, we explore the differences between the two types of models when (i) using data from different sensor placements, (ii) having access to users with data from heterogeneous sensor placements, (iii) considering bandwidth efficiency, and (iv) dealing with data with incorrect labels. Our results show that FL models suffer from a consistent performance deficit in comparison to their DL counterparts, but achieve these results with much better bandwidth efficiency. Furthermore, we observe that FL models exhibit very similar responses to those of DL models when exposed to data from heterogeneous sensor placements. Finally, we show that the FL models are more robust to data with incorrect labels than their centralized DL counterparts.}, author = {Kalabakov, Stefan and Jovanovski, Borche and Denkovski, Daniel and Rakovic, Valentin and Pfitzner, Bjarne and Konak, Orhan and Arnrich, Bert and Gjoreski, Hristijan}, journal = {IEEE Access}, keywords = {bertarnrich bjarnepfitzner orhankonak widehealth stefankalabakov}, pages = {64442-64457}, title = {Federated Learning for Activity Recognition: A System Level Perspective}, volume = 11, year = 2023 }
Towards Supporting an Early Diagnosis of Multiple Sclerosis using Vocal Features. Gonzalez-Machorro, Monica; Hecker, Pascal; Reichel, Uwe D.; Hammer, Helly N.; Hoepner, Robert; Pedrotti, Lisa; Zmutt, Alisha; Sagha, Hesam; van Beek, Johan; Eyben, Florian; Schuller, Dagmar M.; Schuller, Björn W.; Arnrich, Bert (2023). 1518–1522.
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
Multiple sclerosis (MS) is a neuroinflammatory disease that affects millions of people worldwide. Since dysarthria is prominent in people with MS (pwMS), this paper aims to identify acoustic features that differ between people with MS and healthy controls (HC). Additionally, we develop automatic classification methods to distinguish between pwMS and HC. In this work, we present a new dataset of a German-speaking cohort which contains 39 patients with low disability of relapsing MS and 16 HC. Findings suggest that certain interpretable speech features could be useful in diagnosing MS, and that machine learning methods could potentially support fast and unobtrusive screening in clinical practice. The study emphasises the importance of analysing free speech compared to read speech.
@inproceedings{gonzalezmachorro23_interspeech, abstract = {Multiple sclerosis (MS) is a neuroinflammatory disease that affects millions of people worldwide. Since dysarthria is prominent in people with MS (pwMS), this paper aims to identify acoustic features that differ between people with MS and healthy controls (HC). Additionally, we develop automatic classification methods to distinguish between pwMS and HC. In this work, we present a new dataset of a German-speaking cohort which contains 39 patients with low disability of relapsing MS and 16 HC. Findings suggest that certain interpretable speech features could be useful in diagnosing MS, and that machine learning methods could potentially support fast and unobtrusive screening in clinical practice. The study emphasises the importance of analysing free speech compared to read speech.}, author = {Gonzalez-Machorro, Monica and Hecker, Pascal and Reichel, Uwe D. and Hammer, Helly N. and Hoepner, Robert and Pedrotti, Lisa and Zmutt, Alisha and Sagha, Hesam and van Beek, Johan and Eyben, Florian and Schuller, Dagmar M. and Schuller, Björn W. and Arnrich, Bert}, booktitle = {Interspeech 2023}, keywords = {pascalhecker bertarnrich monicagonzalezmachorro}, pages = {1518-1522}, title = {Towards Supporting an Early Diagnosis of Multiple Sclerosis using Vocal Features}, year = 2023 }
NephroCAGE: Wie Künstliche Intelligenz bei Nierenversagen unterstützen kann. Schapranow, Matthieu-P. in Gesundhyte: Forschung neu vernetzen. (2023). 15 100—102.
[ BibTeX ]
 
@article{schapranow2023nephrocage, author = {Schapranow, Matthieu-P.}, journal = {Gesundhyte: Forschung neu vernetzen.}, keywords = {myown nephrocage}, pages = {100—102}, title = {NephroCAGE: Wie Künstliche Intelligenz bei Nierenversagen unterstützen kann.}, volume = 15, year = 2023 }
Kann uns ChatGPT bei der Digitalisierung der Medizin helfen?. Schapranow, Matthieu-P. in Management & Krankenhaus (2023). 42(6) 10.
[ BibTeX ]
 
@article{schapranow2023chatgpt, author = {Schapranow, Matthieu-P.}, journal = {Management & Krankenhaus}, keywords = {myown pls}, month = {june}, number = 6, pages = 10, title = {Kann uns ChatGPT bei der Digitalisierung der Medizin helfen?}, volume = 42, year = 2023 }
Protocol for a Randomized Crossover Trial to Evaluate the Effect of Soft Brace and Rigid Orthosis on Performance and Readiness to Return to Sport Six Months Post-ACL-Reconstruction. Jahnke, Sonja; Cruysen, Caren; Prill, Robert; Kittmann, Fabian; Pflug, Nicola; Albert, Justin Amadeus; de Camargo, Tibor; Arnrich, Bert; Królikowska, Aleksandra; Kołcz, Anna; Reichert, Paweł; Oleksy, Łukasz; Michel, Sven; Kopf, Sebastian; Wagner, Michael; Scheffler, Sven; Becker, Roland in Healthcare (2023). 11(4)
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
A randomized crossover trial was designed to investigate the influence of muscle activation and strength on functional stability/control of the knee joint, to determine whether bilateral imbalances still occur six months after successful anterior cruciate ligament reconstruction (ACLR), and to analyze whether the use of orthotic devices changes the activity onset of these muscles. Furthermore, conclusions on the feedforward and feedback mechanisms are highlighted. Therefore, twenty-eight patients will take part in a modified Back in Action (BIA) test battery at an average of six months after a primary unilateral ACLR, which used an autologous ipsilateral semitendinosus tendon graft. This includes double-leg and single-leg stability tests, double-leg and single-leg countermovement jumps, double-leg and single-leg drop jumps, a speedy jump test, and a quick feet test. During the tests, gluteus medius and semitendinosus muscle activity are analyzed using surface electromyography (sEMG). Motion analysis is conducted using Microsoft Azure DK and 3D force plates. The tests are performed while wearing knee rigid orthosis, soft brace, and with no aid, in random order. Additionally, the range of hip and knee motion and hip abductor muscle strength under isometric conditions are measured. Furthermore, patient-rated outcomes will be assessed.
@article{healthcare11040513, abstract = {A randomized crossover trial was designed to investigate the influence of muscle activation and strength on functional stability/control of the knee joint, to determine whether bilateral imbalances still occur six months after successful anterior cruciate ligament reconstruction (ACLR), and to analyze whether the use of orthotic devices changes the activity onset of these muscles. Furthermore, conclusions on the feedforward and feedback mechanisms are highlighted. Therefore, twenty-eight patients will take part in a modified Back in Action (BIA) test battery at an average of six months after a primary unilateral ACLR, which used an autologous ipsilateral semitendinosus tendon graft. This includes double-leg and single-leg stability tests, double-leg and single-leg countermovement jumps, double-leg and single-leg drop jumps, a speedy jump test, and a quick feet test. During the tests, gluteus medius and semitendinosus muscle activity are analyzed using surface electromyography (sEMG). Motion analysis is conducted using Microsoft Azure DK and 3D force plates. The tests are performed while wearing knee rigid orthosis, soft brace, and with no aid, in random order. Additionally, the range of hip and knee motion and hip abductor muscle strength under isometric conditions are measured. Furthermore, patient-rated outcomes will be assessed.}, author = {Jahnke, Sonja and Cruysen, Caren and Prill, Robert and Kittmann, Fabian and Pflug, Nicola and Albert, Justin Amadeus and de Camargo, Tibor and Arnrich, Bert and Królikowska, Aleksandra and Kołcz, Anna and Reichert, Paweł and Oleksy, Łukasz and Michel, Sven and Kopf, Sebastian and Wagner, Michael and Scheffler, Sven and Becker, Roland}, journal = {Healthcare}, keywords = {justinalbert bertarnrich}, number = 4, title = {Protocol for a Randomized Crossover Trial to Evaluate the Effect of Soft Brace and Rigid Orthosis on Performance and Readiness to Return to Sport Six Months Post-ACL-Reconstruction}, volume = 11, year = 2023 }
NephroCAGE—German-Canadian Consortium on AI for Improved Kidney Transplantation Outcome: Protocol for an Algorithm Development and Validation Study. Schapranow, Matthieu-P.; Bayat, M; Rasheed, A; Naik, M; Graf, V; Schmidt, D; Budde, K; Cardinal, H; Sapir-Pichhadze, R; Fenninger, F; Sherwood, K; Keown, P; Günther, O; Pandl, K; Leiser, F; Thiebes, S; Sunyaev, A; Niemann, M; Schimanski, A; Klein, T in JMIR Res Protoc 2023 (2023). 12(e48892)
[ BibTeX ] [ URL ] [ DOI ]
 
@article{noauthororeditor2023nephrocagegermancanadian, author = {Schapranow, Matthieu-P. and Bayat, M and Rasheed, A and Naik, M and Graf, V and Schmidt, D and Budde, K and Cardinal, H and Sapir-Pichhadze, R and Fenninger, F and Sherwood, K and Keown, P and Günther, O and Pandl, K and Leiser, F and Thiebes, S and Sunyaev, A and Niemann, M and Schimanski, A and Klein, T}, journal = {JMIR Res Protoc 2023}, keywords = {myown nephrocage}, month = {dec}, number = {e48892}, title = {NephroCAGE—German-Canadian Consortium on AI for Improved Kidney Transplantation Outcome: Protocol for an Algorithm Development and Validation Study}, volume = 12, year = 2023 }
HPIDHC at NTCIR-17 MedNLP-SC: Data Augmentation and Ensemble Learning for Multilingual Adverse Drug Event Detection. Fox, Smilla; Preiß, Martin; Borchert, Florian; Rasheed, Aadil; Schapranow, Matthieu-P. (2023). 185–192.
[ BibTeX ] [ URL ] [ DOI ]
 
@inproceedings{fox2023hpidhc, address = {Tokyo, Japan}, author = {Fox, Smilla and Preiß, Martin and Borchert, Florian and Rasheed, Aadil and Schapranow, Matthieu-P.}, booktitle = {NTCIR 17 Conference: Proceedings of the 17th NTCIR Conference on Evaluation of Information Access Technologies}, keywords = {nlp myown gemtex}, month = {dec}, pages = {185-192}, title = {HPIDHC at NTCIR-17 MedNLP-SC: Data Augmentation and Ensemble Learning for Multilingual Adverse Drug Event Detection}, year = 2023 }
HARE: Unifying the Human Activity Recognition Engineering Workflow. Konak, Orhan; van de Water, Robin; Döring, Valentin; Fiedler, Tobias; Liebe, Lucas; Masopust, Leander; Postnov, Kirill; Sauerwald, Franz; Treykorn, Felix; Wischmann, Alexander; Gjoreski, Hristijan; Luštrek, Mitja; Arnrich, Bert in Sensors (2023). 23(23)
[ BibTeX ] [ URL ] [ DOI ]
 
@article{s23239571, author = {Konak, Orhan and van de Water, Robin and Döring, Valentin and Fiedler, Tobias and Liebe, Lucas and Masopust, Leander and Postnov, Kirill and Sauerwald, Franz and Treykorn, Felix and Wischmann, Alexander and Gjoreski, Hristijan and Luštrek, Mitja and Arnrich, Bert}, journal = {Sensors}, keywords = {bertarnrich orhankonak robinvandewater widehealth}, number = 23, title = {HARE: Unifying the Human Activity Recognition Engineering Workflow}, volume = 23, year = 2023 }
Online learning for wearable eeg-based emotion classification. Moontaha, Sidratul; Schumann, Franziska Elisabeth Friederike; Arnrich, Bert in Sensors (2023). 23(5) 2387.
[ BibTeX ] [ DOI ]
 
@article{moontaha2023online, author = {Moontaha, Sidratul and Schumann, Franziska Elisabeth Friederike and Arnrich, Bert}, journal = {Sensors}, keywords = {sidratulmoontaha}, number = 5, pages = 2387, publisher = {MDPI}, title = {Online learning for wearable eeg-based emotion classification}, volume = 23, year = 2023 }
Food Choices after Cognitive Load: An Affective Computing Approach. Kappattanavar, Arpita Mallikarjuna; Hecker, Pascal; Moontaha, Sidratul; Steckhan, Nico; Arnrich, Bert in Sensors (2023). 23(14)
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
Psychology and nutritional science research has highlighted the impact of negative emotions and cognitive load on calorie consumption behaviour using subjective questionnaires. Isolated studies in other domains objectively assess cognitive load without considering its effects on eating behaviour. This study aims to explore the potential for developing an integrated eating behaviour assistant system that incorporates cognitive load factors. Two experimental sessions were conducted using custom-developed experimentation software to induce different stimuli. During these sessions, we collected 30 h of physiological, food consumption, and affective states questionnaires data to automatically detect cognitive load and analyse its effect on food choice. Utilising grid search optimisation and leave-one-subject-out cross-validation, a support vector machine model achieved a mean classification accuracy of 85.12% for the two cognitive load tasks using eight relevant features. Statistical analysis was performed on calorie consumption and questionnaire data. Furthermore, 75% of the subjects with higher negative affect significantly increased consumption of specific foods after high-cognitive-load tasks. These findings offer insights into the intricate relationship between cognitive load, affective states, and food choice, paving the way for an eating behaviour assistant system to manage food choices during cognitive load. Future research should enhance system capabilities and explore real-world applications.
@article{kappattanavar2023choices, abstract = {Psychology and nutritional science research has highlighted the impact of negative emotions and cognitive load on calorie consumption behaviour using subjective questionnaires. Isolated studies in other domains objectively assess cognitive load without considering its effects on eating behaviour. This study aims to explore the potential for developing an integrated eating behaviour assistant system that incorporates cognitive load factors. Two experimental sessions were conducted using custom-developed experimentation software to induce different stimuli. During these sessions, we collected 30 h of physiological, food consumption, and affective states questionnaires data to automatically detect cognitive load and analyse its effect on food choice. Utilising grid search optimisation and leave-one-subject-out cross-validation, a support vector machine model achieved a mean classification accuracy of 85.12% for the two cognitive load tasks using eight relevant features. Statistical analysis was performed on calorie consumption and questionnaire data. Furthermore, 75% of the subjects with higher negative affect significantly increased consumption of specific foods after high-cognitive-load tasks. These findings offer insights into the intricate relationship between cognitive load, affective states, and food choice, paving the way for an eating behaviour assistant system to manage food choices during cognitive load. Future research should enhance system capabilities and explore real-world applications.}, author = {Kappattanavar, Arpita Mallikarjuna and Hecker, Pascal and Moontaha, Sidratul and Steckhan, Nico and Arnrich, Bert}, journal = {Sensors}, keywords = {pascalhecker nicosteckhan bertarnrich sidratulmoontaha arpitakappattanavar}, number = 14, title = {Food Choices after Cognitive Load: An Affective Computing Approach}, volume = 23, year = 2023 }
Optimization of data pre-processing methods for time-series classification of electroencephalography data. Anders, Christoph; Curio, Gabriel; Arnrich, Bert; Waterstraat, Gunnar in Taylor and Francis, Network: Computation in Neural Systems (2023). 34(4) 374–391.
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
The performance of time-series classification of electroencephalographic data varies strongly across experimental paradigms and study participants. Reasons are task-dependent differences in neuronal processing and seemingly random variations between subjects, amongst others. The effect of data pre-processing techniques to ameliorate these challenges is relatively little studied. Here, the influence of spatial filter optimization methods and non-linear data transformation on time-series classification performance is analyzed by the example of high-frequency somatosensory evoked responses. This is a model paradigm for the analysis of high-frequency electroencephalography data at a very low signal-to-noise ratio, which emphasizes the differences of the explored methods. For the utilized data, it was found that the individual signal-to-noise ratio explained up to 74% of the performance differences between subjects. While data pre-processing was shown to increase average time-series classification performance, it could not fully compensate the signal-to-noise ratio differences between the subjects. This study proposes an algorithm to prototype and benchmark pre-processing pipelines for a paradigm and data set at hand. Extreme learning machines, Random Forest, and Logistic Regression can be used quickly to compare a set of potentially suitable pipelines. For subsequent classification, however, machine learning models were shown to provide better accuracy.
@article{anders_optimization_2023, abstract = {The performance of time-series classification of electroencephalographic data varies strongly across experimental paradigms and study participants. Reasons are task-dependent differences in neuronal processing and seemingly random variations between subjects, amongst others. The effect of data pre-processing techniques to ameliorate these challenges is relatively little studied. Here, the influence of spatial filter optimization methods and non-linear data transformation on time-series classification performance is analyzed by the example of high-frequency somatosensory evoked responses. This is a model paradigm for the analysis of high-frequency electroencephalography data at a very low signal-to-noise ratio, which emphasizes the differences of the explored methods. For the utilized data, it was found that the individual signal-to-noise ratio explained up to 74\% of the performance differences between subjects. While data pre-processing was shown to increase average time-series classification performance, it could not fully compensate the signal-to-noise ratio differences between the subjects. This study proposes an algorithm to prototype and benchmark pre-processing pipelines for a paradigm and data set at hand. Extreme learning machines, Random Forest, and Logistic Regression can be used quickly to compare a set of potentially suitable pipelines. For subsequent classification, however, machine learning models were shown to provide better accuracy.}, author = {Anders, Christoph and Curio, Gabriel and Arnrich, Bert and Waterstraat, Gunnar}, journal = {Taylor and Francis, Network: Computation in Neural Systems}, keywords = {christophanders bertarnrich}, note = {Publisher: Taylor \& Francis\_eprint: https://doi.org/10.1080/0954898X.2023.2263083}, number = 4, pages = {374–391}, title = {Optimization of data pre-processing methods for time-series classification of electroencephalography data}, volume = 34, year = 2023 }
HPI-DHC @ BC8 SympTEMIST Track: Detection and Normalization of Symptom Mentions with SpanMarker and xMEN. Borchert, Florian; Llorca, Ignacio; Schapranow, Matthieu-P. R. Islamaj, C. Arighi, I. Campbell, G. Gonzalez-Hernandez, L. Hirschman, M. Krallinger, S. Lima-López, D. Weissenbacher, Z. Lu (eds.) (2023).
[ BibTeX ] [ URL ] [ DOI ]
 
@inproceedings{borchert2023hpidhc, address = {New Orleans, LA}, author = {Borchert, Florian and Llorca, Ignacio and Schapranow, Matthieu-P.}, booktitle = {Proceedings of the BioCreative VIII Challenge and Workshop: Curation and Evaluation in the era of Generative Models}, editor = {Islamaj, Rezarta and Arighi, Cecilia and Campbell, Ian and Gonzalez-Hernandez, Graciela and Hirschman, Lynette and Krallinger, Martin and Lima-López, Salvador and Weissenbacher, Davy and Lu, Zhiyong}, keywords = {nlp myown gemtex}, title = {HPI-DHC @ BC8 SympTEMIST Track: Detection and Normalization of Symptom Mentions with SpanMarker and xMEN}, year = 2023 }
Overcoming Data Scarcity in Human Activity Recognition. Konak, Orhan; Liebe, Lucas; Postnov, Kirill; Sauerwald, Franz; Gjoreski, Hristijan; Luštrek, Mitja; Arnrich, Bert in IEEE EMBC 2023 (2023).
[ BibTeX ]
 
@article{konak2023overcoming, author = {Konak, Orhan and Liebe, Lucas and Postnov, Kirill and Sauerwald, Franz and Gjoreski, Hristijan and Luštrek, Mitja and Arnrich, Bert}, booktitle = {IEEE EMBC 2023}, keywords = {bertarnrich orhankonak widehealth}, organization = {IEEE EMBC}, title = {Overcoming Data Scarcity in Human Activity Recognition}, year = 2023 }
A Real-time Human Pose Estimation Approach for Optimal Sensor Placement in Sensor-based Human Activity Recognition. Konak, Orhan; Wischmann, Alexander; van De Water, Robin; Arnrich, Bert (2023). 1–6.
[ BibTeX ]
 
@inproceedings{konak2023real, author = {Konak, Orhan and Wischmann, Alexander and van De Water, Robin and Arnrich, Bert}, booktitle = {Proceedings of the 8th international Workshop on Sensor-Based Activity Recognition and Artificial Intelligence}, keywords = {bertarnrich orhankonak robinvandewater}, pages = {1–6}, title = {A Real-time Human Pose Estimation Approach for Optimal Sensor Placement in Sensor-based Human Activity Recognition}, year = 2023 }
SONAR, a nursing activity dataset with inertial sensors. Konak, Orhan; Döring, Valentin; Fiedler, Tobias; Liebe, Lucas; Masopust, Leander; Postnov, Kirill; Sauerwald, Franz; Treykorn, Felix; Wischmann, Alexander; Kalabakov, Stefan; others in Scientific Data (2023). 10(1) 727.
[ BibTeX ]
 
@article{konak2023sonar, author = {Konak, Orhan and D{ö}ring, Valentin and Fiedler, Tobias and Liebe, Lucas and Masopust, Leander and Postnov, Kirill and Sauerwald, Franz and Treykorn, Felix and Wischmann, Alexander and Kalabakov, Stefan and others}, journal = {Scientific Data}, keywords = {bertarnrich orhankonak widehealth stefankalabakov}, number = 1, pages = 727, publisher = {Nature Publishing Group UK London}, title = {SONAR, a nursing activity dataset with inertial sensors}, volume = 10, year = 2023 }
Extraction of Crohn’s Disease Clinical Phenotypes from Clinical Text Using Natural Language Processing. Schmidt, Linea; Ibing, Susanne; Borchert, Florian; Hugo, Julian; Marshall, Allison; Peraza, Jellyana; Cho, Judy H.; Böttinger, Erwin P.; Ungaro, Ryan C. in medRxiv (2023).
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Schmidt2023.10.16.23297099, author = {Schmidt, Linea and Ibing, Susanne and Borchert, Florian and Hugo, Julian and Marshall, Allison and Peraza, Jellyana and Cho, Judy H. and B{ö}ttinger, Erwin P. and Ungaro, Ryan C.}, journal = {medRxiv}, keywords = {nlp fb-boettinger}, publisher = {Cold Spring Harbor Laboratory Press}, title = {Extraction of Crohn's Disease Clinical Phenotypes from Clinical Text Using Natural Language Processing}, year = 2023 }
xMEN: A Modular Toolkit for Cross-Lingual Medical Entity Normalization. Borchert, Florian; Llorca, Ignacio; Roller, Roland; Arnrich, Bert; Schapranow, Matthieu-P. in arXiv preprint arXiv:2310.11275 (2023).
[ BibTeX ] [ URL ]
 
@article{borchert2023xmen, author = {Borchert, Florian and Llorca, Ignacio and Roller, Roland and Arnrich, Bert and Schapranow, Matthieu-P.}, journal = {arXiv preprint arXiv:2310.11275}, keywords = {nlp gemtex fb-boettinger}, title = {xMEN: A Modular Toolkit for Cross-Lingual Medical Entity Normalization}, year = 2023 }
Wearable EEG-Based Cognitive Load Classification by Personalized and Generalized Model Using Brain Asymmetry. Moontaha, Sidratul; Kappattanavar, Arpita Mallikarjuna; Hecker, Pascal; Arnrich, Bert (2023).
[ Abstract ] [ BibTeX ] [ URL ]
 
EEG measures have become prominent with the increasing popularity of non-invasive, portable EEG sensors for neuro-physiological measures to assess cognitive load. In this paper, utilizing a four-channel wearable EEG device, the brain activity data from eleven participants were recorded while watching a relaxation video and performing three cognitive load tasks. The data was pre-processed using outlier rejection based on a movement filter, spectral filtering, common average referencing, and normalization. Four frequency-domain feature sets were extracted from 30-second windows encompassing the power of δ, θ, α, β and γ frequency bands, the respective ratios, and the asymmetry features of each band. A personalized and generalized model was built for the binary classification between the relaxation and cognitive load tasks and self-reported labels. The asymmetry feature set outperformed the band ratio feature sets with a mean classification accuracy of 81.7% for the personalized model and 78% for the generalized model. A similar result for the models from the self-reported labels necessitates utilizing asymmetry features for cognitive load classification. Extracting high-level features from asymmetry features in the future may surpass the performance. Moreover, the better performance of the personalized model leads to future work to update pre-trained generalized models on personal data.
@article{moontaha2023wearable, abstract = {EEG measures have become prominent with the increasing popularity of non-invasive, portable EEG sensors for neuro-physiological measures to assess cognitive load. In this paper, utilizing a four-channel wearable EEG device, the brain activity data from eleven participants were recorded while watching a relaxation video and performing three cognitive load tasks. The data was pre-processed using outlier rejection based on a movement filter, spectral filtering, common average referencing, and normalization. Four frequency-domain feature sets were extracted from 30-second windows encompassing the power of δ, θ, α, β and γ frequency bands, the respective ratios, and the asymmetry features of each band. A personalized and generalized model was built for the binary classification between the relaxation and cognitive load tasks and self-reported labels. The asymmetry feature set outperformed the band ratio feature sets with a mean classification accuracy of 81.7% for the personalized model and 78% for the generalized model. A similar result for the models from the self-reported labels necessitates utilizing asymmetry features for cognitive load classification. Extracting high-level features from asymmetry features in the future may surpass the performance. Moreover, the better performance of the personalized model leads to future work to update pre-trained generalized models on personal data.}, author = {Moontaha, Sidratul and Kappattanavar, Arpita Mallikarjuna and Hecker, Pascal and Arnrich, Bert}, keywords = {pascalhecker bertarnrich sidratulmoontaha arpitakappattanavar}, title = {Wearable EEG-Based Cognitive Load Classification by Personalized and Generalized Model Using Brain Asymmetry}, year = 2023 }
Resolving Elliptical Compounds in German Medical Text. Kämmer, Niklas; and Borchert, Florian; and Winkler, Silvia; and de Melo, Gerard; and Schapranow, Matthieu-P. (2023). 292–305.
[ BibTeX ] [ URL ]
 
@inproceedings{kammer2023resolving, address = {Toronto, Canada}, author = {Kämmer, Niklas and and Borchert, Florian and and Winkler, Silvia and and de Melo, Gerard and and Schapranow, Matthieu-P.}, booktitle = {The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks}, keywords = {nlp myown gemtex highmed nephrocage fb-boettinger}, pages = {292-305}, publisher = {Association for Computational Linguistics}, title = {Resolving Elliptical Compounds in German Medical Text}, year = 2023 }
Lernende Laborsysteme: Wie kann künstliche Intelligenz im Labor unterstützen?. Schapranow, Matthieu-P. in Immunoassays: ergänzende Methoden, Troubleshooting, regulatorische Anforderungen, A. M. Raem, P. Rauch (eds.) (2023). 755–775.
[ BibTeX ] [ URL ] [ DOI ]
 
@inbook{Schapranow2023, address = {Berlin, Heidelberg}, author = {Schapranow, Matthieu-P.}, booktitle = {Immunoassays: ergänzende Methoden, Troubleshooting, regulatorische Anforderungen}, editor = {Raem, Arnold Maria and Rauch, Peter}, keywords = {myown}, pages = {755–775}, publisher = {Springer Berlin Heidelberg}, title = {Lernende Laborsysteme: Wie kann künstliche Intelligenz im Labor unterstützen?}, year = 2023 }
Cross-Lingual Candidate Retrieval and Re-ranking for Biomedical Entity Linking. Borchert, Florian; Llorca, Ignacio; Schapranow, Matthieu-P. A. Arampatzis, E. Kanoulas, T. Tsikrika, S. Vrochidis, A. Giachanou, D. Li, M. Aliannejadi, M. Vlachos, G. Faggioli, N. Ferro (eds.) (2023). 135–147.
[ BibTeX ] [ URL ]
 
@inproceedings{10.1007/978-3-031-42448-9_12, address = {Cham}, author = {Borchert, Florian and Llorca, Ignacio and Schapranow, Matthieu-P.}, booktitle = {Experimental IR Meets Multilinguality, Multimodality, and Interaction}, editor = {Arampatzis, Avi and Kanoulas, Evangelos and Tsikrika, Theodora and Vrochidis, Stefanos and Giachanou, Anastasia and Li, Dan and Aliannejadi, Mohammad and Vlachos, Michalis and Faggioli, Guglielmo and Ferro, Nicola}, keywords = {nlp myown gemtex nephrocage fb-boettinger}, pages = {135–147}, publisher = {Springer Nature Switzerland}, title = {Cross-Lingual Candidate Retrieval and Re-ranking for Biomedical Entity Linking}, year = 2023 }
Recommender System for Alarm Thresholds in Medical Patient Monitors. Schmidt, Denise; Chromik, Jonas; Arnrich, Bert (2023). 74–85.
[ BibTeX ] [ URL ] [ DOI ]
 
@conference{schmidt2023recommender, author = {Schmidt, Denise and Chromik, Jonas and Arnrich, Bert}, booktitle = {Proceedings of the 16th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2023) - HEALTHINF}, keywords = {bertarnrich jonaschromik}, organization = {INSTICC}, pages = {74-85}, publisher = {SciTePress}, title = {Recommender System for Alarm Thresholds in Medical Patient Monitors}, year = 2023 }
Predictive Alarm Prevention by Forecasting Threshold Alarms at the Intensive Care Unit. Chromik, Jonas; Pfitzner, Bjarne; Ihde, Nina; Michaelis, Marius; Schmidt, Denise; Klopfenstein, Sophie Anne Ines; Poncette, Akira-Sebastian; Balzer, Felix; Arnrich, Bert in Biomedical Engineering Systems and Technologies, A. C. A. Roque, D. Gracanin, R. Lorenz, A. Tsanas, N. Bier, A. Fred, H. Gamboa (eds.) (2023). (Vol. 1814) 215–236.
[ BibTeX ] [ URL ] [ DOI ]
 
@incollection{chromik2023predictive, address = {{Cham}}, author = {Chromik, Jonas and Pfitzner, Bjarne and Ihde, Nina and Michaelis, Marius and Schmidt, Denise and Klopfenstein, Sophie Anne Ines and Poncette, Akira-Sebastian and Balzer, Felix and Arnrich, Bert}, booktitle = {Biomedical {{Engineering Systems}} and {{Technologies}}}, editor = {Roque, Ana Cecília A. and Gracanin, Denis and Lorenz, Ronny and Tsanas, Athanasios and Bier, Nathalie and Fred, Ana and Gamboa, Hugo}, keywords = {bertarnrich bjarnepfitzner jonaschromik}, pages = {215–236}, publisher = {{Springer Nature Switzerland}}, title = {Predictive {{Alarm Prevention}} by {{Forecasting Threshold Alarms}} at the {{Intensive Care Unit}}}, volume = 1814, year = 2023 }
Assessing Cognitive Load in Software Development with Wearable Sensors. Stolp, Fabian (2023). 227–229.
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
https://ieeexplore.ieee.org/abstract/document/10172510
@inproceedings{10172510, abstract = {https://ieeexplore.ieee.org/abstract/document/10172510}, author = {Stolp, Fabian}, booktitle = {2023 IEEE/ACM 45th International Conference on Software Engineering: Companion Proceedings (ICSE-Companion)}, keywords = {fabianstolp}, pages = {227-229}, title = {Assessing Cognitive Load in Software Development with Wearable Sensors}, year = 2023 }
Machine Learning Based Prediction of Incident Cases of Crohn’s Disease Using Electronic Health Records from a Large Integrated Health System. Hugo, Julian; Ibing, Susanne; Borchert, Florian; Sachs, Jan Philipp; Cho, Judy; Ungaro, Ryan C.; Böttinger, Erwin P. J. M. Juarez, M. Marcos, G. Stiglic, A. Tucker (eds.) (2023). 293–302.
[ BibTeX ] [ URL ] [ DOI ]
 
@inproceedings{10.1007/978-3-031-34344-5_35, address = {Cham}, author = {Hugo, Julian and Ibing, Susanne and Borchert, Florian and Sachs, Jan Philipp and Cho, Judy and Ungaro, Ryan C. and B{ö}ttinger, Erwin P.}, booktitle = {Artificial Intelligence in Medicine}, editor = {Juarez, Jose M. and Marcos, Mar and Stiglic, Gregor and Tucker, Allan}, keywords = {fb-boettinger}, pages = {293–302}, publisher = {Springer Nature Switzerland}, title = {Machine Learning Based Prediction of Incident Cases of Crohn's Disease Using Electronic Health Records from a Large Integrated Health System}, year = 2023 }
Design, Implementation and Evaluation of an Air Quality Sonification System. Terboven, Carla; Panourgia, Eleni-Ira; Arnrich, Bert; Steckhan, Nico (2023).
[ BibTeX ] [ URL ]
 
@misc{icad, author = {Terboven, Carla and Panourgia, Eleni-Ira and Arnrich, Bert and Steckhan, Nico}, keywords = {nicosteckhan bertarnrich}, title = {Design, Implementation and Evaluation of an Air Quality Sonification System}, year = 2023 }
Disease- and sex-specific differences in patients with heart valve disease: A proteome study. Nordmeyer, S; Kraus, M; Ziehm, M; Kirchner, M; Schafstedde, M; Kelm, M; Niquet, S; Stephen, MM; Baczko, I; Knosalla, C; Schapranow, M-P; Dittmar, G; Gotthardt, M; Falcke, M; Regitz-Zagrosek, V; Kuehne, T; Mertins, P in Life Sci Alliance (2023). 6(3) e202201411.
[ BibTeX ] [ DOI ]
 
@article{s2022disease, author = {Nordmeyer, S and Kraus, M and Ziehm, M and Kirchner, M and Schafstedde, M and Kelm, M and Niquet, S and Stephen, MM and Baczko, I and Knosalla, C and Schapranow, M-P and Dittmar, G and Gotthardt, M and Falcke, M and Regitz-Zagrosek, V and Kuehne, T and Mertins, P}, journal = {Life Sci Alliance}, keywords = {myown SMART}, month = {jan}, number = 3, pages = {e202201411}, title = {Disease- and sex-specific differences in patients with heart valve disease: A proteome study.}, volume = 6, year = 2023 }
Triangulation of Questionnaires, Qualitative Data and Natural Language Processing: A Differential Approach to Religious Bahá’í Fasting in Germany. Steckhan, Nico; Ring, Raphaela; Borchert, Florian; Koppold, Daniela A. in Journal of Religion and Health (2023).
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
Approaches to integrating mixed methods into medical research are gaining popularity. To get a holistic understanding of the effects of behavioural interventions, we investigated religious fasting using a triangulation of quantitative, qualitative, and natural language analysis. We analysed an observational study of Bahá'í fasting in Germany using a between-method triangulation that is based on links between qualitative and quantitative analyses. Individual interviews show an increase in the mindfulness and well-being categories. Sentiment scores, extracted from the interviews through natural language processing, positively correlate with questionnaire outcomes on quality of life (WHO-5: Spearman correlation r = 0.486, p = 0.048). Five questionnaires contribute to the first principal component capturing the spectrum of mood states (50.1% explained variance). Integrating the findings of the between-method triangulation enabled us to converge on the underlying effects of this kind of intermittent fasting.
@article{steckhan2023triangulation, abstract = {Approaches to integrating mixed methods into medical research are gaining popularity. To get a holistic understanding of the effects of behavioural interventions, we investigated religious fasting using a triangulation of quantitative, qualitative, and natural language analysis. We analysed an observational study of Bahá'í fasting in Germany using a between-method triangulation that is based on links between qualitative and quantitative analyses. Individual interviews show an increase in the mindfulness and well-being categories. Sentiment scores, extracted from the interviews through natural language processing, positively correlate with questionnaire outcomes on quality of life (WHO-5: Spearman correlation r = 0.486, p = 0.048). Five questionnaires contribute to the first principal component capturing the spectrum of mood states (50.1% explained variance). Integrating the findings of the between-method triangulation enabled us to converge on the underlying effects of this kind of intermittent fasting.}, author = {Steckhan, Nico and Ring, Raphaela and Borchert, Florian and Koppold, Daniela A.}, journal = {Journal of Religion and Health}, keywords = {nlp}, title = {Triangulation of Questionnaires, Qualitative Data and Natural Language Processing: A Differential Approach to Religious Bahá’í Fasting in Germany}, year = 2023 }
GGTWEAK: Gene Tagging with Weak Supervision for German Clinical Text. Steinwand, Sandro; Borchert, Florian; Winkler, Silvia; Schapranow, Matthieu-P. J. M. Juarez, M. Marcos, G. Stiglic, A. Tucker (eds.) (2023). 183–192.
[ BibTeX ] [ URL ] [ DOI ]
 
@inproceedings{10.1007/978-3-031-34344-5_22, address = {Cham}, author = {Steinwand, Sandro and Borchert, Florian and Winkler, Silvia and Schapranow, Matthieu-P.}, booktitle = {Artificial Intelligence in Medicine}, editor = {Juarez, Jose M. and Marcos, Mar and Stiglic, Gregor and Tucker, Allan}, keywords = {nlp myown highmed fb-boettinger}, pages = {183–192}, publisher = {Springer Nature Switzerland}, title = {GGTWEAK: Gene Tagging with Weak Supervision for German Clinical Text}, year = 2023 }
Software-Tool Support for Collaborative, Virtual, Multi-Site Molecular Tumor Boards. Schapranow, Matthieu-P; Borchert, Florian; Bougatf, Nina; Hund, Hauke; Eils, Roland in SN Computer Science (2023). 4(4) 358.
[ BibTeX ] [ URL ]
 
@article{schapranow2023software, author = {Schapranow, Matthieu-P and Borchert, Florian and Bougatf, Nina and Hund, Hauke and Eils, Roland}, journal = {SN Computer Science}, keywords = {highmed fb-boettinger}, number = 4, pages = 358, publisher = {Springer}, title = {Software-Tool Support for Collaborative, Virtual, Multi-Site Molecular Tumor Boards}, volume = 4, year = 2023 }
Programming techniques for improving rule readability for rule-based information extraction natural language processing pipelines of unstructured and semi-structured medical texts. Ladas, Nektarios; Borchert, Florian; Franz, Stefan; Rehberg, Alina; Strauch, Natalia; Sommer, Kim Katrin; Marschollek, Michael; Gietzelt, Matthias in Health Informatics Journal (2023). 29(2) 14604582231164696.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{doi:10.1177/14604582231164696, author = {Ladas, Nektarios and Borchert, Florian and Franz, Stefan and Rehberg, Alina and Strauch, Natalia and Sommer, Kim Katrin and Marschollek, Michael and Gietzelt, Matthias}, journal = {Health Informatics Journal}, keywords = {nlp myown highmed fb-boettinger}, note = {PMID: 37068028}, number = 2, pages = 14604582231164696, title = {Programming techniques for improving rule readability for rule-based information extraction natural language processing pipelines of unstructured and semi-structured medical texts}, volume = 29, year = 2023 }
KI für Gesundheitsfachkräfte: Chancen und Herausforderungen von medizinischen und pflegerischen KI-Anwendungen. Technical Report (2), Budde, Klemens; Hiltawsky, Karsten; Eskofier, Björn; Heismann, Björn; Kirchner, Elsa; Klevesath, Manfred; Lang, Maren; Loskill, Hannelore; Neumuth, Thomas; Schapranow, Matthieu-P.; Schmidt-Rumposch, Andrea; Susec, Barbara; Welskop-Deffaa, Eva Maria; Wolf-Ostermann, Karin (2023).
[ BibTeX ] [ URL ] [ DOI ]
 
@techreport{budde2023gesundheitsfachkrfte, author = {Budde, Klemens and Hiltawsky, Karsten and Eskofier, Björn and Heismann, Björn and Kirchner, Elsa and Klevesath, Manfred and Lang, Maren and Loskill, Hannelore and Neumuth, Thomas and Schapranow, Matthieu-P. and Schmidt-Rumposch, Andrea and Susec, Barbara and Welskop-Deffaa, Eva Maria and Wolf-Ostermann, Karin}, institution = {Plattform Lernende Systeme}, keywords = {myown pls}, month = {apr}, number = 2, title = {KI für Gesundheitsfachkräfte: Chancen und Herausforderungen von medizinischen und pflegerischen KI-Anwendungen}, type = {Publication}, year = 2023 }
A Distributable German Clinical Corpus Containing Cardiovascular Clinical Routine Doctor’s Letters. Richter-Pechanski, Phillip; Wiesenbach, Philipp; Schwab, Dominic M.; Kiriakou, Christina; He, Mingyang; Allers, Michael M.; Tiefenbacher, Anna S.; Kunz, Nicola; Martynova, Anna; Spiller, Noemie; Mierisch, Julian; Borchert, Florian; Schwind, Charlotte; Frey, Norbert; Dieterich, Christoph; Geis, Nicolas A. in Scientific Data (2023). 10(1) 207.
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
We present CARDIO:DE, the first freely available and distributable large German clinical corpus from the cardiovascular domain. CARDIO:DE encompasses 500 clinical routine German doctor's letters from Heidelberg University Hospital, which were manually annotated. Our prospective study design complies well with current data protection regulations and allows us to keep the original structure of clinical documents consistent. In order to ease access to our corpus, we manually de-identified all letters. To enable various information extraction tasks the temporal information in the documents was preserved. We added two high-quality manual annotation layers to CARDIO:DE, (1) medication information and (2) CDA-compliant section classes. To the best of our knowledge, CARDIO:DE is the first freely available and distributable German clinical corpus in the cardiovascular domain. In summary, our corpus offers unique opportunities for collaborative and reproducible research on natural language processing models for German clinical texts.
@article{richter-pechanskiDistributableGermanClinical2023, abstract = {We present CARDIO:DE, the first freely available and distributable large German clinical corpus from the cardiovascular domain. CARDIO:DE encompasses 500 clinical routine German doctor's letters from Heidelberg University Hospital, which were manually annotated. Our prospective study design complies well with current data protection regulations and allows us to keep the original structure of clinical documents consistent. In order to ease access to our corpus, we manually de-identified all letters. To enable various information extraction tasks the temporal information in the documents was preserved. We added two high-quality manual annotation layers to CARDIO:DE, (1) medication information and (2) CDA-compliant section classes. To the best of our knowledge, CARDIO:DE is the first freely available and distributable German clinical corpus in the cardiovascular domain. In summary, our corpus offers unique opportunities for collaborative and reproducible research on natural language processing models for German clinical texts.}, author = {{Richter-Pechanski}, Phillip and Wiesenbach, Philipp and Schwab, Dominic M. and Kiriakou, Christina and He, Mingyang and Allers, Michael M. and Tiefenbacher, Anna S. and Kunz, Nicola and Martynova, Anna and Spiller, Noemie and Mierisch, Julian and Borchert, Florian and Schwind, Charlotte and Frey, Norbert and Dieterich, Christoph and Geis, Nicolas A.}, journal = {Scientific Data}, keywords = {nlp myown highmed fb-boettinger}, month = {apr}, number = 1, pages = 207, title = {A Distributable {{German}} Clinical Corpus Containing Cardiovascular Clinical Routine Doctor's Letters}, volume = 10, year = 2023 }
DUO-GAIT: A gait dataset for walking under dual-task and fatigue conditions with inertial measurement units. Zhou, Lin; Fischer, Eric; Brahms, Clemens Markus; Granacher, Urs; Arnrich, Bert (2023).
[ BibTeX ]
 
@article{noauthororeditor2023duogait, author = {Zhou, Lin and Fischer, Eric and Brahms, Clemens Markus and Granacher, Urs and Arnrich, Bert}, keywords = {linzhou bertarnrich}, title = {DUO-GAIT: A gait dataset for walking under dual-task and fatigue conditions with inertial measurement units}, year = 2023 }

2022

KI-Systeme schützen, Missbrauch verhindern: Maßnahmen und Szenarien in fünf Anwendungsgebieten. Technical Report (2), Beyerer, Jürgen; Müller-Quade, Jörn; Albers, Albert; Houdeau, Detlef; Tchouchenkov, Igor; Dzaack, Jeronimo; Schapranow, Matthieu-P.; Reiner, Nadine; Neuburger, Railed; Stowasser, Sascha; Rapp, Simon; Terstegen, Sebastian (2022).
[ BibTeX ] [ DOI ]
 
@techreport{beyerer2022kisysteme, author = {Beyerer, Jürgen and Müller-Quade, Jörn and Albers, Albert and Houdeau, Detlef and Tchouchenkov, Igor and Dzaack, Jeronimo and Schapranow, Matthieu-P. and Reiner, Nadine and Neuburger, Railed and Stowasser, Sascha and Rapp, Simon and Terstegen, Sebastian}, howpublished = {https://doi.org/10.48669/pls_2022-2}, institution = {Plattform Lernende Systeme}, keywords = {myown pls}, month = {mar}, number = 2, title = {KI-Systeme schützen, Missbrauch verhindern: Maßnahmen und Szenarien in fünf Anwendungsgebieten}, year = 2022 }
StudyU: A Platform for Designing and Conducting Innovative Digital N-of-1 Trials. Konigorski, Stefan; Wernicke, Sarah; Slosarek, Tamara; Zenner, Alexander M; Strelow, Nils; Ruether, Darius F; Henschel, Florian; Manaswini, Manisha; Pottbäcker, Fabian; Edelman, Jonathan A; Owoyele, Babajide; Danieletto, Matteo; Golden, Eddye; Zweig, Micol; Nadkarni, Girish N; Böttinger, Erwin in J Med Internet Res (2022). 24(7) e35884.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{info:doi/10.2196/35884, author = {Konigorski, Stefan and Wernicke, Sarah and Slosarek, Tamara and Zenner, Alexander M and Strelow, Nils and Ruether, Darius F and Henschel, Florian and Manaswini, Manisha and Pottbäcker, Fabian and Edelman, Jonathan A and Owoyele, Babajide and Danieletto, Matteo and Golden, Eddye and Zweig, Micol and Nadkarni, Girish N and Böttinger, Erwin}, journal = {J Med Internet Res}, keywords = {myown}, month = {jul}, number = 7, pages = {e35884}, title = {StudyU: A Platform for Designing and Conducting Innovative Digital N-of-1 Trials}, volume = 24, year = 2022 }
PERSIST: A Multimodal Dataset for the Prediction of Perceived Exertion during Resistance Training. Albert, Justin Amadeus; Herdick, Arne; Brahms, Clemens Markus; Granacher, Urs; Arnrich, Bert in Data (2022). 8(1)
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
Measuring and adjusting the training load is essential in resistance training, as training overload can increase the risk of injuries. At the same time, too little load does not deliver the desired training effects. Usually, external load is quantified using objective measurements, such as lifted weight distributed across sets and repetitions per exercise. Internal training load is usually assessed using questionnaires or ratings of perceived exertion (RPE). A standard RPE scale is the Borg scale, which ranges from 6 (no exertion) to 20 (the highest exertion ever experienced). Researchers have investigated predicting RPE for different sports using sensor modalities and machine learning methods, such as Support Vector Regression or Random Forests. This paper presents PERSIST, a novel dataset for predicting PERceived exertion during reSIStance Training. We recorded multiple sensor modalities simultaneously, including inertial measurement units (IMU), electrocardiography (ECG), and motion capture (MoCap). The MoCap data has been synchronized to the IMU and ECG data. We also provide heart rate variability (HRV) parameters obtained from the ECG signal. Our dataset contains data from twelve young and healthy male participants with at least one year of resistance training experience. Subjects performed twelve sets of squats on a Flywheel platform with twelve repetitions per set. After each set, subjects reported their current RPE. We chose the squat exercise as it involves the largest muscle group. This paper demonstrates how to access the dataset. We further present an exploratory data analysis and show how researchers can use IMU and ECG data to predict perceived exertion.
@article{data8010009, abstract = {Measuring and adjusting the training load is essential in resistance training, as training overload can increase the risk of injuries. At the same time, too little load does not deliver the desired training effects. Usually, external load is quantified using objective measurements, such as lifted weight distributed across sets and repetitions per exercise. Internal training load is usually assessed using questionnaires or ratings of perceived exertion (RPE). A standard RPE scale is the Borg scale, which ranges from 6 (no exertion) to 20 (the highest exertion ever experienced). Researchers have investigated predicting RPE for different sports using sensor modalities and machine learning methods, such as Support Vector Regression or Random Forests. This paper presents PERSIST, a novel dataset for predicting PERceived exertion during reSIStance Training. We recorded multiple sensor modalities simultaneously, including inertial measurement units (IMU), electrocardiography (ECG), and motion capture (MoCap). The MoCap data has been synchronized to the IMU and ECG data. We also provide heart rate variability (HRV) parameters obtained from the ECG signal. Our dataset contains data from twelve young and healthy male participants with at least one year of resistance training experience. Subjects performed twelve sets of squats on a Flywheel platform with twelve repetitions per set. After each set, subjects reported their current RPE. We chose the squat exercise as it involves the largest muscle group. This paper demonstrates how to access the dataset. We further present an exploratory data analysis and show how researchers can use IMU and ECG data to predict perceived exertion.}, author = {Albert, Justin Amadeus and Herdick, Arne and Brahms, Clemens Markus and Granacher, Urs and Arnrich, Bert}, journal = {Data}, keywords = {justinalbert bertarnrich arneherdick}, number = 1, title = {PERSIST: A Multimodal Dataset for the Prediction of Perceived Exertion during Resistance Training}, volume = 8, year = 2022 }
What Actually Works for Activity Recognition in Scenarios with Significant Domain Shift: Lessons Learned from the 2019 and 2020 Sussex-Huawei Challenges. Kalabakov, Stefan; Stankoski, Simon; Kiprijanovska, Ivana; Andova, Andrejaana; Reščič, Nina; Janko, Vito; Gjoreski, Martin; Gams, Matjaž; Luštrek, Mitja in Sensors (2022). 22 3613.
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
From 2018 to 2021, the Sussex-Huawei Locomotion-Transportation Recognition Challenge presented different scenarios in which participants were tasked with recognizing eight different modes of locomotion and transportation using sensor data from smartphones. In 2019, the main challenge was using sensor data from one location to recognize activities with sensors in another location, while in the following year, the main challenge was using the sensor data of one person to recognize the activities of other persons. We use these two challenge scenarios as a framework in which to analyze the effectiveness of different components of a machine-learning pipeline for activity recognition. We show that: (i) selecting an appropriate (location-specific) portion of the available data for training can improve the F1 score by up to 10 percentage points (p. p.) compared to a more naive approach, (ii) separate models for human locomotion and for transportation in vehicles can yield an increase of roughly 1 p. p., (iii) using semi-supervised learning can, again, yield an increase of roughly 1 p. p., and (iv) temporal smoothing of predictions with Hidden Markov models, when applicable, can bring an improvement of almost 10 p. p. Our experiments also indicate that the usefulness of advanced feature selection techniques and clustering to create person-specific models is inconclusive and should be explored separately in each use-case.
@article{kalabakov2022actually, abstract = {From 2018 to 2021, the Sussex-Huawei Locomotion-Transportation Recognition Challenge presented different scenarios in which participants were tasked with recognizing eight different modes of locomotion and transportation using sensor data from smartphones. In 2019, the main challenge was using sensor data from one location to recognize activities with sensors in another location, while in the following year, the main challenge was using the sensor data of one person to recognize the activities of other persons. We use these two challenge scenarios as a framework in which to analyze the effectiveness of different components of a machine-learning pipeline for activity recognition. We show that: (i) selecting an appropriate (location-specific) portion of the available data for training can improve the F1 score by up to 10 percentage points (p. p.) compared to a more naive approach, (ii) separate models for human locomotion and for transportation in vehicles can yield an increase of roughly 1 p. p., (iii) using semi-supervised learning can, again, yield an increase of roughly 1 p. p., and (iv) temporal smoothing of predictions with Hidden Markov models, when applicable, can bring an improvement of almost 10 p. p. Our experiments also indicate that the usefulness of advanced feature selection techniques and clustering to create person-specific models is inconclusive and should be explored separately in each use-case.}, author = {Kalabakov, Stefan and Stankoski, Simon and Kiprijanovska, Ivana and Andova, Andrejaana and Reščič, Nina and Janko, Vito and Gjoreski, Martin and Gams, Matjaž and Luštrek, Mitja}, journal = {Sensors}, keywords = {bertarnrich prior-hpi kalabakovstefan}, pages = 3613, series = 10, title = {What Actually Works for Activity Recognition in Scenarios with Significant Domain Shift: Lessons Learned from the 2019 and 2020 Sussex-Huawei Challenges}, volume = 22, year = 2022 }
Defending against Reconstruction Attacks through Differentially Private Federated Learning for Classification of Heterogeneous Chest X-ray Data. Ziegler, Joceline; Pfitzner, Bjarne; Schulz, Heinrich; Saalbach, Axel; Arnrich, Bert in Sensors, (F. Marulli; L. Verde, eds.) (2022). 22(14)
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
Privacy regulations and the physical distribution of heterogeneous data are often primary concerns for the development of deep learning models in a medical context. This paper evaluates the feasibility of differentially private federated learning for chest X-ray classification as a defense against data privacy attacks. To the best of our knowledge, we are the first to directly compare the impact of differentially private training on two different neural network architectures, DenseNet121 and ResNet50. Extending the federated learning environments previously analyzed in terms of privacy, we simulated a heterogeneous and imbalanced federated setting by distributing images from the public CheXpert and Mendeley chest X-ray datasets unevenly among 36 clients. Both non-private baseline models achieved an area under the receiver operating characteristic curve (AUC) of 0.94 on the binary classification task of detecting the presence of a medical finding. We demonstrate that both model architectures are vulnerable to privacy violation by applying image reconstruction attacks to local model updates from individual clients. The attack was particularly successful during later training stages. To mitigate the risk of a privacy breach, we integrated Rényi differential privacy with a Gaussian noise mechanism into local model training. We evaluate model performance and attack vulnerability for privacy budgets ε∈1,3,6,10. The DenseNet121 achieved the best utility-privacy trade-off with an AUC of 0.94 for ε=6. Model performance deteriorated slightly for individual clients compared to the non-private baseline. The ResNet50 only reached an AUC of 0.76 in the same privacy setting. Its performance was inferior to that of the DenseNet121 for all considered privacy constraints, suggesting that the DenseNet121 architecture is more robust to differentially private training.
@article{ziegler2022defending, abstract = {Privacy regulations and the physical distribution of heterogeneous data are often primary concerns for the development of deep learning models in a medical context. This paper evaluates the feasibility of differentially private federated learning for chest X-ray classification as a defense against data privacy attacks. To the best of our knowledge, we are the first to directly compare the impact of differentially private training on two different neural network architectures, DenseNet121 and ResNet50. Extending the federated learning environments previously analyzed in terms of privacy, we simulated a heterogeneous and imbalanced federated setting by distributing images from the public CheXpert and Mendeley chest X-ray datasets unevenly among 36 clients. Both non-private baseline models achieved an area under the receiver operating characteristic curve (AUC) of 0.94 on the binary classification task of detecting the presence of a medical finding. We demonstrate that both model architectures are vulnerable to privacy violation by applying image reconstruction attacks to local model updates from individual clients. The attack was particularly successful during later training stages. To mitigate the risk of a privacy breach, we integrated Rényi differential privacy with a Gaussian noise mechanism into local model training. We evaluate model performance and attack vulnerability for privacy budgets ε∈{1,3,6,10}. The DenseNet121 achieved the best utility-privacy trade-off with an AUC of 0.94 for ε=6. Model performance deteriorated slightly for individual clients compared to the non-private baseline. The ResNet50 only reached an AUC of 0.76 in the same privacy setting. Its performance was inferior to that of the DenseNet121 for all considered privacy constraints, suggesting that the DenseNet121 architecture is more robust to differentially private training.}, author = {Ziegler, Joceline and Pfitzner, Bjarne and Schulz, Heinrich and Saalbach, Axel and Arnrich, Bert}, editor = {Marulli, Fiammetta and Verde, Laura}, journal = {Sensors}, keywords = {bertarnrich bjarnepfitzner}, number = 14, title = {Defending against Reconstruction Attacks through Differentially Private Federated Learning for Classification of Heterogeneous Chest X-ray Data}, volume = 22, year = 2022 }
Elements of a System for Automatic Monitoring of Specific Mental Health Characteristics at Home. Kirsten, Kristina; Arnrich, Bert (2022).
[ Abstract ] [ BibTeX ] [ URL ]
 
Addressing one’s mental health has never been more important. The incidences of mental diseases, such as depression or anxiety disorders, have drastically increased in recent years. The longer an adequate treatment is delayed, the greater the impact on the severity of the illness which often results in long absences from work. With the development of smart devices and wearables, it is already possible to measure many physiological parameters in everyday life. In addition, monitoring people in their natural environment offers many advantages, e.g. it is not based on retrospective feelings and memories but can measure and reflect the momentary state. This conceptual paper presents an overview of possible elements of a system for automated monitoring of mental health characteristics in the home. We describe examples of typical parameters for various mental disorders and present different systems and methods to measure them. Furthermore, we show how the individual components of a system can be connected to get a holistic view of specific mental health characteristics. Finally, we also discuss challenges and limitations.
@conference{kirsten_arnrich_2022, abstract = {Addressing one’s mental health has never been more important. The incidences of mental diseases, such as depression or anxiety disorders, have drastically increased in recent years. The longer an adequate treatment is delayed, the greater the impact on the severity of the illness which often results in long absences from work. With the development of smart devices and wearables, it is already possible to measure many physiological parameters in everyday life. In addition, monitoring people in their natural environment offers many advantages, e.g. it is not based on retrospective feelings and memories but can measure and reflect the momentary state. This conceptual paper presents an overview of possible elements of a system for automated monitoring of mental health characteristics in the home. We describe examples of typical parameters for various mental disorders and present different systems and methods to measure them. Furthermore, we show how the individual components of a system can be connected to get a holistic view of specific mental health characteristics. Finally, we also discuss challenges and limitations.}, author = {Kirsten, Kristina and Arnrich, Bert}, booktitle = {Proceedings of the 25th International Multiconference Information Society 2022, IS 2022, Ljubljana, Slovenia}, keywords = {bertarnrich kristinakirsten}, title = {Elements of a System for Automatic Monitoring of Specific Mental Health Characteristics at Home}, year = 2022 }
Quantifying Cognitive Load from Voice using Transformer-Based Models and a Cross-Dataset Evaluation. Hecker, Pascal; Kappattanavar, Arpita M; Schmitt, Maximilian; Moontaha, Sidratul; Wagner, Johannes; Eyben, Florian; Schuller, Björn W; Arnrich, Bert (2022). 337–344.
[ BibTeX ]
 
@inproceedings{hecker2022quantifying, author = {Hecker, Pascal and Kappattanavar, Arpita M and Schmitt, Maximilian and Moontaha, Sidratul and Wagner, Johannes and Eyben, Florian and Schuller, Bj{ö}rn W and Arnrich, Bert}, booktitle = {2022 21st IEEE International Conference on Machine Learning and Applications (ICMLA)}, keywords = {sidratulmoontaha}, organization = {IEEE}, pages = {337–344}, title = {Quantifying Cognitive Load from Voice using Transformer-Based Models and a Cross-Dataset Evaluation}, year = 2022 }
Towards Multi-Modal Recordings in Daily Life: A Baseline Assessment of an Experimental Frame- work. Moontaha, Sidratul; Anders, Christoph; Arnrich, Bert (2022). 27–30.
[ BibTeX ] [ URL ]
 
@conference{moontaha2022towards, author = {Moontaha, Sidratul and Anders, Christoph and Arnrich, Bert}, keywords = {sidratulmoontaha}, pages = {27-30}, title = {Towards Multi-Modal Recordings in Daily Life: A Baseline Assessment of an Experimental Frame- work.}, year = 2022 }
Travelers’ information need in automated vehicles-a psychophysiological analysis. Brandebusemeyer, Charlotte; Ihme, Klas; Bosch, Esther (2022). 1–6.
[ BibTeX ]
 
@inproceedings{brandebusemeyer2022travelers, author = {Brandebusemeyer, Charlotte and Ihme, Klas and Bosch, Esther}, booktitle = {2022 Human-Centered Cognitive Systems (HCCS)}, keywords = {charlottebrandebusemeyer}, organization = {IEEE}, pages = {1–6}, title = {Travelers' information need in automated vehicles-a psychophysiological analysis}, year = 2022 }
SensorHub: Multimodal Sensing in Real-Life Enables Home-Based Studies. Chromik, Jonas; Kirsten, Kristina; Herdick, Arne; Kappattanavar, Arpita Mallikarjuna; Arnrich, Bert in Sensors (2022). 22(1)
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
Observational studies are an important tool for determining whether the findings from controlled experiments can be transferred into scenarios that are closer to subjects’ real-life circumstances. A rigorous approach to observational studies involves collecting data from different sensors to comprehensively capture the situation of the subject. However, this leads to technical difficulties especially if the sensors are from different manufacturers, as multiple data collection tools have to run simultaneously. We present SensorHub, a system that can collect data from various wearable devices from different manufacturers, such as inertial measurement units, portable electrocardiographs, portable electroencephalographs, portable photoplethysmographs, and sensors for electrodermal activity. Additionally, our tool offers the possibility to include ecological momentary assessments (EMAs) in studies. Hence, SensorHub enables multimodal sensor data collection under real-world conditions and allows direct user feedback to be collected through questionnaires, enabling studies at home. In a first study with 11 participants, we successfully used SensorHub to record multiple signals with different devices and collected additional information with the help of EMAs. In addition, we evaluated SensorHub’s technical capabilities in several trials with up to 21 participants recording simultaneously using multiple sensors with sampling frequencies as high as 1000 Hz. We could show that although there is a theoretical limitation to the transmissible data rate, in practice this limitation is not an issue and data loss is rare. We conclude that with modern communication protocols and with the increasingly powerful smartphones and wearables, a system like our SensorHub establishes an interoperability framework to adequately combine consumer-grade sensing hardware which enables observational studies in real life.
@article{s22010408, abstract = {Observational studies are an important tool for determining whether the findings from controlled experiments can be transferred into scenarios that are closer to subjects’ real-life circumstances. A rigorous approach to observational studies involves collecting data from different sensors to comprehensively capture the situation of the subject. However, this leads to technical difficulties especially if the sensors are from different manufacturers, as multiple data collection tools have to run simultaneously. We present SensorHub, a system that can collect data from various wearable devices from different manufacturers, such as inertial measurement units, portable electrocardiographs, portable electroencephalographs, portable photoplethysmographs, and sensors for electrodermal activity. Additionally, our tool offers the possibility to include ecological momentary assessments (EMAs) in studies. Hence, SensorHub enables multimodal sensor data collection under real-world conditions and allows direct user feedback to be collected through questionnaires, enabling studies at home. In a first study with 11 participants, we successfully used SensorHub to record multiple signals with different devices and collected additional information with the help of EMAs. In addition, we evaluated SensorHub’s technical capabilities in several trials with up to 21 participants recording simultaneously using multiple sensors with sampling frequencies as high as 1000 Hz. We could show that although there is a theoretical limitation to the transmissible data rate, in practice this limitation is not an issue and data loss is rare. We conclude that with modern communication protocols and with the increasingly powerful smartphones and wearables, a system like our SensorHub establishes an interoperability framework to adequately combine consumer-grade sensing hardware which enables observational studies in real life.}, author = {Chromik, Jonas and Kirsten, Kristina and Herdick, Arne and Kappattanavar, Arpita Mallikarjuna and Arnrich, Bert}, journal = {Sensors}, keywords = {bertarnrich jonaschromik kristinakirsten arpitakappattanavar}, number = 1, title = {SensorHub: Multimodal Sensing in Real-Life Enables Home-Based Studies}, volume = 22, year = 2022 }
CLUZH at SIGMORPHON 2022 Shared Tasks on Morpheme Segmentation and Inflection Generation. Wehrli, Silvan; Clematide, Simon; Makarov, Peter (2022).
[ BibTeX ] [ URL ] [ DOI ]
 
@inproceedings{wehrli2022cluzh, author = {Wehrli, Silvan and Clematide, Simon and Makarov, Peter}, booktitle = {Proceedings of the 19th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology}, keywords = {silvanwehrli bertarnrich}, title = {{CLUZH} at {SIGMORPHON} 2022 Shared Tasks on Morpheme Segmentation and Inflection Generation}, year = 2022 }
Quantifying Cognitive Load from Voice using Transformer-Based Models and a Cross-Dataset Evaluation. Hecker, Pascal; Kappattanavar, Arpita M.; Schmitt, Maximilian; Moontaha, Sidratul; Wagner, Johannes; Eyben, Florian; Schuller, Björn W.; Arnrich, Bert (2022). 337–344.
[ Abstract ] [ BibTeX ] [ DOI ]
 
Cognitive load is frequently induced in laboratory setups to measure responses to stress, and its impact on voice has been studied in the field of computational paralinguistics. One dataset on this topic was provided in the Computational Paralinguistics Challenge (ComParE) 2014, and therefore offers great comparability. Recently, transformer-based deep learning architectures established a new state-of-the-art and are finding their way gradually into the audio domain. In this context, we investigate the performance of popular transformer architectures in the audio domain on the ComParE 2014 dataset, and the impact of different pre-training and fine-tuning setups on these models. Further, we recorded a small custom dataset, designed to be comparable with the ComParE 2014 one, to assess cross-corpus model generalisability. We find that the transformer models outperform the challenge baseline, the challenge winner, and more recent deep learning approaches. Models based on the ‘large’ architecture perform well on the task at hand, while models based on the ‘base’ architecture perform at chance level. Fine-tuning on related domains (such as ASR or emotion), before fine-tuning on the targets, yields no higher performance compared to models pre-trained only in a self-supervised manner. The generalisability of the models between datasets is more intricate than expected, as seen in an unexpected low performance on the small custom dataset, and we discuss potential ‘hidden’ underlying discrepancies between the datasets. In summary, transformer-based architectures outperform previous attempts to quantify cognitive load from voice. This is promising, in particular for healthcare-related problems in computational paralinguistics applications, since datasets are sparse in that realm.
@inproceedings{hecker2022quantifying, abstract = {Cognitive load is frequently induced in laboratory setups to measure responses to stress, and its impact on voice has been studied in the field of computational paralinguistics. One dataset on this topic was provided in the Computational Paralinguistics Challenge (ComParE) 2014, and therefore offers great comparability. Recently, transformer-based deep learning architectures established a new state-of-the-art and are finding their way gradually into the audio domain. In this context, we investigate the performance of popular transformer architectures in the audio domain on the ComParE 2014 dataset, and the impact of different pre-training and fine-tuning setups on these models. Further, we recorded a small custom dataset, designed to be comparable with the ComParE 2014 one, to assess cross-corpus model generalisability. We find that the transformer models outperform the challenge baseline, the challenge winner, and more recent deep learning approaches. Models based on the ‘large’ architecture perform well on the task at hand, while models based on the ‘base’ architecture perform at chance level. Fine-tuning on related domains (such as ASR or emotion), before fine-tuning on the targets, yields no higher performance compared to models pre-trained only in a self-supervised manner. The generalisability of the models between datasets is more intricate than expected, as seen in an unexpected low performance on the small custom dataset, and we discuss potential ‘hidden’ underlying discrepancies between the datasets. In summary, transformer-based architectures outperform previous attempts to quantify cognitive load from voice. This is promising, in particular for healthcare-related problems in computational paralinguistics applications, since datasets are sparse in that realm.}, author = {Hecker, Pascal and Kappattanavar, Arpita M. and Schmitt, Maximilian and Moontaha, Sidratul and Wagner, Johannes and Eyben, Florian and Schuller, Björn W. and Arnrich, Bert}, booktitle = {2022 21st IEEE International Conference on Machine Learning and Applications (ICMLA)}, keywords = {pascalhecker bertarnrich sidratulmoontaha arpitakappattanavar}, month = {dec}, pages = {337-344}, title = {Quantifying Cognitive Load from Voice using Transformer-Based Models and a Cross-Dataset Evaluation}, year = 2022 }
Farm Your ML-based Query Optimizer’s Food - Human-Guided Training Data Generation. van de Water, Robin; Ventura, Francesco; Kaoudi, Z; Quiane-Ruiz, J; Markl, Volker (2022).
[ BibTeX ] [ URL ]
 
@inproceedings{vandewaterFarmYourMLbased2022, author = {{van de Water}, Robin and Ventura, Francesco and Kaoudi, Z and {Quiane-Ruiz}, J and Markl, Volker}, booktitle = {Conference on {{Innovative Data Systems Research}} ({{CIDR}})}, keywords = {prior-hpi robinvandewater}, title = {Farm Your ML-based Query Optimizer's Food - Human-Guided Training Data Generation}, year = 2022 }
Farming Your ML-based Query Optimizer’s Food. Van De Water, Robin; Ventura, Francesco; Kaoudi, Zoi; Quiané-Ruiz, Jorge-Arnulfo; Markl, Volker (2022). 3186–3189.
[ Abstract ] [ BibTeX ] [ URL ]
 
Machine learning (ML) is becoming a core component in query optimizers, e.g., to estimate costs or cardinalities. This means large heterogeneous sets of labeled query plans or jobs (i.e., plans with their runtime or cardinality output) are needed. However, collecting such a training dataset is a very tedious and time-consuming task: It requires both developing numerous jobs and executing them to acquire ground-truth labels. We demonstrate Datafarm,a novel framework for efficiently generating and labeling training data for ML-based query optimizers to overcome these issues. Datafarmenables generating training data tailored to users' needs by learning from their existing workload patterns, input data, and computational resources. It uses an active learning approach to determine a subset of jobs to be executed and encloses the human into the loop, resulting in higher quality data. The graphical user interface of Datafarmallows users to get informative details of the generated jobs and guides them through the generation process step-by-step. We show how users can intervene and provide feedback to the system in an iterative fashion. As an output, users can download both the generated jobs to use as a benchmark and the training data (jobs with their labels).
@inproceedings{vandewaterFarmingYourMLbased2022, abstract = {Machine learning (ML) is becoming a core component in query optimizers, e.g., to estimate costs or cardinalities. This means large heterogeneous sets of labeled query plans or jobs (i.e., plans with their runtime or cardinality output) are needed. However, collecting such a training dataset is a very tedious and time-consuming task: It requires both developing numerous jobs and executing them to acquire ground-truth labels. We demonstrate Datafarm,a novel framework for efficiently generating and labeling training data for ML-based query optimizers to overcome these issues. Datafarmenables generating training data tailored to users' needs by learning from their existing workload patterns, input data, and computational resources. It uses an active learning approach to determine a subset of jobs to be executed and encloses the human into the loop, resulting in higher quality data. The graphical user interface of Datafarmallows users to get informative details of the generated jobs and guides them through the generation process step-by-step. We show how users can intervene and provide feedback to the system in an iterative fashion. As an output, users can download both the generated jobs to use as a benchmark and the training data (jobs with their labels).}, author = {Van De Water, Robin and Ventura, Francesco and Kaoudi, Zoi and Quiané-Ruiz, Jorge-Arnulfo and Markl, Volker}, keywords = {prior-hpi robinvandewater}, organization = {IEEE}, pages = {3186–3189}, title = {Farming Your ML-based Query Optimizer's Food}, year = 2022 }
DPD-fVAE: Synthetic Data Generation Using Federated Variational Autoencoders With Differentially-Private Decoder Pfitzner, Bjarne; Arnrich, Bert (2022).
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
Federated learning (FL) is getting increased attention for processing sensitive, distributed datasets common to domains such as healthcare. Instead of directly training classification models on these datasets, recent works have considered training data generators capable of synthesising a new dataset which is not protected by any privacy restrictions. Thus, the synthetic data can be made available to anyone, which enables further evaluation of machine learning architectures and research questions off-site. As an additional layer of privacy-preservation, differential privacy can be introduced into the training process. We propose DPD-fVAE, a federated Variational Autoencoder with Differentially-Private Decoder, to synthesise a new, labelled dataset for subsequent machine learning tasks. By synchronising only the decoder component with FL, we can reduce the privacy cost per epoch and thus enable better data generators. In our evaluation on MNIST, Fashion-MNIST and CelebA, we show the benefits of DPD-fVAE and report competitive performance to related work in terms of Fréchet Inception Distance and accuracy of classifiers trained on the synthesised dataset.
@preprint{https://doi.org/10.48550/arxiv.2211.11591, abstract = {Federated learning (FL) is getting increased attention for processing sensitive, distributed datasets common to domains such as healthcare. Instead of directly training classification models on these datasets, recent works have considered training data generators capable of synthesising a new dataset which is not protected by any privacy restrictions. Thus, the synthetic data can be made available to anyone, which enables further evaluation of machine learning architectures and research questions off-site. As an additional layer of privacy-preservation, differential privacy can be introduced into the training process. We propose DPD-fVAE, a federated Variational Autoencoder with Differentially-Private Decoder, to synthesise a new, labelled dataset for subsequent machine learning tasks. By synchronising only the decoder component with FL, we can reduce the privacy cost per epoch and thus enable better data generators. In our evaluation on MNIST, Fashion-MNIST and CelebA, we show the benefits of DPD-fVAE and report competitive performance to related work in terms of Fréchet Inception Distance and accuracy of classifiers trained on the synthesised dataset.}, author = {Pfitzner, Bjarne and Arnrich, Bert}, keywords = {bertarnrich bjarnepfitzner}, publisher = {arXiv}, title = {DPD-fVAE: Synthetic Data Generation Using Federated Variational Autoencoders With Differentially-Private Decoder}, year = 2022 }
Wearable electroencephalography and multi-modal mental state classification: A systematic literature review. Anders, Christoph; Arnrich, Bert in Computers in Biology and Medicine (2022). 150 106088.
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
Background: Wearable multi-modal time-series classification applications outperform their best uni-modal counterparts and hold great promise. A modality that directly measures electrical correlates from the brain is electroencephalography. Due to varying noise sources, different key brain regions, key frequency bands, and signal characteristics like non-stationarity, techniques for data pre-processing and classification algorithms are task-dependent. Method: Here, a systematic literature review on mental state classification for wearable electroencephalography is presented. Four search terms in different combinations were used for an in-title search. The search was executed on the 29th of June 2022, across Google Scholar, PubMed, IEEEXplore, and ScienceDirect. 76 most relevant publications were set into context as the current state-of-the-art in mental state time-series classification. Results: Pre-processing techniques, features, and time-series classification models were analyzed. Across publications, a window length of one second was mainly chosen for classification and spectral features were utilized the most. The achieved performance per time-series classification model is analyzed, finding linear discriminant analysis, decision trees, and k-nearest neighbors models outperform support-vector machines by a factor of up to 1.5. A historical analysis depicts future trends while under-reported aspects relevant to practical applications are discussed. Conclusions: Five main conclusions are given, covering utilization of available area for electrode placement on the head, most often or scarcely utilized features and time-series classification model architectures, baseline reporting practices, as well as explainability and interpretability of Deep Learning. The importance of a ‘test battery’ assessing the influence of data pre-processing and multi-modality on time-series classification performance is emphasized.
@article{ANDERS2022106088, abstract = {Background: Wearable multi-modal time-series classification applications outperform their best uni-modal counterparts and hold great promise. A modality that directly measures electrical correlates from the brain is electroencephalography. Due to varying noise sources, different key brain regions, key frequency bands, and signal characteristics like non-stationarity, techniques for data pre-processing and classification algorithms are task-dependent. Method: Here, a systematic literature review on mental state classification for wearable electroencephalography is presented. Four search terms in different combinations were used for an in-title search. The search was executed on the 29th of June 2022, across Google Scholar, PubMed, IEEEXplore, and ScienceDirect. 76 most relevant publications were set into context as the current state-of-the-art in mental state time-series classification. Results: Pre-processing techniques, features, and time-series classification models were analyzed. Across publications, a window length of one second was mainly chosen for classification and spectral features were utilized the most. The achieved performance per time-series classification model is analyzed, finding linear discriminant analysis, decision trees, and k-nearest neighbors models outperform support-vector machines by a factor of up to 1.5. A historical analysis depicts future trends while under-reported aspects relevant to practical applications are discussed. Conclusions: Five main conclusions are given, covering utilization of available area for electrode placement on the head, most often or scarcely utilized features and time-series classification model architectures, baseline reporting practices, as well as explainability and interpretability of Deep Learning. The importance of a ‘test battery’ assessing the influence of data pre-processing and multi-modality on time-series classification performance is emphasized.}, author = {Anders, Christoph and Arnrich, Bert}, journal = {Computers in Biology and Medicine}, keywords = {christophanders bertarnrich}, pages = 106088, title = {Wearable electroencephalography and multi-modal mental state classification: A systematic literature review}, volume = 150, year = 2022 }
Implementation and Evaluation of Personal Genetic Testing As Part of Genomics Analysis Courses in German Universities Slosarek, Tamara; Ibing, Susanne; Schormair, Barbara; Heyne, Henrike O; Böttinger, Erwin P; Andlauer, Till FM; Schurmann, Claudia (2022, December 20).
[ BibTeX ] [ URL ] [ DOI ]
 
@preprint{slosarek2022implementation, author = {Slosarek, Tamara and Ibing, Susanne and Schormair, Barbara and Heyne, Henrike O and Böttinger, Erwin P and Andlauer, Till FM and Schurmann, Claudia}, journal = {Research Square}, keywords = {myown}, month = {dec}, title = {Implementation and Evaluation of Personal Genetic Testing As Part of Genomics Analysis Courses in German Universities}, year = 2022 }
Computational Approaches to Alleviate Alarm Fatigue in Intensive Care Medicine: A Systematic Literature Review. Chromik, Jonas; Klopfenstein, Sophie Anne Ines; Pfitzner, Bjarne; Sinno, Zeena-Carola; Arnrich, Bert; Balzer, Felix; Poncette, Akira-Sebastian in Frontiers in Digital Health (2022). 4
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
Patient monitoring technology has been used to guide therapy and alert staff when a vital sign leaves a predefined range in the intensive care unit (ICU) for decades. However, large amounts of technically false or clinically irrelevant alarms provoke alarm fatigue in staff leading to desensitisation towards critical alarms. With this systematic review, we are following the Preferred Reporting Items for Systematic Reviews (PRISMA) checklist in order to summarise scientific efforts that aimed to develop IT systems to reduce alarm fatigue in ICUs. 69 peer-reviewed publications were included. The majority of publications targeted the avoidance of technically false alarms, while the remainder focused on prediction of patient deterioration or alarm presentation. The investigated alarm types were mostly associated with heart rate or arrhythmia, followed by arterial blood pressure, oxygen saturation, and respiratory rate. Most publications focused on the development of software solutions, some on wearables, smartphones, or headmounted displays for delivering alarms to staff. The most commonly used statistical models were tree-based. In conclusion, we found strong evidence that alarm fatigue can be alleviated by IT-based solutions. However, future efforts should focus more on the avoidance of clinically non-actionable alarms which could be accelerated by improving the data availability.
@article{chromik2022computational, abstract = {Patient monitoring technology has been used to guide therapy and alert staff when a vital sign leaves a predefined range in the intensive care unit (ICU) for decades. However, large amounts of technically false or clinically irrelevant alarms provoke alarm fatigue in staff leading to desensitisation towards critical alarms. With this systematic review, we are following the Preferred Reporting Items for Systematic Reviews (PRISMA) checklist in order to summarise scientific efforts that aimed to develop IT systems to reduce alarm fatigue in ICUs. 69 peer-reviewed publications were included. The majority of publications targeted the avoidance of technically false alarms, while the remainder focused on prediction of patient deterioration or alarm presentation. The investigated alarm types were mostly associated with heart rate or arrhythmia, followed by arterial blood pressure, oxygen saturation, and respiratory rate. Most publications focused on the development of software solutions, some on wearables, smartphones, or headmounted displays for delivering alarms to staff. The most commonly used statistical models were tree-based. In conclusion, we found strong evidence that alarm fatigue can be alleviated by IT-based solutions. However, future efforts should focus more on the avoidance of clinically non-actionable alarms which could be accelerated by improving the data availability.}, author = {Chromik, Jonas and Klopfenstein, Sophie Anne Ines and Pfitzner, Bjarne and Sinno, Zeena-Carola and Arnrich, Bert and Balzer, Felix and Poncette, Akira-Sebastian}, journal = {Frontiers in Digital Health}, keywords = {bertarnrich bjarnepfitzner jonaschromik}, month = {aug}, title = {Computational Approaches to Alleviate Alarm Fatigue in Intensive Care Medicine: A Systematic Literature Review}, volume = 4, year = 2022 }
Gene variant effects across sodium channelopathies predict function and guide precision therapy. Brunklaus, Andreas; Feng, Tony; Brünger, Tobias; Perez-Palma, Eduardo; Heyne, Henrike; Matthews, Emma; Semsarian, Christopher; Symonds, Joseph D; Zuberi, Sameer M; Lal, Dennis; others in Brain (2022).
[ BibTeX ]
 
@article{brunklaus2022gene, author = {Brunklaus, Andreas and Feng, Tony and Br{ü}nger, Tobias and Perez-Palma, Eduardo and Heyne, Henrike and Matthews, Emma and Semsarian, Christopher and Symonds, Joseph D and Zuberi, Sameer M and Lal, Dennis and others}, journal = {Brain}, keywords = {myown}, title = {Gene variant effects across sodium channelopathies predict function and guide precision therapy}, year = 2022 }
Insights From a Large-Scale Whole-Genome Sequencing Study of Systolic Blood Pressure, Diastolic Blood Pressure, and Hypertension. Kelly, Tanika N.; Sun, Xiao; He, Karen Y.; Brown, Michael R.; Taliun, Sarah A. Gagliano; Hellwege, Jacklyn N.; Irvin, Marguerite R.; Mi, Xuenan; Brody, Jennifer A.; Franceschini, Nora; Guo, Xiuqing; Hwang, Shih-Jen; de Vries, Paul S.; Gao, Yan; Moscati, Arden; Nadkarni, Girish N.; Yanek, Lisa R.; Elfassy, Tali; Smith, Jennifer A.; Chung, Ren-Hua; Beitelshees, Amber L.; Patki, Amit; Aslibekyan, Stella; Blobner, Brandon M.; Peralta, Juan M.; Assimes, Themistocles L.; Palmas, Walter R.; Liu, Chunyu; Bress, Adam P.; Huang, Zhijie; Becker, Lewis C.; Hwa, Chii-Min; O’Connell, Jeffrey R.; Carlson, Jenna C.; Warren, Helen R.; Das, Sayantan; Giri, Ayush; Martin, Lisa W.; Johnson, W. Craig; Fox, Ervin R.; Bottinger, Erwin P.; Razavi, Alexander C.; Vaidya, Dhananjay; Chuang, Lee-Ming; Chang, Yen-Pei C.; Naseri, Take; Jain, Deepti; Kang, Hyun Min; Hung, Adriana M.; Srinivasasainagendra, Vinodh; Snively, Beverly M.; Gu, Dongfeng; Montasser, May E.; Reupena, Muagututi`a Sefuiva; Heavner, Benjamin D.; LeFaive, Jonathon; Hixson, James E.; Rice, Kenneth M.; Wang, Fei Fei; Nielsen, Jonas B.; Huang, Jianfeng; Khan, Alyna T.; Zhou, Wei; Nierenberg, Jovia L.; Laurie, Cathy C.; Armstrong, Nicole D.; Shi, Mengyao; Pan, Yang; Stilp, Adrienne M.; Emery, Leslie; Wong, Quenna; Hawley, Nicola L.; Minster, Ryan L.; Curran, Joanne E.; Munroe, Patricia B.; Weeks, Daniel E.; North, Kari E.; Tracy, Russell P.; Kenny, Eimear E.; Shimbo, Daichi; Chakravarti, Aravinda; Rich, Stephen S.; Reiner, Alex P.; Blangero, John; Redline, Susan; Mitchell, Braxton D.; Rao, Dabeeru C.; Chen, Yii-Der Ida; Kardia, Sharon L.R.; Kaplan, Robert C.; Mathias, Rasika A.; He, Jiang; Psaty, Bruce M.; Fornage, Myriam; Loos, Ruth J.F.; Correa, Adolfo; Boerwinkle, Eric; Rotter, Jerome I.; Kooperberg, Charles; Edwards, Todd L.; Abecasis, Gonçalo R.; Zhu, Xiaofeng; Levy, Daniel; Arnett, Donna K.; Morrison, Alanna C. in Hypertension (2022). 79(8) 1656–1667.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Kelly2022, author = {Kelly, Tanika N. and Sun, Xiao and He, Karen Y. and Brown, Michael R. and Taliun, Sarah A. Gagliano and Hellwege, Jacklyn N. and Irvin, Marguerite R. and Mi, Xuenan and Brody, Jennifer A. and Franceschini, Nora and Guo, Xiuqing and Hwang, Shih-Jen and de Vries, Paul S. and Gao, Yan and Moscati, Arden and Nadkarni, Girish N. and Yanek, Lisa R. and Elfassy, Tali and Smith, Jennifer A. and Chung, Ren-Hua and Beitelshees, Amber L. and Patki, Amit and Aslibekyan, Stella and Blobner, Brandon M. and Peralta, Juan M. and Assimes, Themistocles L. and Palmas, Walter R. and Liu, Chunyu and Bress, Adam P. and Huang, Zhijie and Becker, Lewis C. and Hwa, Chii-Min and O'Connell, Jeffrey R. and Carlson, Jenna C. and Warren, Helen R. and Das, Sayantan and Giri, Ayush and Martin, Lisa W. and Johnson, W. Craig and Fox, Ervin R. and Bottinger, Erwin P. and Razavi, Alexander C. and Vaidya, Dhananjay and Chuang, Lee-Ming and Chang, Yen-Pei C. and Naseri, Take and Jain, Deepti and Kang, Hyun Min and Hung, Adriana M. and Srinivasasainagendra, Vinodh and Snively, Beverly M. and Gu, Dongfeng and Montasser, May E. and Reupena, Muagututi`a Sefuiva and Heavner, Benjamin D. and LeFaive, Jonathon and Hixson, James E. and Rice, Kenneth M. and Wang, Fei Fei and Nielsen, Jonas B. and Huang, Jianfeng and Khan, Alyna T. and Zhou, Wei and Nierenberg, Jovia L. and Laurie, Cathy C. and Armstrong, Nicole D. and Shi, Mengyao and Pan, Yang and Stilp, Adrienne M. and Emery, Leslie and Wong, Quenna and Hawley, Nicola L. and Minster, Ryan L. and Curran, Joanne E. and Munroe, Patricia B. and Weeks, Daniel E. and North, Kari E. and Tracy, Russell P. and Kenny, Eimear E. and Shimbo, Daichi and Chakravarti, Aravinda and Rich, Stephen S. and Reiner, Alex P. and Blangero, John and Redline, Susan and Mitchell, Braxton D. and Rao, Dabeeru C. and Chen, Yii-Der Ida and Kardia, Sharon L.R. and Kaplan, Robert C. and Mathias, Rasika A. and He, Jiang and Psaty, Bruce M. and Fornage, Myriam and Loos, Ruth J.F. and Correa, Adolfo and Boerwinkle, Eric and Rotter, Jerome I. and Kooperberg, Charles and Edwards, Todd L. and Abecasis, Gonçalo R. and Zhu, Xiaofeng and Levy, Daniel and Arnett, Donna K. and Morrison, Alanna C.}, journal = {Hypertension}, keywords = {boettinger hpims fb-boettinger}, month = {aug}, number = 8, pages = {1656–1667}, publisher = {Ovid Technologies (Wolters Kluwer Health)}, title = {Insights From a Large-Scale Whole-Genome Sequencing Study of Systolic Blood Pressure, Diastolic Blood Pressure, and Hypertension}, volume = 79, year = 2022 }
GGPONC 2.0 - The German Clinical Guideline Corpus for Oncology: Curation Workflow, Annotation Policy, Baseline NER Taggers. Borchert, Florian; Lohr, Christina; Modersohn, Luise; Witt, Jonas; Langer, Thomas; Follmann, Markus; Gietzelt, Matthias; Arnrich, Bert; Hahn, Udo; Schapranow, Matthieu-P. (2022). 3650–3660.
[ Abstract ] [ BibTeX ] [ URL ]
 
Despite remarkable advances in the development of language resources over the recent years, there is still a shortage of annotated, publicly available corpora covering (German) medical language. With the initial release of the German Guideline Program in Oncology NLP Corpus (GGPONC), we have demonstrated how such corpora can be built upon clinical guidelines, a widely available resource in many natural languages with a reasonable coverage of medical terminology. In this work, we describe a major new release for GGPONC. The corpus has been substantially extended in size and re-annotated with a new annotation scheme based on SNOMED CT top level hierarchies, reaching high inter-annotator agreement (γ=.94). Moreover, we annotated elliptical coordinated noun phrases and their resolutions, a common language phenomenon in (not only German) scientific documents. We also trained BERT-based named entity recognition models on this new data set, which achieve high performance on short, coarse-grained entity spans (F1=.89), while the rate of boundary errors increases for long entity spans. GGPONC is freely available through a data use agreement. The trained named entity recognition models, as well as the detailed annotation guide, are also made publicly available.
@inproceedings{borchert-EtAl:2022:LREC, abstract = {Despite remarkable advances in the development of language resources over the recent years, there is still a shortage of annotated, publicly available corpora covering (German) medical language. With the initial release of the German Guideline Program in Oncology NLP Corpus (GGPONC), we have demonstrated how such corpora can be built upon clinical guidelines, a widely available resource in many natural languages with a reasonable coverage of medical terminology. In this work, we describe a major new release for GGPONC. The corpus has been substantially extended in size and re-annotated with a new annotation scheme based on SNOMED CT top level hierarchies, reaching high inter-annotator agreement (γ=.94). Moreover, we annotated elliptical coordinated noun phrases and their resolutions, a common language phenomenon in (not only German) scientific documents. We also trained BERT-based named entity recognition models on this new data set, which achieve high performance on short, coarse-grained entity spans (F1=.89), while the rate of boundary errors increases for long entity spans. GGPONC is freely available through a data use agreement. The trained named entity recognition models, as well as the detailed annotation guide, are also made publicly available.}, address = {Marseille, France}, author = {Borchert, Florian and Lohr, Christina and Modersohn, Luise and Witt, Jonas and Langer, Thomas and Follmann, Markus and Gietzelt, Matthias and Arnrich, Bert and Hahn, Udo and Schapranow, Matthieu-P.}, booktitle = {Proceedings of the Language Resources and Evaluation Conference}, keywords = {nlp highmed fb-boettinger}, month = {June}, pages = {3650–3660}, publisher = {European Language Resources Association}, title = {GGPONC 2.0 - The German Clinical Guideline Corpus for Oncology: Curation Workflow, Annotation Policy, Baseline NER Taggers}, year = 2022 }
Inducing and Recording Acute Stress Responses on a Large Scale With the Digital Stress Test (DST): Development and Evaluation Study. Norden, Matthias; Hofmann, Amin Gerard; Meier, Martin; Balzer, Felix; Wolf, Oliver T; Bottinger, Erwin; Drimalla, Hanna in Journal of Medical Internet Research (2022). 24(7) e32280.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Norden2022, author = {Norden, Matthias and Hofmann, Amin Gerard and Meier, Martin and Balzer, Felix and Wolf, Oliver T and Bottinger, Erwin and Drimalla, Hanna}, journal = {Journal of Medical Internet Research}, keywords = {boettinger fb-boettinger}, month = {jul}, number = 7, pages = {e32280}, publisher = {{JMIR} Publications Inc.}, title = {Inducing and Recording Acute Stress Responses on a Large Scale With the Digital Stress Test ({DST}): Development and Evaluation Study}, volume = 24, year = 2022 }
Effects of a Supplement Containing a Cranberry Extract on Recurrent Urinary Tract Infections and Intestinal Microbiota: A Prospective, Uncontrolled Exploratory Study. Jeitler, Michael; Michalsen, Andreas; Schwiertz, Andreas; Kessler, Christian S.; Koppold-Liebscher, Daniela; Grasme, Julia; Kandil, Farid I.; Steckhan, Nico in Journal of Integrative and Complementary Medicine (2022). 28(5) 399–406.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Jeitler2022, author = {Jeitler, Michael and Michalsen, Andreas and Schwiertz, Andreas and Kessler, Christian S. and Koppold-Liebscher, Daniela and Grasme, Julia and Kandil, Farid I. and Steckhan, Nico}, journal = {Journal of Integrative and Complementary Medicine}, keywords = {nicosteckhan bertarnrich}, month = {may}, number = 5, pages = {399–406}, publisher = {Mary Ann Liebert Inc}, title = {Effects of a Supplement Containing a Cranberry Extract on Recurrent Urinary Tract Infections and Intestinal Microbiota: A Prospective, Uncontrolled Exploratory Study}, volume = 28, year = 2022 }
Mental and Behavioural Responses to Bahá’’i Fasting: Looking behind the Scenes of a Religiously Motivated Intermittent Fast Using a Mixed Methods Approach. Ring, Raphaela M.; Eisenmann, Clemens; Kandil, Farid I.; Steckhan, Nico; Demmrich, Sarah; Klatte, Caroline; Kessler, Christian S.; Jeitler, Michael; Boschmann, Michael; Michalsen, Andreas; Blakeslee, Sarah B.; Stöckigt, Barbara; Stritter, Wiebke; Koppold-Liebscher, Daniela A. in Nutrients (2022). 14(5) 1038.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Ring2022, author = {Ring, Raphaela M. and Eisenmann, Clemens and Kandil, Farid I. and Steckhan, Nico and Demmrich, Sarah and Klatte, Caroline and Kessler, Christian S. and Jeitler, Michael and Boschmann, Michael and Michalsen, Andreas and Blakeslee, Sarah B. and St{ö}ckigt, Barbara and Stritter, Wiebke and Koppold-Liebscher, Daniela A.}, journal = {Nutrients}, keywords = {nicosteckhan bertarnrich}, month = {feb}, number = 5, pages = 1038, publisher = {{MDPI} {AG}}, title = {Mental and Behavioural Responses to Bah{{á}}'{\'{\i}} Fasting: Looking behind the Scenes of a Religiously Motivated Intermittent Fast Using a Mixed Methods Approach}, volume = 14, year = 2022 }
Voice Analysis for Neurological Disorder Recognition - A Systematic Review and Perspective on Emerging Trends. Hecker, Pascal; Steckhan, Nico; Eyben, Florian; Schuller, Björn W.; Arnrich, Bert in Frontiers in Digital Health (2022). 4
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
Quantifying neurological disorders from voice is a rapidly growing field of research and holds promise for unobtrusive and large-scale disorder monitoring. The data recording setup and data analysis pipelines are both crucial aspects to effectively obtain relevant information from participants. Therefore, we performed a systematic review to provide a high-level overview of practices across various neurological disorders and highlight emerging trends. PRISMA-based literature searches were conducted through PubMed, Web of Science, and IEEE Xplore to identify publications in which original (i.e., newly recorded) datasets were collected. Disorders of interest were psychiatric as well as neurodegenerative disorders, such as bipolar disorder, depression, and stress, as well as amyotrophic lateral sclerosis amyotrophic lateral sclerosis, Alzheimer's, and Parkinson's disease, and speech impairments (aphasia, dysarthria, and dysphonia). Of the 43 retrieved studies, Parkinson's disease is represented most prominently with 19 discovered datasets. Free speech and read speech tasks are most commonly used across disorders. Besides popular feature extraction toolkits, many studies utilise custom-built feature sets. Correlations of acoustic features with psychiatric and neurodegenerative disorders are presented. In terms of analysis, statistical analysis for significance of individual features is commonly used, as well as predictive modeling approaches, especially with support vector machines and a small number of artificial neural networks. An emerging trend and recommendation for future studies is to collect data in everyday life to facilitate longitudinal data collection and to capture the behavior of participants more naturally. Another emerging trend is to record additional modalities to voice, which can potentially increase analytical performance.
@article{Hecker2022, abstract = {Quantifying neurological disorders from voice is a rapidly growing field of research and holds promise for unobtrusive and large-scale disorder monitoring. The data recording setup and data analysis pipelines are both crucial aspects to effectively obtain relevant information from participants. Therefore, we performed a systematic review to provide a high-level overview of practices across various neurological disorders and highlight emerging trends. PRISMA-based literature searches were conducted through PubMed, Web of Science, and IEEE Xplore to identify publications in which original (i.e., newly recorded) datasets were collected. Disorders of interest were psychiatric as well as neurodegenerative disorders, such as bipolar disorder, depression, and stress, as well as amyotrophic lateral sclerosis amyotrophic lateral sclerosis, Alzheimer's, and Parkinson's disease, and speech impairments (aphasia, dysarthria, and dysphonia). Of the 43 retrieved studies, Parkinson's disease is represented most prominently with 19 discovered datasets. Free speech and read speech tasks are most commonly used across disorders. Besides popular feature extraction toolkits, many studies utilise custom-built feature sets. Correlations of acoustic features with psychiatric and neurodegenerative disorders are presented. In terms of analysis, statistical analysis for significance of individual features is commonly used, as well as predictive modeling approaches, especially with support vector machines and a small number of artificial neural networks. An emerging trend and recommendation for future studies is to collect data in everyday life to facilitate longitudinal data collection and to capture the behavior of participants more naturally. Another emerging trend is to record additional modalities to voice, which can potentially increase analytical performance.}, author = {Hecker, Pascal and Steckhan, Nico and Eyben, Florian and Schuller, Bj{ö}rn W. and Arnrich, Bert}, journal = {Frontiers in Digital Health}, keywords = {pascalhecker nicosteckhan bertarnrich}, month = {jul}, publisher = {Frontiers Media {SA}}, title = {Voice Analysis for Neurological Disorder Recognition - A Systematic Review and Perspective on Emerging Trends}, volume = 4, year = 2022 }
Hand Gesture Recognition in Daily Life as an Additional Tool for Unobtrusive Data Labeling in Medical Studies. Joch, Julia; Kirsten, Kristina; Arnrich, Bert (2022).
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
For many use cases, such as supervised machine learning, labeled data is needed. However, to collect information for labels in real-life contexts, scientists are confronted with the challenge of gathering labeled data over an extended period. Labeling this data can become problematic, as constant supervision, similar to a laboratory setting, is neither feasible nor desired. Therefore, participants of such studies have to label their data themselves via appropriate apps on a smartphone. Nevertheless, this process can become very obtrusive in daily life and might even influence the results, especially studies regarding emotions. For example, in studies where participants need to indicate their stress levels frequently, labels get missed in situations where it would be inappropriate to take the phone. Consequently, missing these labels presents a significant problem. This paper aims to provide an unobtrusive solution to labeling data in real-world studies. We recorded a dataset consisting of five gestures and data from daily life. Thereby, we provide a set of predefined gestures that can be distinguished from other everyday life activities by using accelerometer and gyroscope sensors of wearable devices on the wrist. The use of predefined hand gestures for labeling data can therefore serve as an additional tool for the labeling process. Two machine learning approaches were compared and achieved promising results with Matthews Correlation Coefficients of up to 0.789 for a Random Forest and up to 0.835 for a Convolutional Neural Network.
@inproceedings{joch_kirsten_2022handgesture, abstract = {For many use cases, such as supervised machine learning, labeled data is needed. However, to collect information for labels in real-life contexts, scientists are confronted with the challenge of gathering labeled data over an extended period. Labeling this data can become problematic, as constant supervision, similar to a laboratory setting, is neither feasible nor desired. Therefore, participants of such studies have to label their data themselves via appropriate apps on a smartphone. Nevertheless, this process can become very obtrusive in daily life and might even influence the results, especially studies regarding emotions. For example, in studies where participants need to indicate their stress levels frequently, labels get missed in situations where it would be inappropriate to take the phone. Consequently, missing these labels presents a significant problem. This paper aims to provide an unobtrusive solution to labeling data in real-world studies. We recorded a dataset consisting of five gestures and data from daily life. Thereby, we provide a set of predefined gestures that can be distinguished from other everyday life activities by using accelerometer and gyroscope sensors of wearable devices on the wrist. The use of predefined hand gestures for labeling data can therefore serve as an additional tool for the labeling process. Two machine learning approaches were compared and achieved promising results with Matthews Correlation Coefficients of up to 0.789 for a Random Forest and up to 0.835 for a Convolutional Neural Network.}, author = {Joch, Julia and Kirsten, Kristina and Arnrich, Bert}, booktitle = {Proceedings of the 7th international Workshop on Sensor-based Activity Recognition and Artifical Intelligence (iWOAR '22)}, keywords = {bertarnrich kristinakirsten}, publisher = {Association for Computing Machinery}, title = {Hand Gesture Recognition in Daily Life as an Additional Tool for Unobtrusive Data Labeling in Medical Studies}, year = 2022 }
HPI-DHC @ BioASQ DisTEMIST: Spanish Biomedical Entity Linking with Pre-trained Transformers and Cross-lingual Candidate Retrieval. Borchert, Florian; Schapranow, Matthieu-P. (2022). 244–258.
[ BibTeX ] [ URL ]
 
@inproceedings{borchert2022clef, address = {Bologna, Italy}, author = {Borchert, Florian and Schapranow, Matthieu-P.}, booktitle = {Proceedings of the Working Notes of CLEF 2022 - Conference and Labs of the Evaluation Forum}, keywords = {nlp myown highmed fb-boettinger}, month = {September}, pages = {244-258}, title = {HPI-DHC @ BioASQ DisTEMIST: Spanish Biomedical Entity Linking with Pre-trained Transformers and Cross-lingual Candidate Retrieval}, year = 2022 }
KI-Geschäftsmodelle für die Gesundheit. Technical Report (3), Budde, Klemens; Hiltawsky, Karsten; Kirchner, Elsa; Klevesath, Manfred; Lenarz, Thomas; Neumuth, Thomas; Melzer, Andreas; Schapranow, Matthieu-P.; Wolf-Ostermann, Karin; Löbker, Wiebke; Rad, Abtin J.; Zapf, Christian; Heismann, Björn; Kara, Güngör; Buttjes, Daniel; Boll, Susanne; Faisst, Wolfgang; Piller, Frank T.; Gülpen, Christian; Susec, Barbara; Nicolay, Katharina (2022).
[ BibTeX ] [ DOI ]
 
@techreport{budde2022kigeschftsmodelle, author = {Budde, Klemens and Hiltawsky, Karsten and Kirchner, Elsa and Klevesath, Manfred and Lenarz, Thomas and Neumuth, Thomas and Melzer, Andreas and Schapranow, Matthieu-P. and Wolf-Ostermann, Karin and Löbker, Wiebke and Rad, Abtin J. and Zapf, Christian and Heismann, Björn and Kara, Güngör and Buttjes, Daniel and Boll, Susanne and Faisst, Wolfgang and Piller, Frank T. and Gülpen, Christian and Susec, Barbara and Nicolay, Katharina}, institution = {Plattform Lernende Systeme}, keywords = {myown pls}, month = {apr}, number = 3, title = {KI-Geschäftsmodelle für die Gesundheit}, type = {https://doi.org/10.48669/pls_2022-3}, year = 2022 }
An Engineering Approach towards Multi-Site Virtual Molecular Tumor Board Software Support. Henkenjohann, Richard; Bergner, Benjamin; Borchert, Florian; Bougatf, Nina; Hund, Hauke; Eils, Roland; Schapranow, Matthieu-P. in Communications in Computer and Information Science, E. Pissaloux, G. Papadopoulos, A. Achilleos, R. Velázquez (eds.) (2022). (Vol. 1538) 156–170.
[ BibTeX ] [ URL ]
 
@inproceedings{henkenjohann2021mtb, author = {Henkenjohann, Richard and Bergner, Benjamin and Borchert, Florian and Bougatf, Nina and Hund, Hauke and Eils, Roland and Schapranow, Matthieu-P.}, booktitle = {ICT for Health, Accessibility and Wellbeing. IHAW 2021}, editor = {Pissaloux, E. and Papadopoulos, G.A. and Achilleos, A. and Velázquez, R.}, keywords = {myown highmed mtb}, month = {mar}, pages = {156-170}, publisher = {Springer, Cham.}, series = {Communications in Computer and Information Science}, title = {An Engineering Approach towards Multi-Site Virtual Molecular Tumor Board Software Support}, volume = 1538, year = 2022 }
Forecasting Thresholds Alarms in Medical Patient Monitors using Time Series Models. Chromik., Jonas; Pfitzner., Bjarne; Ihde., Nina; Michaelis., Marius; Schmidt., Denise; Klopfenstein., Sophie; Poncette., Akira-Sebastian; Balzer., Felix; Arnrich., Bert (2022). 26–34.
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
Too many alarms are a persistent problem in today’s intensive care medicine leading to alarm desensitisation and alarm fatigue. This puts patients and staff at risk. We propose a forecasting strategy for threshold alarms in patient monitors in order to replace alarms that are actionable right now with scheduled tasks in an attempt to remove the urgency from the situation. Therefore, we employ both statistical and machine learning mod- els for time series forecasting and apply these models to vital parameter data such as blood pressure, heart rate, and oxygen saturation. The results are promising, although impaired by low and non-constant sampling frequencies of the time series data in use. The combination of a GRU model with medium-resampled data shows the best performance for most types of alarms. However, higher time resolution and constant sampling frequencies are needed in order to meaningfully evaluate our approach.
@conference{chromik2022forecasting, abstract = {Too many alarms are a persistent problem in today’s intensive care medicine leading to alarm desensitisation and alarm fatigue. This puts patients and staff at risk. We propose a forecasting strategy for threshold alarms in patient monitors in order to replace alarms that are actionable right now with scheduled tasks in an attempt to remove the urgency from the situation. Therefore, we employ both statistical and machine learning mod- els for time series forecasting and apply these models to vital parameter data such as blood pressure, heart rate, and oxygen saturation. The results are promising, although impaired by low and non-constant sampling frequencies of the time series data in use. The combination of a GRU model with medium-resampled data shows the best performance for most types of alarms. However, higher time resolution and constant sampling frequencies are needed in order to meaningfully evaluate our approach.}, author = {Chromik., Jonas and Pfitzner., Bjarne and Ihde., Nina and Michaelis., Marius and Schmidt., Denise and Klopfenstein., Sophie and Poncette., Akira{-}Sebastian and Balzer., Felix and Arnrich., Bert}, booktitle = {Proceedings of the 15th International Joint Conference on Biomedical Engineering Systems and Technologies - HEALTHINF,}, keywords = {bertarnrich bjarnepfitzner jonaschromik}, organization = {INSTICC}, pages = {26-34}, publisher = {SciTePress}, title = {Forecasting Thresholds Alarms in Medical Patient Monitors using Time Series Models}, year = 2022 }
Unsupervised Activity Recognition Using Trajectory Heatmaps from Inertial Measurement Unit Data. Konak., Orhan; Wegner., Pit; Albert., Justin; Arnrich., Bert (2022). 304–312.
[ BibTeX ] [ DOI ]
 
@conference{icaart22, author = {Konak., Orhan and Wegner., Pit and Albert., Justin and Arnrich., Bert}, booktitle = {Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,}, keywords = {arnrich bertarnrich}, organization = {INSTICC}, pages = {304-312}, publisher = {SciTePress}, title = {Unsupervised Activity Recognition Using Trajectory Heatmaps from Inertial Measurement Unit Data}, year = 2022 }
Effects of Testing and Disclosing Ancestry-Specific Genetic Risk for Kidney Failure on Patients and Health Care Professionals. Nadkarni, Girish N.; Fei, Kezhen; Ramos, Michelle A.; Hauser, Diane; Bagiella, Emilia; Ellis, Stephen B.; Sanderson, Saskia; Scott, Stuart A.; Sabin, Tatiana; Madden, Ebony; Cooper, Richard; Pollak, Martin; Calman, Neil; Bottinger, Erwin P.; Horowitz, Carol R. in JAMA Network Open (2022). 5(3) e221048.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Nadkarni2022, author = {Nadkarni, Girish N. and Fei, Kezhen and Ramos, Michelle A. and Hauser, Diane and Bagiella, Emilia and Ellis, Stephen B. and Sanderson, Saskia and Scott, Stuart A. and Sabin, Tatiana and Madden, Ebony and Cooper, Richard and Pollak, Martin and Calman, Neil and Bottinger, Erwin P. and Horowitz, Carol R.}, journal = {{JAMA} Network Open}, keywords = {boettinger hpims fb-boettinger}, month = {mar}, number = 3, pages = {e221048}, publisher = {American Medical Association ({AMA})}, title = {Effects of Testing and Disclosing Ancestry-Specific Genetic Risk for Kidney Failure on Patients and Health Care Professionals}, volume = 5, year = 2022 }
Digital Therapeutic Care Apps With Decision-Support Interventions for People With Low Back Pain in Germany: Cost-Effectiveness Analysis. Lewkowicz, Daniel; Wohlbrandt, Attila M; Bottinger, Erwin in JMIR Mhealth Uhealth (2022). 10(2) e35042.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{info:doi/10.2196/35042, author = {Lewkowicz, Daniel and Wohlbrandt, Attila M and Bottinger, Erwin}, journal = {JMIR Mhealth Uhealth}, keywords = {myown bottinger bottinger-not-dhc dhc}, month = {feb}, number = 2, pages = {e35042}, title = {Digital Therapeutic Care Apps With Decision-Support Interventions for People With Low Back Pain in Germany: Cost-Effectiveness Analysis.}, volume = 10, year = 2022 }
Unsupervised Activity Recognition Using Trajectory Heatmaps from Inertial Measurement Unit Data. Konak., Orhan; Wegner., Pit; Albert., Justin; Arnrich., Bert (2022). 304–312.
[ BibTeX ] [ URL ] [ DOI ]
 
@conference{icaart22, author = {Konak., Orhan and Wegner., Pit and Albert., Justin and Arnrich., Bert}, booktitle = {Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,}, keywords = {justinalbert bertarnrich orhankonak}, organization = {INSTICC}, pages = {304-312}, publisher = {SciTePress}, title = {Unsupervised Activity Recognition Using Trajectory Heatmaps from Inertial Measurement Unit Data}, year = 2022 }
Extracting Alarm Events from the MIMIC-III Clinical Database. Chromik., Jonas; Pfitzner., Bjarne; Ihde., Nina; Michaelis., Marius; Schmidt., Denise; Klopfenstein., Sophie; Poncette., Akira-Sebastian; Balzer., Felix; Arnrich., Bert (2022). 328–335.
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
Lack of readily available data on ICU alarm events constitutes a major obstacle to alarm fatigue research. There are ICU databases available that aim to give a holistic picture of everything happening at the respective ICU. However, these databases do not contain data on alarm events. We utilise the vital parameters and alarm thresholds recorded in the MIMIC-III database in order to artificially extract alarm events from this database. Prior to that, we uncover, investigate, and mitigate inconsistencies we found in the data. The results of this work are an approach and an algorithm for cleaning the alarm data available in MIMIC-III and extract concrete alarm events from them. The data set generated by this algorithm is investigated in this work and can be used for further research into the problem of alarm fatigue.
@conference{chromik2022extracting, abstract = {Lack of readily available data on ICU alarm events constitutes a major obstacle to alarm fatigue research. There are ICU databases available that aim to give a holistic picture of everything happening at the respective ICU. However, these databases do not contain data on alarm events. We utilise the vital parameters and alarm thresholds recorded in the MIMIC-III database in order to artificially extract alarm events from this database. Prior to that, we uncover, investigate, and mitigate inconsistencies we found in the data. The results of this work are an approach and an algorithm for cleaning the alarm data available in MIMIC-III and extract concrete alarm events from them. The data set generated by this algorithm is investigated in this work and can be used for further research into the problem of alarm fatigue.}, author = {Chromik., Jonas and Pfitzner., Bjarne and Ihde., Nina and Michaelis., Marius and Schmidt., Denise and Klopfenstein., Sophie and Poncette., Akira{-}Sebastian and Balzer., Felix and Arnrich., Bert}, booktitle = {Proceedings of the 15th International Joint Conference on Biomedical Engineering Systems and Technologies - HEALTHINF,}, keywords = {bertarnrich bjarnepfitzner jonaschromik}, organization = {INSTICC}, pages = {328-335}, publisher = {SciTePress}, title = {Extracting Alarm Events from the MIMIC-III Clinical Database}, year = 2022 }
Have Your Cake and Log it Too: A Pilot Study Leveraging IMU Sensors for Real-time Food Journaling Notifications Kappattanavar, Arpita; Kremser, Marten; Arnrich, Bert (2022). (Vol. 5) 532–541.
[ BibTeX ] [ URL ]
 
@proceedings{kappattanavarhave, author = {Kappattanavar, Arpita and Kremser, Marten and Arnrich, Bert}, keywords = {bertarnrich arpitakappattanavar}, pages = {532-541}, title = {Have Your Cake and Log it Too: A Pilot Study Leveraging IMU Sensors for Real-time Food Journaling Notifications}, volume = 5, year = 2022 }
Towards Multi-Modal Recordings in Daily Life: A Baseline Assessment of an Experimental Framework Anders, Christoph; Moontaha, Sidratul; Arnrich, Bert in IS (2022). (Vol. H) 27–30. Information Society.
[ Abstract ] [ BibTeX ] [ URL ]
 
Background: Wearable devices can record physiological signals from humans to enable an objective assessment of their Mental State. In the future, such devices will enable researchers to work on paradigms outside, rather than only inside, of controlled laboratory environments. This transition requires a paradigm shift on how experiments are conducted, and introduces new challenges. Method: Here, an experimental framework for multi-modal baseline assessments is presented. The developed test battery covers stimuli and questionnaire presenters, and multi-modal data can be recorded in parallel, such as Photoplethysmography, Electroencephalography, Acceleration, and Electrodermal Activity data. The multi-modal data is extracted using a single platform, and synchronized using a shake detection tool. A baseline was recorded from eight participants in a controlled environment. Using Leave-One-Out Cross-Validation, the resampling of data, the ideal window size, and the applicability of Deep Learning for Mental Workload Classification were evaluated. In addition, participants were polled on the acceptance of using the wearable devices. Results: The binary classification performance declined by an average of 7.81% when using eye-blink removal, underlining the importance of data synchronization, correct artefact identification, evaluating and developing artefact removal techniques, and investigating on the robustness of the multi-modal setup. Experiments showed that the optimal window size for the acquired data is 30 seconds for Mental Workload classification, with which a Random Forest classifier and an optimized Deep Convolutional Neural Network achieved the best-balanced classification accuracy of 70.27% and 74.16%, respectively. Conclusions: This baseline assessment gives valuable insights on how to prototype stimulus presentation with different wearable devices and suggests future work packages, paving the way for researchers to investigate new paradigm outside of controlled environments.
@proceedings{is-2022, abstract = {Background: Wearable devices can record physiological signals from humans to enable an objective assessment of their Mental State. In the future, such devices will enable researchers to work on paradigms outside, rather than only inside, of controlled laboratory environments. This transition requires a paradigm shift on how experiments are conducted, and introduces new challenges. Method: Here, an experimental framework for multi-modal baseline assessments is presented. The developed test battery covers stimuli and questionnaire presenters, and multi-modal data can be recorded in parallel, such as Photoplethysmography, Electroencephalography, Acceleration, and Electrodermal Activity data. The multi-modal data is extracted using a single platform, and synchronized using a shake detection tool. A baseline was recorded from eight participants in a controlled environment. Using Leave-One-Out Cross-Validation, the resampling of data, the ideal window size, and the applicability of Deep Learning for Mental Workload Classification were evaluated. In addition, participants were polled on the acceptance of using the wearable devices. Results: The binary classification performance declined by an average of 7.81% when using eye-blink removal, underlining the importance of data synchronization, correct artefact identification, evaluating and developing artefact removal techniques, and investigating on the robustness of the multi-modal setup. Experiments showed that the optimal window size for the acquired data is 30 seconds for Mental Workload classification, with which a Random Forest classifier and an optimized Deep Convolutional Neural Network achieved the best-balanced classification accuracy of 70.27% and 74.16%, respectively. Conclusions: This baseline assessment gives valuable insights on how to prototype stimulus presentation with different wearable devices and suggests future work packages, paving the way for researchers to investigate new paradigm outside of controlled environments.}, author = {Anders, Christoph and Moontaha, Sidratul and Arnrich, Bert}, booktitle = {Proc.\ 25th International Multiconference INFORMATION SOCIETY Pervasive Health and Smart Sensing (IS 2022)}, keywords = {christophanders bertarnrich sidratulmoontaha}, pages = {27-30}, publisher = {Information Society}, series = {IS}, title = {Towards Multi-Modal Recordings in Daily Life: A Baseline Assessment of an Experimental Framework}, volume = {H}, year = 2022 }

2021

Domain-Specific Event Abstraction. Klessascheck, Finn; Lichtenstein, Tom; Meier, Martin; Remy, Simon; Sachs, Jan Philipp; Pufahl, Luise; Miotto, Riccardo; Bottinger, Erwin; Weske, Mathias in Business Information Systems (2021). 117–126.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Klessascheck2021, author = {Klessascheck, Finn and Lichtenstein, Tom and Meier, Martin and Remy, Simon and Sachs, Jan Philipp and Pufahl, Luise and Miotto, Riccardo and Bottinger, Erwin and Weske, Mathias}, journal = {Business Information Systems}, keywords = {boettinger hpims fb-boettinger}, month = {jul}, pages = {117–126}, publisher = {{TIB} Open Publishing}, title = {Domain-Specific Event Abstraction}, year = 2021 }
Perioperative Risk Assessment in Pancreatic Surgery Using Machine Learning. Pfitzner, Bjarne; Chromik, Jonas; Brabender, Rachel; Fischer, Eric; Kromer, Alexander; Winter, Axel; Moosburner, Simon; Sauer, Igor M.; Malinka, Thomas; Pratschke, Johann; Arnrich, Bert; Maurer, Max M. (2021). 2211–2214.
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
Pancreatic surgery is associated with a high risk for postoperative complications and death of patients. Complications occur in a variable interval after the procedure. Often, a patient has already left the ICU and is not properly monitored anymore when the complication occurs. Risk stratification models can assist in identifying patients at risk in order to keep these patients in ICU for longer. This, in turn, helps to identify complications earlier and increase survival rates. We trained multiple machine learning models on pre-, intra- and short term postoperative data from patients who underwent pancreatic resection at the Department of Surgery, Campus Charité Mitte | Campus Virchow-Klinikum, Charité – Universitätsmedizin Berlin. The presented models achieve an area under the precision-recall curve (AUPRC) of up to 0.51 for predicting patient death and 0.53 for predicting a specific major complication. Overall, we found that a classical logistic regression model performs best for the investigated classification tasks. As more patient data becomes available throughout the perioperative stay, the performance of the risk stratification model improves and should therefore repeatedly be computed.
@inproceedings{9630897, abstract = {Pancreatic surgery is associated with a high risk for postoperative complications and death of patients. Complications occur in a variable interval after the procedure. Often, a patient has already left the ICU and is not properly monitored anymore when the complication occurs. Risk stratification models can assist in identifying patients at risk in order to keep these patients in ICU for longer. This, in turn, helps to identify complications earlier and increase survival rates. We trained multiple machine learning models on pre-, intra- and short term postoperative data from patients who underwent pancreatic resection at the Department of Surgery, Campus Charité Mitte | Campus Virchow-Klinikum, Charité – Universitätsmedizin Berlin. The presented models achieve an area under the precision-recall curve (AUPRC) of up to 0.51 for predicting patient death and 0.53 for predicting a specific major complication. Overall, we found that a classical logistic regression model performs best for the investigated classification tasks. As more patient data becomes available throughout the perioperative stay, the performance of the risk stratification model improves and should therefore repeatedly be computed.}, author = {Pfitzner, Bjarne and Chromik, Jonas and Brabender, Rachel and Fischer, Eric and Kromer, Alexander and Winter, Axel and Moosburner, Simon and Sauer, Igor M. and Malinka, Thomas and Pratschke, Johann and Arnrich, Bert and Maurer, Max M.}, booktitle = {2021 43rd Annual International Conference of the IEEE Engineering in Medicine Biology Society (EMBC)}, keywords = {bertarnrich bjarnepfitzner jonaschromik}, pages = {2211-2214}, title = {Perioperative Risk Assessment in Pancreatic Surgery Using Machine Learning}, year = 2021 }
Impact of Custom Features of Do-it-yourself Artificial Pancreas Systems (DIYAPS) on Glycemic Outcomes of People with Type 1 Diabetes. Staszak, Wiktoria; Chromik, Jonas; Braune, Katarina; Arnrich, Bert (2021). 1472–1475.
[ BibTeX ] [ URL ] [ DOI ]
 
@inproceedings{9629487, author = {Staszak, Wiktoria and Chromik, Jonas and Braune, Katarina and Arnrich, Bert}, booktitle = {2021 43rd Annual International Conference of the IEEE Engineering in Medicine Biology Society (EMBC)}, keywords = {bertarnrich jonaschromik}, pages = {1472-1475}, title = {Impact of Custom Features of Do-it-yourself Artificial Pancreas Systems (DIYAPS) on Glycemic Outcomes of People with Type 1 Diabetes}, year = 2021 }
Scientific sexism: the gender bias in the scientific production of the Universidade de São Paulo. Oliveira-Ciabati, Livia; Santos, Luciane Loures; Hsiou, Annie Schmaltz; Sasso, Ariane Morassi; Castro, Margaret; Souza, Joao Paulo in Revista de Saúde Pública (2021). 55 46.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Oliveira-Ciabati2021, author = {Oliveira-Ciabati, Livia and Santos, Luciane Loures and Hsiou, Annie Schmaltz and Sasso, Ariane Morassi and Castro, Margaret and Souza, Joao Paulo}, journal = {Revista de Saúde Pública}, keywords = {myown fb-boettinger}, month = {October}, pages = 46, publisher = {Faculdade de Saúde Pública da Universidade de São Paulo}, title = {Scientific sexism: the gender bias in the scientific production of the Universidade de São Paulo.}, volume = 55, year = 2021 }
Predictive Approaches for Acute Dialysis Requirement and Death in COVID-19. Vaid, Akhil; Chan, Lili; Chaudhary, Kumardeep; Jaladanki, Suraj K.; Paranjpe, Ishan; Russak, Adam; Kia, Arash; Timsina, Prem; Levin, Matthew A.; He, John Cijiang; Bottinger, Erwin P.; Charney, Alexander W.; Fayad, Zahi A.; Coca, Steven G.; Glicksberg, Benjamin S.; Nadkarni, Girish N. in Clinical Journal of the American Society of Nephrology (2021). 16(8) 1158–1168.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Vaid2021, author = {Vaid, Akhil and Chan, Lili and Chaudhary, Kumardeep and Jaladanki, Suraj K. and Paranjpe, Ishan and Russak, Adam and Kia, Arash and Timsina, Prem and Levin, Matthew A. and He, John Cijiang and Bottinger, Erwin P. and Charney, Alexander W. and Fayad, Zahi A. and Coca, Steven G. and Glicksberg, Benjamin S. and Nadkarni, Girish N.}, journal = {Clinical Journal of the American Society of Nephrology}, keywords = {boettinger hpims fb-boettinger}, month = {may}, number = 8, pages = {1158–1168}, publisher = {American Society of Nephrology ({ASN})}, title = {Predictive Approaches for Acute Dialysis Requirement and Death in {COVID}-19}, volume = 16, year = 2021 }
Effects of Early vs. Late Time-Restricted Eating on Cardiometabolic Health, Inflammation, and Sleep in Overweight and Obese Women: A Study Protocol for the ChronoFast Trial. Peters, Beeke; Koppold-Liebscher, Daniela A.; Schuppelius, Bettina; Steckhan, Nico; Pfeiffer, Andreas F. H.; Kramer, Achim; Michalsen, Andreas; Pivovarova-Ramich, Olga in Frontiers in Nutrition (2021). 8
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Peters2021, author = {Peters, Beeke and Koppold-Liebscher, Daniela A. and Schuppelius, Bettina and Steckhan, Nico and Pfeiffer, Andreas F. H. and Kramer, Achim and Michalsen, Andreas and Pivovarova-Ramich, Olga}, journal = {Frontiers in Nutrition}, keywords = {nicosteckhan bertarnrich}, month = {nov}, publisher = {Frontiers Media {SA}}, title = {Effects of Early vs. Late Time-Restricted Eating on Cardiometabolic Health, Inflammation, and Sleep in Overweight and Obese Women: A Study Protocol for the {ChronoFast} Trial}, volume = 8, year = 2021 }
Using interpretability approaches to update textquotedblleftblack-boxtextquotedblright clinical prediction models: an external validation study in nephrology. da Cruz, Harry Freitas; Pfahringer, Boris; Martensen, Tom; Schneider, Frederic; Meyer, Alexander; Bottinger, Erwin; Schapranow, Matthieu-P. in Artificial Intelligence in Medicine (2021). 111 101982.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{daCruz2021, author = {da Cruz, Harry Freitas and Pfahringer, Boris and Martensen, Tom and Schneider, Frederic and Meyer, Alexander and Bottinger, Erwin and Schapranow, Matthieu-P.}, journal = {Artificial Intelligence in Medicine}, keywords = {boettinger fb-boettinger}, month = {jan}, pages = 101982, publisher = {Elsevier {BV}}, title = {Using interpretability approaches to update {\textquotedblleft}black-box{\textquotedblright} clinical prediction models: an external validation study in nephrology}, volume = 111, year = 2021 }
Interaction-Based Feature Selection Algorithm Outperforms Polygenic Risk Score in Predicting Parkinson’s Disease Status. Cope, Justin L.; Baukmann, Hannes A.; Klinger, Jörn E.; Ravarani, Charles N. J.; Bottinger, Erwin P.; Konigorski, Stefan; Schmidt, Marco F. in Frontiers in Genetics (2021). 12
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Cope2021, author = {Cope, Justin L. and Baukmann, Hannes A. and Klinger, Jörn E. and Ravarani, Charles N. J. and Bottinger, Erwin P. and Konigorski, Stefan and Schmidt, Marco F.}, journal = {Frontiers in Genetics}, keywords = {boettinger fb-boettinger}, month = {oct}, publisher = {Frontiers Media {SA}}, title = {Interaction-Based Feature Selection Algorithm Outperforms Polygenic Risk Score in Predicting Parkinson's Disease Status}, volume = 12, year = 2021 }
Impact of a vibrotactile belt on emotionally challenging everyday situations of the blind. Brandebusemeyer, Charlotte; Luther, Anna Ricarda; König, Sabine U; König, Peter; Kärcher, Silke M in Sensors (2021). 21(21) 7384.
[ BibTeX ] [ URL ]
 
@article{brandebusemeyer2021impact, author = {Brandebusemeyer, Charlotte and Luther, Anna Ricarda and K{ö}nig, Sabine U and K{ö}nig, Peter and K{ä}rcher, Silke M}, journal = {Sensors}, keywords = {charlottebrandebusemeyer prior-hpi}, number = 21, pages = 7384, publisher = {MDPI}, title = {Impact of a vibrotactile belt on emotionally challenging everyday situations of the blind}, volume = 21, year = 2021 }
Evaluation of a Machine Learning Approach Utilizing Wearable Data for Prediction of SARS-CoV-2 Infection in Healthcare Workers. Hirten, Robert P.; Tomalin, Lewis; Danieletto, Matteo; Golden, Eddye; Zweig, Micol; Kaur, Sparshdeep; Helmus, Drew; Biello, Anthony; Pyzik, Renata; Bottinger, Erwin P; Keefer, Laurie; Charney, Dennis; Nadkarni, Girish N.; Suarez-Farinas, Mayte; Fayad, Zahi A. (2021).
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Hirten2021, author = {Hirten, Robert P. and Tomalin, Lewis and Danieletto, Matteo and Golden, Eddye and Zweig, Micol and Kaur, Sparshdeep and Helmus, Drew and Biello, Anthony and Pyzik, Renata and Bottinger, Erwin P and Keefer, Laurie and Charney, Dennis and Nadkarni, Girish N. and Suarez-Farinas, Mayte and Fayad, Zahi A.}, keywords = {boettinger hpims fb-boettinger}, month = {nov}, publisher = {Cold Spring Harbor Laboratory}, title = {Evaluation of a Machine Learning Approach Utilizing Wearable Data for Prediction of SARS-CoV-2 Infection in Healthcare Workers}, year = 2021 }
Analysis of Deep Transfer Learning Using DeepConvLSTM for Human Activity Recognition from Wearable Sensors. Kalabakov, Stefan; Gjoreski, Martin; Gjoreski, Hristijan; Gams, Matjaz in Informatica (2021). 45(2)
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
Human Activity Recognition (HAR) from wearable sensors has gained significant attention in the last few decades, largely because of the potential healthcare benefits. For many years, HAR was done using classical machine learning approaches that require extraction of features. With the resurgence of deep learning, a major shift happened and at the moment, HAR researchers are mainly investigating different kinds of deep neural networks. However, deep learning comes with the challenge of having access to large amounts of labeled examples, which in the field of HAR is considered an expensive task, both in terms of time and effort. Another challenge is the fact that the training and testing data in HAR can be different due to the personal preferences of different people when performing the same activity. In order to try and mitigate these problems, in this paper we explore transfer learning, a paradigm for transferring knowledge from a source domain, to another related target domain. More specifically, we explore the effects of transferring knowledge between two open-source datasets, the Opportunity and JSI-FOS datasets, using weight-transfer for the DeepConvLSTM architecture. We also explore the performance of this transfer at different amounts of labeled data from the target domain. The experiments showed that it is beneficial to transfer the weights of fewer layers, and that deep transfer learning can perform better than a domain-specific deep end-to-end model in specific circumstances. Finally, we show that deep transfer learning is a viable alternative to classical machine learning approaches as it produces comparable results and does not require feature extraction.
@article{kalabakov2021analysis, abstract = {Human Activity Recognition (HAR) from wearable sensors has gained significant attention in the last few decades, largely because of the potential healthcare benefits. For many years, HAR was done using classical machine learning approaches that require extraction of features. With the resurgence of deep learning, a major shift happened and at the moment, HAR researchers are mainly investigating different kinds of deep neural networks. However, deep learning comes with the challenge of having access to large amounts of labeled examples, which in the field of HAR is considered an expensive task, both in terms of time and effort. Another challenge is the fact that the training and testing data in HAR can be different due to the personal preferences of different people when performing the same activity. In order to try and mitigate these problems, in this paper we explore transfer learning, a paradigm for transferring knowledge from a source domain, to another related target domain. More specifically, we explore the effects of transferring knowledge between two open-source datasets, the Opportunity and JSI-FOS datasets, using weight-transfer for the DeepConvLSTM architecture. We also explore the performance of this transfer at different amounts of labeled data from the target domain. The experiments showed that it is beneficial to transfer the weights of fewer layers, and that deep transfer learning can perform better than a domain-specific deep end-to-end model in specific circumstances. Finally, we show that deep transfer learning is a viable alternative to classical machine learning approaches as it produces comparable results and does not require feature extraction.}, author = {Kalabakov, Stefan and Gjoreski, Martin and Gjoreski, Hristijan and Gams, Matjaz}, journal = {Informatica}, keywords = {bertarnrich prior-hpi kalabakovstefan}, number = 2, title = {Analysis of Deep Transfer Learning Using DeepConvLSTM for Human Activity Recognition from Wearable Sensors}, volume = 45, year = 2021 }
Multi-ethnic polygenic risk modifies the association between APOL1 high risk genotypes and chronic kidney disease. Vy, Ha My T.; Gulamali, Faris F.; Glicksberg, Benjamin S; Gutierrez, Orlando; Cooper, Richard; Bottinger, Erwin P; Cho, Judy; Loos, Ruth J.F.; Horowitz, Carol R.; Do, Ron; Nadkarni, Girish N (2021).
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Vy2021, author = {Vy, Ha My T. and Gulamali, Faris F. and Glicksberg, Benjamin S and Gutierrez, Orlando and Cooper, Richard and Bottinger, Erwin P and Cho, Judy and Loos, Ruth J.F. and Horowitz, Carol R. and Do, Ron and Nadkarni, Girish N}, keywords = {boettinger hpims}, month = {nov}, publisher = {Cold Spring Harbor Laboratory}, title = {Multi-ethnic polygenic risk modifies the association between {APOL}1 high risk genotypes and chronic kidney disease}, year = 2021 }
Electronic phenotyping technique for diagnosing chronic kidney disease. Nadkarni, Girish; Gottesman, Omri; Ellis, Stephen Bartlett; Bottinger, Erwin (2021).
[ BibTeX ]
 
@misc{nadkarni2021electronic, author = {Nadkarni, Girish and Gottesman, Omri and Ellis, Stephen Bartlett and Bottinger, Erwin}, keywords = {boettinger hpims fb-boettinger}, note = {US Patent 11,101,021}, publisher = {Google Patents}, title = {Electronic phenotyping technique for diagnosing chronic kidney disease}, year = 2021 }
Phe2vec: Automated disease phenotyping based on unsupervised embeddings from electronic health records. Freitas, Jessica K. De; Johnson, Kipp W.; Golden, Eddye; Nadkarni, Girish N.; Dudley, Joel T.; Bottinger, Erwin P.; Glicksberg, Benjamin S.; Miotto, Riccardo in Patterns (2021). 2(9) 100337.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{DeFreitas2021, author = {Freitas, Jessica K. De and Johnson, Kipp W. and Golden, Eddye and Nadkarni, Girish N. and Dudley, Joel T. and Bottinger, Erwin P. and Glicksberg, Benjamin S. and Miotto, Riccardo}, journal = {Patterns}, keywords = {boettinger hpims fb-boettinger}, month = {sep}, number = 9, pages = 100337, publisher = {Elsevier {BV}}, title = {Phe2vec: Automated disease phenotyping based on unsupervised embeddings from electronic health records}, volume = 2, year = 2021 }
Implicit Model Specialization through Dag-Based Decentralized Federated Learning. Beilharz, Jossekin; Pfitzner, Bjarne; Schmid, Robert; Geppert, Paul; Arnrich, Bert; Polze, Andreas in Middleware ’21 (2021). 310–322.
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
Federated learning allows a group of distributed clients to train a common machine learning model on private data. The exchange of model updates is managed either by a central entity or in a decentralized way, e.g. by a blockchain. However, the strong generalization across all clients makes these approaches unsuited for non-independent and identically distributed (non-IID) data.We propose a unified approach to decentralization and personalization in federated learning that is based on a directed acyclic graph (DAG) of model updates. Instead of training a single global model, clients specialize on their local data while using the model updates from other clients dependent on the similarity of their respective data. This specialization implicitly emerges from the DAG-based communication and selection of model updates. Thus, we enable the evolution of specialized models, which focus on a subset of the data and therefore cover non-IID data better than federated learning in a centralized or blockchain-based setup.To the best of our knowledge, the proposed solution is the first to unite personalization and poisoning robustness in fully decentralized federated learning. Our evaluation shows that the specialization of models emerges directly from the DAG-based communication of model updates on three different datasets. Furthermore, we show stable model accuracy and less variance across clients when compared to federated averaging.
@inproceedings{10.1145/3464298.3493403, abstract = {Federated learning allows a group of distributed clients to train a common machine learning model on private data. The exchange of model updates is managed either by a central entity or in a decentralized way, e.g. by a blockchain. However, the strong generalization across all clients makes these approaches unsuited for non-independent and identically distributed (non-IID) data.We propose a unified approach to decentralization and personalization in federated learning that is based on a directed acyclic graph (DAG) of model updates. Instead of training a single global model, clients specialize on their local data while using the model updates from other clients dependent on the similarity of their respective data. This specialization implicitly emerges from the DAG-based communication and selection of model updates. Thus, we enable the evolution of specialized models, which focus on a subset of the data and therefore cover non-IID data better than federated learning in a centralized or blockchain-based setup.To the best of our knowledge, the proposed solution is the first to unite personalization and poisoning robustness in fully decentralized federated learning. Our evaluation shows that the specialization of models emerges directly from the DAG-based communication of model updates on three different datasets. Furthermore, we show stable model accuracy and less variance across clients when compared to federated averaging.}, address = {New York, NY, USA}, author = {Beilharz, Jossekin and Pfitzner, Bjarne and Schmid, Robert and Geppert, Paul and Arnrich, Bert and Polze, Andreas}, booktitle = {Proceedings of the 22nd International Middleware Conference}, keywords = {bertarnrich bjarnepfitzner}, pages = {310–322}, publisher = {Association for Computing Machinery}, series = {Middleware '21}, title = {Implicit Model Specialization through Dag-Based Decentralized Federated Learning}, year = 2021 }
Optimal Deployment in Emergency Medicine with Genetic Algorithm Exemplified by Lifeguard Assignments^*. Chromik, Jonas; Arnrich, Bert (2021). 1806–1809.
[ BibTeX ] [ URL ] [ DOI ]
 
@inproceedings{9629796, author = {Chromik, Jonas and Arnrich, Bert}, booktitle = {2021 43rd Annual International Conference of the IEEE Engineering in Medicine Biology Society (EMBC)}, keywords = {bertarnrich jonaschromik}, pages = {1806-1809}, title = {Optimal Deployment in Emergency Medicine with Genetic Algorithm Exemplified by Lifeguard Assignments^*}, year = 2021 }
Head-AR: Human Activity Recognition with Head-Mounted IMU Using Weighted Ensemble Learning. Gjoreski, Hristijan; Kiprijanovska, Ivana; Stankoski, Simon; Kalabakov, Stefan; Broulidakis, John; Nduka, Charles; Gjoreski, Martin in Activity and Behavior Computing, M. A. R. Ahad, S. Inoue, D. Roggen, K. Fujinami (eds.) (2021). 153–167.
[ Abstract ] [ BibTeX ] [ DOI ]
 
This paper describes the machine learning (ML) method Head-AR, which achieved the highest performance in a competition with 11 other algorithms and won the Emteq Activity Recognition challenge. The goal of the challenge was to recognize eight activities of daily life from a device mounted on the head, which provided data from a 3-axis IMU: accelerometer, gyroscope, and magnetometer. The challenge dataset was collected by four subjects, of which one subject was used as a test for the challenge evaluation. The method processes the stream of sensors data and recognizes one of the eight activities every two seconds. The method is based on weighted ensemble learning, which combines three models: (i) a dynamic time warping classification model, which analyzes raw accelerometer data; (ii) a classification model that uses expert features; (iii) and a classification model that uses features selected by a feature selection algorithm. To compute the final output, the predictions of the three models are combined using a novel weighing scheme. The method achieved an F1-score of 61.25% on the competition’s evaluation.
@incollection{gjoreski2021headar, abstract = {This paper describes the machine learning (ML) method Head-AR, which achieved the highest performance in a competition with 11 other algorithms and won the Emteq Activity Recognition challenge. The goal of the challenge was to recognize eight activities of daily life from a device mounted on the head, which provided data from a 3-axis IMU: accelerometer, gyroscope, and magnetometer. The challenge dataset was collected by four subjects, of which one subject was used as a test for the challenge evaluation. The method processes the stream of sensors data and recognizes one of the eight activities every two seconds. The method is based on weighted ensemble learning, which combines three models: (i) a dynamic time warping classification model, which analyzes raw accelerometer data; (ii) a classification model that uses expert features; (iii) and a classification model that uses features selected by a feature selection algorithm. To compute the final output, the predictions of the three models are combined using a novel weighing scheme. The method achieved an F1-score of 61.25% on the competition’s evaluation.}, address = {Springer Singapore}, author = {Gjoreski, Hristijan and Kiprijanovska, Ivana and Stankoski, Simon and Kalabakov, Stefan and Broulidakis, John and Nduka, Charles and Gjoreski, Martin}, booktitle = {Activity and Behavior Computing}, editor = {Ahad, Md Atiqur Rahman and Inoue, Sozo and Roggen, Daniel and Fujinami, Kaori}, howpublished = {Singapore}, keywords = {bertarnrich prior-hpi kalabakovstefan}, pages = {153-167}, title = {Head-AR: Human Activity Recognition with Head-Mounted IMU Using Weighted Ensemble Learning}, year = 2021 }
Mono- and bi-allelic effects of coding variants on disease in 176,899 Finns. Heyne, H. O.; Karjalainen, J.; Karczewski, K. J.; Lemmelä, S. M.; Zhou, W.; FinnGen; Havulinna, A. S.; Kurki, M.; Rehm, H. L.; Palotie, A.; Daly, M. J. in medRxiv (2021).
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
Identifying Mendelian diseases with recessive inheritance is challenging as the majority of cases are caused by compound heterozygous genotypes which require sequencing data in families to definitively identify. Bottleneck events, such as in the Finnish population, enrich specific homozygous variants to higher frequencies and thus facilitate identification of disease associations through easily recognized homozygous genotypes. Here, we study homozygous and heterozygous effects of 82,516 coding variants on 2,444 disease endpoints using nationwide electronic health record (EHR) data of 176,899 Finns. We find known and novel associations to homozygous genotypes across a broad spectrum of phenotypes such as retinal dystrophy, adult-onset cataract and female infertility (13/20 of which would have been missed by the traditional additive GWAS model). With these results, and supporting simulations, we demonstrate the added benefit of homozygous scans in GWAS. We further use these results to explore inheritance patterns of known Mendelian variants. We find many Mendelian variants whose inheritance cannot be adequately described with the traditional definition of dominant or recessive. In particular, we find disease risk in heterozygous carriers of variants known to cause disease with recessive inheritance, as well as for variants labeled benign in ClinVar. Our results demonstrate how biobank efforts, particularly in founder populations, can broaden our understanding of the impact of genetic variants.Competing Interest StatementA.P. is a member of the Pfizer Genetics Scientific Advisory Panel. M.J.D is a founder of Maze Therapeutics. The remaining authors declare no competing interests.Clinical Protocols https://finngen.gitbook.io/documentation/ Funding StatementThe FinnGen project is funded by two grants from Business Finland (HUS 4685/31/2016 and UH 4386/31/2016) and eleven industry partners (AbbVie Inc, AstraZeneca UK Ltd, Biogen MA Inc, Celgene Corporation, Celgene International II Sàrl, Genentech Inc, Merck Sharp \& Dohme Corp, Pfizer Inc., GlaxoSmithKline, Sanofi, Maze Therapeutics Inc., Janssen Biotech Inc). Following biobanks are acknowledged for delivering biobank samples to FinnGen: Auria Biobank (www.auria.fi/biopankki), THL Biobank (www.thl.fi/biobank), Helsinki Biobank (www.helsinginbiopankki.fi), Biobank Borealis of Northern Finland (https://www.ppshp.fi/Tutkimus-ja-opetus/Biopankki/Pages/Biobank-Borealis-briefly-in-English.aspx), Finnish Clinical Biobank Tampere (www.tays.fi/en-US/Research_and_development/Finnish_Clinical_Biobank_Tampere), Biobank of Eastern Finland (www.ita-suomenbiopankki.fi/en), Central Finland Biobank (www.ksshp.fi/fi-FI/Potilaalle/Biopankki), Finnish Red Cross Blood Service Biobank (www.veripalvelu.fi/verenluovutus/biopankkitoiminta) and Terveystalo Biobank (www.terveystalo.com/fi/Yritystietoa/Terveystalo-Biopankki/Biopankki/). All Finnish Biobanks are members of BBMRI.fi infrastructure (www.bbmri.fi).Author DeclarationsI confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.YesThe details of the IRB/oversight body that provided approval or exemption for the research described are given below:The Coordinating Ethics Committee of the Hospital District of Helsinki and Uusimaa (HUS) approved the FinnGen study protocol Nr HUS/990/2017. The FinnGen project is approved by Finnish Institute for Health and Welfare (THL), approval number THL/2031/6.02.00/2017, amendments THL/1101/5.05.00/2017, THL/341/6.02.00/2018, THL/2222/6.02.00/2018, THL/283/6.02.00/2019), Digital and population data service agency VRK43431/2017-3, VRK/6909/2018-3, the Social Insurance Institution (KELA) KELA 58/522/2017, KELA 131/522/2018, KELA 70/522/2019 and Statistics Finland TK-53-1041-17. The Biobank Access Decisions for FinnGen samples and data utilized in FinnGen Data Freeze 4 include: THL Biobank BB2017_55, BB2017_111, BB2018_19, BB_2018_34, BB_2018_67, BB2018_71, BB2019_7 Finnish Red Cross Blood Service Biobank 7.12.2017, Helsinki Biobank HUS/359/2017, Auria Biobank AB17-5154, Biobank Borealis of Northern Finland_2017_1013, Biobank of Eastern Finland 1186/2018, Finnish Clinical Biobank Tampere MH0004, Central Finland Biobank 1-2017, and Terveystalo Biobank STB 2018001. UK biobank data was accessed under protocol 31063.I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.YesI understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).YesI have followed all appropriate research reporting guidelines and uploaded the relevant EQUATOR Network research reporting checklist(s) and other pertinent material as supplementary files, if applicable.YesAll summary statistics described in this manuscript can be found in the Supplementary Material. Additional summary statistics of additive and recessive GWAS of FinnGen release 4 can be investigated in our web browser at http://r4.finngen.fi/ or downloaded at https://www.finngen.fi/en/access_results. A full list of FinnGen endpoints for release 4 is available at https://www.finngen.fi/en/researchers/clinical-endpoints. http://r4.finngen.fi/ https://www.finngen.fi/en/access_results
@article{Heyne2021.11.06.21265920, abstract = {Identifying Mendelian diseases with recessive inheritance is challenging as the majority of cases are caused by compound heterozygous genotypes which require sequencing data in families to definitively identify. Bottleneck events, such as in the Finnish population, enrich specific homozygous variants to higher frequencies and thus facilitate identification of disease associations through easily recognized homozygous genotypes. Here, we study homozygous and heterozygous effects of 82,516 coding variants on 2,444 disease endpoints using nationwide electronic health record (EHR) data of 176,899 Finns. We find known and novel associations to homozygous genotypes across a broad spectrum of phenotypes such as retinal dystrophy, adult-onset cataract and female infertility (13/20 of which would have been missed by the traditional additive GWAS model). With these results, and supporting simulations, we demonstrate the added benefit of homozygous scans in GWAS. We further use these results to explore inheritance patterns of known Mendelian variants. We find many Mendelian variants whose inheritance cannot be adequately described with the traditional definition of dominant or recessive. In particular, we find disease risk in heterozygous carriers of variants known to cause disease with recessive inheritance, as well as for variants labeled benign in ClinVar. Our results demonstrate how biobank efforts, particularly in founder populations, can broaden our understanding of the impact of genetic variants.Competing Interest StatementA.P. is a member of the Pfizer Genetics Scientific Advisory Panel. M.J.D is a founder of Maze Therapeutics. The remaining authors declare no competing interests.Clinical Protocols https://finngen.gitbook.io/documentation/ Funding StatementThe FinnGen project is funded by two grants from Business Finland (HUS 4685/31/2016 and UH 4386/31/2016) and eleven industry partners (AbbVie Inc, AstraZeneca UK Ltd, Biogen MA Inc, Celgene Corporation, Celgene International II S{à}rl, Genentech Inc, Merck Sharp \& Dohme Corp, Pfizer Inc., GlaxoSmithKline, Sanofi, Maze Therapeutics Inc., Janssen Biotech Inc). Following biobanks are acknowledged for delivering biobank samples to FinnGen: Auria Biobank (www.auria.fi/biopankki), THL Biobank (www.thl.fi/biobank), Helsinki Biobank (www.helsinginbiopankki.fi), Biobank Borealis of Northern Finland (https://www.ppshp.fi/Tutkimus-ja-opetus/Biopankki/Pages/Biobank-Borealis-briefly-in-English.aspx), Finnish Clinical Biobank Tampere (www.tays.fi/en-US/Research_and_development/Finnish_Clinical_Biobank_Tampere), Biobank of Eastern Finland (www.ita-suomenbiopankki.fi/en), Central Finland Biobank (www.ksshp.fi/fi-FI/Potilaalle/Biopankki), Finnish Red Cross Blood Service Biobank (www.veripalvelu.fi/verenluovutus/biopankkitoiminta) and Terveystalo Biobank (www.terveystalo.com/fi/Yritystietoa/Terveystalo-Biopankki/Biopankki/). All Finnish Biobanks are members of BBMRI.fi infrastructure (www.bbmri.fi).Author DeclarationsI confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.YesThe details of the IRB/oversight body that provided approval or exemption for the research described are given below:The Coordinating Ethics Committee of the Hospital District of Helsinki and Uusimaa (HUS) approved the FinnGen study protocol Nr HUS/990/2017. The FinnGen project is approved by Finnish Institute for Health and Welfare (THL), approval number THL/2031/6.02.00/2017, amendments THL/1101/5.05.00/2017, THL/341/6.02.00/2018, THL/2222/6.02.00/2018, THL/283/6.02.00/2019), Digital and population data service agency VRK43431/2017-3, VRK/6909/2018-3, the Social Insurance Institution (KELA) KELA 58/522/2017, KELA 131/522/2018, KELA 70/522/2019 and Statistics Finland TK-53-1041-17. The Biobank Access Decisions for FinnGen samples and data utilized in FinnGen Data Freeze 4 include: THL Biobank BB2017_55, BB2017_111, BB2018_19, BB_2018_34, BB_2018_67, BB2018_71, BB2019_7 Finnish Red Cross Blood Service Biobank 7.12.2017, Helsinki Biobank HUS/359/2017, Auria Biobank AB17-5154, Biobank Borealis of Northern Finland_2017_1013, Biobank of Eastern Finland 1186/2018, Finnish Clinical Biobank Tampere MH0004, Central Finland Biobank 1-2017, and Terveystalo Biobank STB 2018001. UK biobank data was accessed under protocol 31063.I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.YesI understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).YesI have followed all appropriate research reporting guidelines and uploaded the relevant EQUATOR Network research reporting checklist(s) and other pertinent material as supplementary files, if applicable.YesAll summary statistics described in this manuscript can be found in the Supplementary Material. Additional summary statistics of additive and recessive GWAS of FinnGen release 4 can be investigated in our web browser at http://r4.finngen.fi/ or downloaded at https://www.finngen.fi/en/access_results. A full list of FinnGen endpoints for release 4 is available at https://www.finngen.fi/en/researchers/clinical-endpoints. http://r4.finngen.fi/ https://www.finngen.fi/en/access_results}, author = {Heyne, H. O. and Karjalainen, J. and Karczewski, K. J. and Lemmel{ä}, S. M. and Zhou, W. and FinnGen and Havulinna, A. S. and Kurki, M. and Rehm, H. L. and Palotie, A. and Daly, M. J.}, journal = {medRxiv}, keywords = {myown}, publisher = {Cold Spring Harbor Laboratory Press}, title = {Mono- and bi-allelic effects of coding variants on disease in 176,899 Finns}, year = 2021 }
Using Machine Learning to Predict Perceived Exertion During Resistance Training With Wearable Heart Rate and Movement Sensors. Albert, Justin; Herdick, Arne; Brahms, Clemens Markus; Granacher, Urs; Arnrich, Bert (2021).
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
The quantification of subjective exertion during training is an important measurement as it has the potential to avoid injuries resulting from overtraining. In this paper, we present a method to predict the subjective exertion during resistance training using Inertial Measurement Units (IMU) and electrocardiographical data. The participants’ subjective exertion was assessed using a Rating of Perceived Exertion (RPE) scale. We obtained data from 16 participants performing squats on a flywheel training machine while being equipped with six IMU sensors and an electrocardiography (ECG) sensor. Data was analyzed using multiple regressors, such as Support Vector Regression, Random Forests, and Gradient Boosting Regression Trees, to predict the personal exertion level on the processed IMU and ECG data. The best learning model achieved a mean absolute percentage error of 7.71% with a Pearson correlation coefficient of 0.85 and a R 2 of 0.48. Additionally, we investigated the impact of supplementing the IMU data features with ECG-derived heart rate variability (HRV) parameters in the training stage. Our results indicate that the HRV parameters derived from ECG significantly improve prediction results, with the training impulse (TRIMP) parameter acting as the most informative feature for predicting perceived exertion.
@inproceedings{albert2021using, abstract = {The quantification of subjective exertion during training is an important measurement as it has the potential to avoid injuries resulting from overtraining. In this paper, we present a method to predict the subjective exertion during resistance training using Inertial Measurement Units (IMU) and electrocardiographical data. The participants’ subjective exertion was assessed using a Rating of Perceived Exertion (RPE) scale. We obtained data from 16 participants performing squats on a flywheel training machine while being equipped with six IMU sensors and an electrocardiography (ECG) sensor. Data was analyzed using multiple regressors, such as Support Vector Regression, Random Forests, and Gradient Boosting Regression Trees, to predict the personal exertion level on the processed IMU and ECG data. The best learning model achieved a mean absolute percentage error of 7.71% with a Pearson correlation coefficient of 0.85 and a R 2 of 0.48. Additionally, we investigated the impact of supplementing the IMU data features with ECG-derived heart rate variability (HRV) parameters in the training stage. Our results indicate that the HRV parameters derived from ECG significantly improve prediction results, with the training impulse (TRIMP) parameter acting as the most informative feature for predicting perceived exertion.}, address = {Los Alamitos, CA, USA}, author = {Albert, Justin and Herdick, Arne and Brahms, Clemens Markus and Granacher, Urs and Arnrich, Bert}, booktitle = {2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)}, keywords = {justinalbert bertarnrich arneherdick}, month = {dec}, publisher = {IEEE Computer Society}, title = {Using Machine Learning to Predict Perceived Exertion During Resistance Training With Wearable Heart Rate and Movement Sensors}, year = 2021 }
Gibt es ein Recht auf medizinische Behandlung mittels KI?. Schapranow, Matthieu-P.; Loskill, Hannelore; Budde, Klemens in Management & Krankenhaus (2021). 40(10) 1.
[ BibTeX ]
 
@article{schapranow2021recht, author = {Schapranow, Matthieu-P. and Loskill, Hannelore and Budde, Klemens}, journal = {Management & Krankenhaus}, keywords = {myown pls}, month = {dec}, number = 10, pages = 1, title = {Gibt es ein Recht auf medizinische Behandlung mittels KI?}, volume = 40, year = 2021 }
Streitsache: Gibt es ein Recht auf medizinische Behandlung mit KI?. Schapranow, Matthieu-P.; Loskill, Hannelore; Budde, Klemens in gesundhyte.de: Das Magazin für Digitale Gesundheit in Deutschland (2021). 14 96–97.
[ BibTeX ]
 
@article{schapranow2021streitsache, author = {Schapranow, Matthieu-P. and Loskill, Hannelore and Budde, Klemens}, journal = {gesundhyte.de: Das Magazin für Digitale Gesundheit in Deutschland}, keywords = {myown pls}, month = {dec}, pages = {96–97}, title = {Streitsache: Gibt es ein Recht auf medizinische Behandlung mit KI?}, volume = 14, year = 2021 }
Zwischen individualisierten Therapieoptionen und gläsernen Patienten. Budde, Klemens; Schapranow, Matthieu-P.; Kirchner, Elsa; Zahn, Thomas in gesundhyte.de: Das Magazin für Digitale Gesundheit in Deutschland (2021). 14 32–36.
[ BibTeX ]
 
@article{budde2021zwischen, author = {Budde, Klemens and Schapranow, Matthieu-P. and Kirchner, Elsa and Zahn, Thomas}, journal = {gesundhyte.de: Das Magazin für Digitale Gesundheit in Deutschland}, keywords = {myown}, month = {dec}, pages = {32–36}, title = {Zwischen individualisierten Therapieoptionen und gläsernen Patienten}, volume = 14, year = 2021 }
FAIRe Datennutzung: Erfahrungen aus Verbundprojekten. Ganzinger, Matthias; Schapranow, Matthieu-P. in gesundhyte.de: Das Magazin für Digitale Gesundheit in Deutschland. (2021). 14 57–61.
[ BibTeX ]
 
@article{ganzinger2021faire, author = {Ganzinger, Matthias and Schapranow, Matthieu-P.}, journal = {gesundhyte.de: Das Magazin für Digitale Gesundheit in Deutschland.}, keywords = {myown highmed sahra}, month = {dec}, pages = {57-61}, title = {FAIRe Datennutzung: Erfahrungen aus Verbundprojekten}, volume = 14, year = 2021 }
Digital Therapeutic Care and Decision Support Interventions for People With Low Back Pain: Systematic Review. Lewkowicz, Daniel; Slosarek, Tamara; Wernicke, Sarah; Winne, Antonia; Wohlbrandt, Attila M; Bottinger, Erwin in JMIR Rehabil Assist Technol (2021). 8(4) e26612.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{info:doi/10.2196/26612, author = {Lewkowicz, Daniel and Slosarek, Tamara and Wernicke, Sarah and Winne, Antonia and Wohlbrandt, Attila M and Bottinger, Erwin}, journal = {JMIR Rehabil Assist Technol}, keywords = {myown bottinger bottinger-not-dhc dhc}, month = {nov}, number = 4, pages = {e26612}, title = {Digital Therapeutic Care and Decision Support Interventions for People With Low Back Pain: Systematic Review.}, volume = 8, year = 2021 }
Sensor-Based Obsessive-Compulsive Disorder Detection With Personalised Federated Learning. Kirsten, Kristina; Pfitzner, Bjarne; Löper, Lando; Arnrich, Bert (2021). 333–339.
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
The mental illness Obsessive-Compulsive Disorder (OCD) is characterised by obsessive thoughts and compulsive actions. The latter can occur as repetitive activities to ensure that severe fears do not come true. A diagnosis of the disease is usually very late due to a lack of knowledge and shame of the patient. Nevertheless, early detection can significantly increase the success of therapy. With the development of new wearable sensors, it is possible to recognise human activities. Accordingly, wearables can also be used to identify recurring activities that indicate an OCD. Through this form of an automatic detection system, a diagnosis can be made earlier and thus therapy can be started sooner. Since compulsive behaviour is very individual and varies from patient to patient, this paper deals with personalised federated machine learning models. We first adapt the publicly available OPPORTUNITY dataset to simulate OCD behaviour. Secondly, we evaluate two existing personalised federated learning algorithms against baseline approaches. Finally, we propose a hybrid approach that merges the two evaluated algorithms and reaches a mean area under the precision-recall curve (AUPRC) of 0.954 across clients.
@inproceedings{kirsten2021sensorbased, abstract = {The mental illness Obsessive-Compulsive Disorder (OCD) is characterised by obsessive thoughts and compulsive actions. The latter can occur as repetitive activities to ensure that severe fears do not come true. A diagnosis of the disease is usually very late due to a lack of knowledge and shame of the patient. Nevertheless, early detection can significantly increase the success of therapy. With the development of new wearable sensors, it is possible to recognise human activities. Accordingly, wearables can also be used to identify recurring activities that indicate an OCD. Through this form of an automatic detection system, a diagnosis can be made earlier and thus therapy can be started sooner. Since compulsive behaviour is very individual and varies from patient to patient, this paper deals with personalised federated machine learning models. We first adapt the publicly available OPPORTUNITY dataset to simulate OCD behaviour. Secondly, we evaluate two existing personalised federated learning algorithms against baseline approaches. Finally, we propose a hybrid approach that merges the two evaluated algorithms and reaches a mean area under the precision-recall curve (AUPRC) of 0.954 across clients.}, author = {Kirsten, Kristina and Pfitzner, Bjarne and Löper, Lando and Arnrich, Bert}, booktitle = {2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)}, keywords = {bertarnrich bjarnepfitzner kristinakirsten}, pages = {333-339}, title = {Sensor-Based Obsessive-Compulsive Disorder Detection With Personalised Federated Learning}, year = 2021 }
UZH OnPoint at Swisstext-2021: Sentence End and Punctuation Prediction in NLG Text Through Ensembling of Different Transformers. Michail, Adrianos; Wehrli, Silvan; Bucková, Terézia (2021).
[ BibTeX ] [ URL ]
 
@inproceedings{michail2021uzh, author = {Michail, Adrianos and Wehrli, Silvan and Buckov{á}, Ter{é}zia}, booktitle = {Proceedings of the Swiss Text Analytics Conference 2021}, keywords = {silvanwehrli bertarnrich}, title = {UZH OnPoint at Swisstext-2021: Sentence End and Punctuation Prediction in NLG Text Through Ensembling of Different Transformers}, year = 2021 }
Analysing an allelic series of rare missense variants of CACNA1I in a Swedish schizophrenia cohort. Baez-Nieto, David; Allen, Andrew; Akers-Campbell, Seth; Yang, Lingling; Budnik, Nikita; Pupo, Amaury; Shin, Young-Cheul; Genovese, Giulio; Liao, Maofu; Pérez-Palma, Eduardo; others in Brain (2021).
[ BibTeX ]
 
@article{baez2021analysing, author = {Baez-Nieto, David and Allen, Andrew and Akers-Campbell, Seth and Yang, Lingling and Budnik, Nikita and Pupo, Amaury and Shin, Young-Cheul and Genovese, Giulio and Liao, Maofu and P{é}rez-Palma, Eduardo and others}, journal = {Brain}, keywords = {myown}, title = {Analysing an allelic series of rare missense variants of CACNA1I in a Swedish schizophrenia cohort}, year = 2021 }
Devicely: A Python package for reading, timeshifting and writing sensor data. Sasso, Ariane; Morgenstern, Jost; Musmann, Felix; Arnrich, Bert in Journal of Open Source Software (2021). 6(66) 3679.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Sasso2021, author = {Sasso, Ariane and Morgenstern, Jost and Musmann, Felix and Arnrich, Bert}, journal = {Journal of Open Source Software}, keywords = {myown bertarnrich fb-boettinger}, month = {oct}, number = 66, pages = 3679, title = {Devicely: A Python package for reading, timeshifting and writing sensor data}, volume = 6, year = 2021 }
Controversial Trials First: Identifying Disagreement Between Clinical Guidelines and New Evidence. Borchert, Florian; Meister, Laura; Langer, Thomas; Follmann, Markus; Arnrich, Bert; Schapranow, Matthieu-P. (2021). (Vol. 2021) 237–246.
[ BibTeX ] [ URL ]
 
@inproceedings{borchert_amia2021, author = {Borchert, Florian and Meister, Laura and Langer, Thomas and Follmann, Markus and Arnrich, Bert and Schapranow, Matthieu-P.}, booktitle = {AMIA Annual Symposium Proceedings}, keywords = {nlp myown highmed fb-boettinger}, organization = {American Medical Informatics Association}, pages = {237-246}, title = {Controversial Trials First: Identifying Disagreement Between Clinical Guidelines and New Evidence}, volume = 2021, year = 2021 }
Standardizing Clinical Predictive Modeling – Standardizing Development, Validation, and Interpretation of Clinical Prediction Models Freitas da Cruz, Harry in Doctoral Dissertation (2021). University of Potsdam.
[ BibTeX ] [ DOI ]
 
@book{freitasdacruz2021standardizing, author = {Freitas da Cruz, Harry}, keywords = {myown}, publisher = {University of Potsdam}, series = {Doctoral Dissertation}, title = {Standardizing Clinical Predictive Modeling – Standardizing Development, Validation, and Interpretation of Clinical Prediction Models}, year = 2021 }
Role of Individual Motivations and Privacy Concerns in the Adoption of German Electronic Patient Record Apps—A Mixed-Methods Study. Henkenjohann, Richard in International Journal of Environmental Research and Public Health (2021). 18(18) 31.
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
Germany’s electronic patient record (“ePA”) launched in 2021 with several attempts and years of delay. The development of such a large-scale project is a complex task, and so is its adoption. Individual attitudes towards an electronic health record are crucial, as individuals can reject opting-in to it and making any national efforts unachievable. Although the integration of an electronic health record serves potential benefits, it also constitutes risks for an individual’s privacy. With a mixed-methods study design, this work provides evidence that different types of motivations and contextual privacy antecedents affect usage intentions towards the ePA. Most significantly, individual motivations stemming from feelings of volition or external mandates positively affect ePA adoption, although internal incentives are more powerful.
@article{ijerph18189553, abstract = {Germany’s electronic patient record (“ePA”) launched in 2021 with several attempts and years of delay. The development of such a large-scale project is a complex task, and so is its adoption. Individual attitudes towards an electronic health record are crucial, as individuals can reject opting-in to it and making any national efforts unachievable. Although the integration of an electronic health record serves potential benefits, it also constitutes risks for an individual’s privacy. With a mixed-methods study design, this work provides evidence that different types of motivations and contextual privacy antecedents affect usage intentions towards the ePA. Most significantly, individual motivations stemming from feelings of volition or external mandates positively affect ePA adoption, although internal incentives are more powerful.}, author = {Henkenjohann, Richard}, journal = {International Journal of Environmental Research and Public Health}, keywords = {myown fb-boettinger}, number = 18, pages = 31, title = {Role of Individual Motivations and Privacy Concerns in the Adoption of German Electronic Patient Record Apps—A Mixed-Methods Study}, volume = 18, year = 2021 }
Mobile app requirements for patients with rare liver diseases: A single center survey for the ERN RARE-LIVER‬‬‬. Ruther, Darius F.; Sebode, Marcial; Lohse, Ansgar W.; Wernicke, Sarah; Bottinger, Erwin; Casar, Christian; Braun, Felix; Schramm, Christoph in Clinics and Research in Hepatology and Gastroenterology (2021). 45(6) 101760.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Rther2021, author = {Ruther, Darius F. and Sebode, Marcial and Lohse, Ansgar W. and Wernicke, Sarah and Bottinger, Erwin and Casar, Christian and Braun, Felix and Schramm, Christoph}, journal = {Clinics and Research in Hepatology and Gastroenterology}, keywords = {boettinger fb-boettinger}, month = {nov}, number = 6, pages = 101760, publisher = {Elsevier {BV}}, title = {Mobile app requirements for patients with rare liver diseases: A single center survey for the {ERN} {RARE}-{LIVER}‬‬‬}, volume = 45, year = 2021 }
Schneller Impfen dank Digitalisierung?. Schapranow, Matthieu-P. in Tagesspiegel Background (2021).
[ BibTeX ] [ URL ]
 
@article{schapranow2021schneller, author = {Schapranow, Matthieu-P.}, journal = {Tagesspiegel Background}, keywords = {myown}, month = {apr}, title = {Schneller Impfen dank Digitalisierung?}, year = 2021 }
StudyMe: A New Mobile App for User-Centric N-of-1 Trials. Zenner, Alexander M.; Bottinger, Erwin; Konigorski, Stefan (2021).
[ BibTeX ]
 
@misc{zenner2021studyme, author = {Zenner, Alexander M. and Bottinger, Erwin and Konigorski, Stefan}, keywords = {boettinger fb-boettinger}, title = {StudyMe: A New Mobile App for User-Centric N-of-1 Trials}, year = 2021 }
Predictive Approaches for Acute Dialysis Requirement and Death in COVID-19. Vaid, Akhil; Chan, Lili; Chaudhary, Kumardeep; Jaladanki, Suraj K.; Paranjpe, Ishan; Russak, Adam; Kia, Arash; Timsina, Prem; Levin, Matthew A.; He, John Cijiang; Boettinger, Erwin P.; Charney, Alexander W.; Fayad, Zahi A.; Coca, Steven G.; Glicksberg, Benjamin S.; Nadkarni, Girish N. in Clinical Journal of the American Society of Nephrology (2021). 16(8) 1158–1168.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Vaid2021, author = {Vaid, Akhil and Chan, Lili and Chaudhary, Kumardeep and Jaladanki, Suraj K. and Paranjpe, Ishan and Russak, Adam and Kia, Arash and Timsina, Prem and Levin, Matthew A. and He, John Cijiang and Boettinger, Erwin P. and Charney, Alexander W. and Fayad, Zahi A. and Coca, Steven G. and Glicksberg, Benjamin S. and Nadkarni, Girish N.}, journal = {Clinical Journal of the American Society of Nephrology}, keywords = {boettinger hpims fb-boettinger}, month = {may}, number = 8, pages = {1158–1168}, publisher = {American Society of Nephrology ({ASN})}, title = {Predictive Approaches for Acute Dialysis Requirement and Death in {COVID}-19}, volume = 16, year = 2021 }
Data Augmentation of Kinematic Time-Series From Rehabilitation Exercises Using GANs. Albert, Justin; Glöckner, Pawel; Pfitzner, Bjarne; Arnrich, Bert (2021). 1–6.
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
Machine learning, especially deep learning, offers great potential for medical applications. However, deep learning algorithms need a vast amount of training data. Especially in the medical domain, it is challenging to collect larger datasets. Access to patients can be limited, and data recording is mainly bound to laboratory settings requiring expertise from medical professionals. When involving a healthy control group, datasets are often unbalanced, with most data belonging to the control group. This paper proposes a data augmentation method to generate pose data of repetitive rehabilitation exercises trained on a specific population, e.g., a specific neurological disease. Our method is based on a generative adversarial network (GAN) that uses convolutional and long short-term memory (LSTM) layers. We evaluated our method using a dataset that contains rehabilitation exercises from stroke and Parkinson’s disease patients and a healthy control group. We demonstrated that a classifier trained using our augmentation method could distinguish between healthy, stroke, and Parkinson’s disease patients with an accuracy of 81%. In contrast, the same classifier achieved only 75% when using a standard resampling technique.
@inproceedings{9524284, abstract = {Machine learning, especially deep learning, offers great potential for medical applications. However, deep learning algorithms need a vast amount of training data. Especially in the medical domain, it is challenging to collect larger datasets. Access to patients can be limited, and data recording is mainly bound to laboratory settings requiring expertise from medical professionals. When involving a healthy control group, datasets are often unbalanced, with most data belonging to the control group. This paper proposes a data augmentation method to generate pose data of repetitive rehabilitation exercises trained on a specific population, e.g., a specific neurological disease. Our method is based on a generative adversarial network (GAN) that uses convolutional and long short-term memory (LSTM) layers. We evaluated our method using a dataset that contains rehabilitation exercises from stroke and Parkinson’s disease patients and a healthy control group. We demonstrated that a classifier trained using our augmentation method could distinguish between healthy, stroke, and Parkinson’s disease patients with an accuracy of 81%. In contrast, the same classifier achieved only 75% when using a standard resampling technique.}, author = {Albert, Justin and Glöckner, Pawel and Pfitzner, Bjarne and Arnrich, Bert}, booktitle = {2021 IEEE International Conference on Omni-Layer Intelligent Systems (COINS)}, keywords = {justinalbert bertarnrich bjarnepfitzner}, pages = {1-6}, title = {Data Augmentation of Kinematic Time-Series From Rehabilitation Exercises Using GANs}, year = 2021 }
Choosing the Appropriate QRS Detector. Eilers, Justus; Chromik, Jonas; Arnrich, Bert (2021). (Vol. 14)
[ Abstract ] [ BibTeX ] [ URL ]
 
QRS detectors are used as the most basic processing tool for ECG signals. Thus, there are many situations and signals with a wide range of characteristics in which they shall show great performance. Despite the expected versatility, most of the published QRS detectors are not tested on a diverse dataset. Using 14 databases, 10,000 heartbeats for each different heartbeat type were extracted to show that there are notable performance differences for the tested eight algorithms. Besides the analysis on heartbeat types, this paper also tests the noise resilience regarding different noise combinations. Each of the tested QRS detectors showed significant differences depending on heartbeat type and noise combination. This leads to the conclusion that before choosing a QRS detector, one should consider its use case and test the detector on data representing it. For authors of QRS detectors, this means that every algorithm evaluation should employ a dataset that is as diverse as the one used in this paper to assess the QRS detector’s performance in an objective and unbiased manner.
@inproceedings{eilers2020choosing, abstract = {QRS detectors are used as the most basic processing tool for ECG signals. Thus, there are many situations and signals with a wide range of characteristics in which they shall show great performance. Despite the expected versatility, most of the published QRS detectors are not tested on a diverse dataset. Using 14 databases, 10,000 heartbeats for each different heartbeat type were extracted to show that there are notable performance differences for the tested eight algorithms. Besides the analysis on heartbeat types, this paper also tests the noise resilience regarding different noise combinations. Each of the tested QRS detectors showed significant differences depending on heartbeat type and noise combination. This leads to the conclusion that before choosing a QRS detector, one should consider its use case and test the detector on data representing it. For authors of QRS detectors, this means that every algorithm evaluation should employ a dataset that is as diverse as the one used in this paper to assess the QRS detector’s performance in an objective and unbiased manner.}, author = {Eilers, Justus and Chromik, Jonas and Arnrich, Bert}, booktitle = {Proceedings of the International Conference on Bioinspired Systems and Signal Processing (BIOSIGNALS 2021)}, journal = {14th International Conference on Bio-inspired Systems and Signal Processing}, keywords = {bertarnrich jonaschromik}, organization = {INSTICC}, publisher = {SciTePress}, title = {Choosing the Appropriate QRS Detector}, volume = 14, year = 2021 }
Speaking Corona? Human and Machine Recognition of COVID-19 from Voice. Hecker, Pascal; Pokorny, Florian B.; Bartl-Pokorny, Katrin D.; Reichel, Uwe; Ren, Zhao; Hantke, Simone; Eyben, Florian; Schuller, Dagmar M.; Arnrich, Bert; Schuller, Björn W. (2021). 1029–1033.
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
With the COVID-19 pandemic, several research teams have reported successful advances in automated recognition of COVID-19 by voice. Resulting voice-based screening tools for COVID-19 could support large-scale testing efforts. While capabilities of machines on this task are progressing, we approach the so far unexplored aspect whether human raters can distinguish COVID-19 positive and negative tested speakers from voice samples, and compare their performance to a machine learning baseline. To account for the challenging symptom similarity between COVID-19 and other respiratory diseases, we use a carefully balanced dataset of voice samples, in which COVID-19 positive and negative tested speakers are matched by their symptoms alongside COVID-19 negative speakers without symptoms. Both human raters and the machine struggle to reliably identify COVID-19 positive speakers in our dataset. These results indicate that particular attention should be paid to the distribution of symptoms across all speakers of a dataset when assessing the capabilities of existing systems. The identification of acoustic aspects of COVID-19-related symptom manifestations might be the key for a reliable voice-based COVID-19 detection in the future by both trained human raters and machine learning models.
@inproceedings{hecker21_interspeech, abstract = {With the COVID-19 pandemic, several research teams have reported successful advances in automated recognition of COVID-19 by voice. Resulting voice-based screening tools for COVID-19 could support large-scale testing efforts. While capabilities of machines on this task are progressing, we approach the so far unexplored aspect whether human raters can distinguish COVID-19 positive and negative tested speakers from voice samples, and compare their performance to a machine learning baseline. To account for the challenging symptom similarity between COVID-19 and other respiratory diseases, we use a carefully balanced dataset of voice samples, in which COVID-19 positive and negative tested speakers are matched by their symptoms alongside COVID-19 negative speakers without symptoms. Both human raters and the machine struggle to reliably identify COVID-19 positive speakers in our dataset. These results indicate that particular attention should be paid to the distribution of symptoms across all speakers of a dataset when assessing the capabilities of existing systems. The identification of acoustic aspects of COVID-19-related symptom manifestations might be the key for a reliable voice-based COVID-19 detection in the future by both trained human raters and machine learning models.}, author = {Hecker, Pascal and Pokorny, Florian B. and Bartl-Pokorny, Katrin D. and Reichel, Uwe and Ren, Zhao and Hantke, Simone and Eyben, Florian and Schuller, Dagmar M. and Arnrich, Bert and Schuller, Björn W.}, booktitle = {Proc. Interspeech 2021}, keywords = {pascalhecker bertarnrich}, pages = {1029–1033}, title = {{Speaking Corona? Human and Machine Recognition of COVID-19 from Voice}}, year = 2021 }
FIBER: enabling flexible retrieval of electronic health records data for clinical predictive modeling. Datta, Suparno; Sachs, Jan Philipp; Cruz, Harry Freitas; Martensen, Tom; Bode, Philipp; Sasso, Ariane Morassi; Glicksberg, Benjamin S; Bottinger, Erwin in JAMIA Open (2021). 4(3)
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Datta2021, author = {Datta, Suparno and Sachs, Jan Philipp and Cruz, Harry Freitas and Martensen, Tom and Bode, Philipp and Sasso, Ariane Morassi and Glicksberg, Benjamin S and Bottinger, Erwin}, journal = {{JAMIA} Open}, keywords = {boettinger hpims fb-boettinger}, month = {jul}, number = 3, publisher = {Oxford University Press ({OUP})}, title = {{FIBER}: enabling flexible retrieval of electronic health records data for clinical predictive modeling}, volume = 4, year = 2021 }
TRIPOD—A Treadmill Walking Dataset with IMU, Pressure-Distribution and Photoelectric Data for Gait Analysis. Trautmann, Justin; Zhou, Lin; Brahms, Clemens Markus; Tunca, Can; Ersoy, Cem; Granacher, Urs; Arnrich, Bert in Data (2021). 6(9) 95.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{trautmann2021tripod, author = {Trautmann, Justin and Zhou, Lin and Brahms, Clemens Markus and Tunca, Can and Ersoy, Cem and Granacher, Urs and Arnrich, Bert}, journal = {Data}, keywords = {linzhou bertarnrich}, number = 9, pages = 95, publisher = {Multidisciplinary Digital Publishing Institute}, title = {TRIPOD—A Treadmill Walking Dataset with IMU, Pressure-Distribution and Photoelectric Data for Gait Analysis}, volume = 6, year = 2021 }
Acute Kidney Injury in Patients Hospitalized With COVID-19 in New York City: Temporal Trends From March 2020 to April 2021. Dellepiane, Sergio; Vaid, Akhil; Jaladanki, Suraj K.; Coca, Steven; Fayad, Zahi A.; Charney, Alexander W.; Bottinger, Erwin P.; He, John Cijiang; Glicksberg, Benjamin S.; Chan, Lili; Nadkarni, Girish in Kidney Medicine (2021).
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Dellepiane2021, author = {Dellepiane, Sergio and Vaid, Akhil and Jaladanki, Suraj K. and Coca, Steven and Fayad, Zahi A. and Charney, Alexander W. and Bottinger, Erwin P. and He, John Cijiang and Glicksberg, Benjamin S. and Chan, Lili and Nadkarni, Girish}, journal = {Kidney Medicine}, keywords = {boettinger hpims fb-boettinger}, month = {jul}, publisher = {Elsevier {BV}}, title = {Acute Kidney Injury in Patients Hospitalized With {COVID}-19 in New York City: Temporal Trends From March 2020 to April 2021}, year = 2021 }
Unsupervised Learning to Subphenotype Heart Failure Patients from Electronic Health Records. Hackl, Melanie; Datta, Suparno; Miotto, Riccardo; Bottinger, Erwin in Artificial Intelligence in Medicine (2021). 219–228.
[ BibTeX ] [ URL ] [ DOI ]
 
@incollection{Hackl2021, author = {Hackl, Melanie and Datta, Suparno and Miotto, Riccardo and Bottinger, Erwin}, booktitle = {Artificial Intelligence in Medicine}, keywords = {boettinger hpims fb-boettinger}, pages = {219–228}, publisher = {Springer International Publishing}, title = {Unsupervised Learning to Subphenotype Heart Failure Patients from Electronic Health Records}, year = 2021 }
Mobile app requirements for patients with rare liver diseases: A single center survey for the ERN RARE-LIVER‬‬‬. Ruther, Darius F.; Sebode, Marcial; Lohse, Ansgar W.; Wernicke, Sarah; Boetinger, Erwin; Casar, Christian; Braun, Felix; Schramm, Christoph in Clinics and Research in Hepatology and Gastroenterology (2021). 45(6) 101760.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Rther2021, author = {Ruther, Darius F. and Sebode, Marcial and Lohse, Ansgar W. and Wernicke, Sarah and Boetinger, Erwin and Casar, Christian and Braun, Felix and Schramm, Christoph}, journal = {Clinics and Research in Hepatology and Gastroenterology}, keywords = {boettinger fb-boettinger}, month = {nov}, number = 6, pages = 101760, publisher = {Elsevier {BV}}, title = {Mobile app requirements for patients with rare liver diseases: A single center survey for the {ERN} {RARE}-{LIVER}‬‬‬}, volume = 45, year = 2021 }
GAIA-X: A Pitch Towards Europe Affairs, Federal Ministry of Economic; Energy (BMWi); others (2021).
[ BibTeX ]
 
@techreport{foreconomicaffairs2021gaiax, author = {{Federal Ministry of Economic Affairs and Energy (BMWi)} and others}, keywords = {myown}, title = {GAIA-X: A Pitch Towards Europe}, year = 2021 }
Optimal Sensor Placement for Human Activity Recognition with a Minimal Smartphone–IMU Setup. Rahn, Vincent Xeno; Zhou, Lin; Klieme, Eric; Arnrich, Bert (2021). (Vol. 10) 37–48.
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
Human Activity Recognition (HAR) of everyday activities using smartphones has been intensively researched over the past years. Despite the high detection performance, smartphones can not continuously provide reli- able information about the currently conducted activity as their placement at the subject’s body is uncertain. In this study, a system is developed that enables real-time collection of data from various Bluetooth inertial mea- surement units (IMUs) in addition to the smartphone. The contribution of this work is an extensive overview of related work in this field and the identification of unobtrusive, minimal combinations of IMUs with the smartphone that achieve high recognition performance. Eighteen young subjects with unrestricted mobility were recorded conducting seven daily-life activities with a smartphone in the pocket and five IMUs at different body positions. With a Convolutional Neural Network (CNN) for activity recognition, activity classification accuracy increased by up to 23% with one IMU additional to the smartphone. An overall prediction rate of 97% was reached with a smartphone in the pocket and an IMU at the ankle. This study demonstrated the potential that an additional IMU can improve the accuracy of smartphone-based HAR on daily-life activities.
@inproceedings{rahn2021optimal, abstract = {Human Activity Recognition (HAR) of everyday activities using smartphones has been intensively researched over the past years. Despite the high detection performance, smartphones can not continuously provide reli- able information about the currently conducted activity as their placement at the subject’s body is uncertain. In this study, a system is developed that enables real-time collection of data from various Bluetooth inertial mea- surement units (IMUs) in addition to the smartphone. The contribution of this work is an extensive overview of related work in this field and the identification of unobtrusive, minimal combinations of IMUs with the smartphone that achieve high recognition performance. Eighteen young subjects with unrestricted mobility were recorded conducting seven daily-life activities with a smartphone in the pocket and five IMUs at different body positions. With a Convolutional Neural Network (CNN) for activity recognition, activity classification accuracy increased by up to 23% with one IMU additional to the smartphone. An overall prediction rate of 97% was reached with a smartphone in the pocket and an IMU at the ankle. This study demonstrated the potential that an additional IMU can improve the accuracy of smartphone-based HAR on daily-life activities.}, author = {Rahn, Vincent Xeno and Zhou, Lin and Klieme, Eric and Arnrich, Bert}, booktitle = {Proceedings of the 10th International Conference on Sensor Networks - Volume 1: SENSORNETS,}, keywords = {linzhou bertarnrich}, month = {February}, organization = {INSTICC}, pages = {37-48}, publisher = {SciTePress}, title = {Optimal Sensor Placement for Human Activity Recognition with a Minimal Smartphone–IMU Setup}, volume = 10, year = 2021 }
Causal inference in developmental medicine and neurology. Konigorski, Stefan in Developmental Medicine & Child Neurology (2021).
[ BibTeX ] [ URL ]
 
@article{noauthororeditor, author = {Konigorski, Stefan}, journal = {Developmental Medicine & Child Neurology}, keywords = {myown}, title = {Causal inference in developmental medicine and neurology.}, year = 2021 }
Monitoring of Sitting Postures With Sensor Networks in Controlled and Free-living Environments: Systematic Review. Kappattanavar, Arpita Mallikarjuna; Steckhan, Nico; Sachs, Jan Philipp; Freitas da Cruz, Harry; Boettinger, Erwin; Arnrich, Bert in JMIR Biomed Eng (2021). 6(1) e21105.
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
Background: A majority of employees in the industrial world spend most of their working time in a seated position. Monitoring sitting postures can provide insights into the underlying causes of occupational discomforts such as low back pain. Objective: This study focuses on the technologies and algorithms used to classify sitting postures on a chair with respect to spine and limb movements, using sensors and wearables such as inertial measurement units, pressure or piezoresistive sensors, accelerometers or gyroscopes, combined with machine learning approaches. Methods: A total of three electronic literature databases were surveyed to identify studies classifying sitting postures in adults. Quality appraisal was performed to extract critical details and assess biases in the shortlisted papers. Results: A total of 14 papers were shortlisted from 952 papers obtained after a systematic search. The majority of the studies used pressure sensors to measure sitting postures, whereas neural networks were the most frequently used approaches for classification tasks in this context. Only 2 studies were performed in a free-living environment. Most studies presented ethical and methodological shortcomings. Moreover, the findings indicate that the strategic placement of sensors can lead to better performance and lower costs. Conclusions: The included studies differed in various aspects of design and analysis. The majority of studies were rated as medium quality according to our assessment. Our study suggests that future work for posture classification can benefit from using inertial measurement unit sensors, since they make it possible to differentiate among spine movements and similar postures, considering transitional movements between postures, and using three-dimensional cameras to annotate the data for ground truth. Finally, comparing such studies is challenging, as there are no standard definitions of sitting postures that could be used for classification. In addition, this study identifies five basic sitting postures along with different combinations of limb and spine movements to help guide future research efforts.
@article{info:doi/10.2196/21105, abstract = {Background: A majority of employees in the industrial world spend most of their working time in a seated position. Monitoring sitting postures can provide insights into the underlying causes of occupational discomforts such as low back pain. Objective: This study focuses on the technologies and algorithms used to classify sitting postures on a chair with respect to spine and limb movements, using sensors and wearables such as inertial measurement units, pressure or piezoresistive sensors, accelerometers or gyroscopes, combined with machine learning approaches. Methods: A total of three electronic literature databases were surveyed to identify studies classifying sitting postures in adults. Quality appraisal was performed to extract critical details and assess biases in the shortlisted papers. Results: A total of 14 papers were shortlisted from 952 papers obtained after a systematic search. The majority of the studies used pressure sensors to measure sitting postures, whereas neural networks were the most frequently used approaches for classification tasks in this context. Only 2 studies were performed in a free-living environment. Most studies presented ethical and methodological shortcomings. Moreover, the findings indicate that the strategic placement of sensors can lead to better performance and lower costs. Conclusions: The included studies differed in various aspects of design and analysis. The majority of studies were rated as medium quality according to our assessment. Our study suggests that future work for posture classification can benefit from using inertial measurement unit sensors, since they make it possible to differentiate among spine movements and similar postures, considering transitional movements between postures, and using three-dimensional cameras to annotate the data for ground truth. Finally, comparing such studies is challenging, as there are no standard definitions of sitting postures that could be used for classification. In addition, this study identifies five basic sitting postures along with different combinations of limb and spine movements to help guide future research efforts.}, author = {Kappattanavar, Arpita Mallikarjuna and Steckhan, Nico and Sachs, Jan Philipp and Freitas da Cruz, Harry and Boettinger, Erwin and Arnrich, Bert}, journal = {JMIR Biomed Eng}, keywords = {bertarnrich arpitakappattanavar}, month = {mar}, number = 1, pages = {e21105}, title = {Monitoring of Sitting Postures With Sensor Networks in Controlled and Free-living Environments: Systematic Review}, volume = 6, year = 2021 }
Certainty in QRS detection with artificial neural networks. Chromik, Jonas; Pirl, Lukas; Beilharz, Jossekin; Arnrich, Bert; Polze, Andreas in Biomedical Signal Processing and Control (2021). 68 102628.
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
Detection of the QRS complex is a long-standing topic in the context of electrocardiography and many algorithms build upon the knowledge of the QRS positions. Although the first solutions to this problem were proposed in the 1970s and 1980s, there is still potential for improvements. Advancements in neural network technology made in recent years also lead to the emergence of enhanced QRS detectors based on artificial neural networks. In this work, we propose a method for assessing the certainty that is in each of the detected QRS complexes, i.e. how confident the QRS detector is that there is, in fact, a QRS complex in the position where it was detected. We further show how this metric can be utilised to distinguish correctly detected QRS complexes from false detections.
@article{CHROMIK2021102628, abstract = {Detection of the QRS complex is a long-standing topic in the context of electrocardiography and many algorithms build upon the knowledge of the QRS positions. Although the first solutions to this problem were proposed in the 1970s and 1980s, there is still potential for improvements. Advancements in neural network technology made in recent years also lead to the emergence of enhanced QRS detectors based on artificial neural networks. In this work, we propose a method for assessing the certainty that is in each of the detected QRS complexes, i.e. how confident the QRS detector is that there is, in fact, a QRS complex in the position where it was detected. We further show how this metric can be utilised to distinguish correctly detected QRS complexes from false detections.}, author = {Chromik, Jonas and Pirl, Lukas and Beilharz, Jossekin and Arnrich, Bert and Polze, Andreas}, journal = {Biomedical Signal Processing and Control}, keywords = {bertarnrich jonaschromik}, pages = 102628, title = {Certainty in QRS detection with artificial neural networks}, volume = 68, year = 2021 }
Biomedical and Clinical Research Data Management. Ganzinger, Matthias; Glaab, Enrico; Kerssemakers, Jules; Nahnsen, Sven; Sax, Ulrich; Schaadt, Nadine Sarah; Schapranow, Matthieu-P.; Tiede, Thorsten in Systems Medicine, O. Wolkenhauer (ed.) (2021). 532–543.
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
Systems medicine is an interdisciplinary approach in medicine that relies on computational models based on data from a variety of sources. Typically, such sources include clinical and biomedical data with heterogeneous data definitions that are sometimes not even structured in a useful way. Consequently, the systematic management of data is an important element for the successful implementation of systems medicine in both research and clinical application. In this article, we provide an overview over the following selected aspects of data management:•Integration of multiple data sources•IT infrastructures•Data protection regulations•Data history and data quality•Data sharing/FAIR principles•Use and access policies The presented best practices and experiences result from several systems medicine projects in which the authors have participated. They can be considered as recommendations for future projects in order to quickly set up data management infrastructures for systems medicine.
@incollection{GANZINGER2021532, abstract = {Systems medicine is an interdisciplinary approach in medicine that relies on computational models based on data from a variety of sources. Typically, such sources include clinical and biomedical data with heterogeneous data definitions that are sometimes not even structured in a useful way. Consequently, the systematic management of data is an important element for the successful implementation of systems medicine in both research and clinical application. In this article, we provide an overview over the following selected aspects of data management:•Integration of multiple data sources•IT infrastructures•Data protection regulations•Data history and data quality•Data sharing/FAIR principles•Use and access policies The presented best practices and experiences result from several systems medicine projects in which the authors have participated. They can be considered as recommendations for future projects in order to quickly set up data management infrastructures for systems medicine.}, address = {Oxford}, author = {Ganzinger, Matthias and Glaab, Enrico and Kerssemakers, Jules and Nahnsen, Sven and Sax, Ulrich and Schaadt, Nadine Sarah and Schapranow, Matthieu-P. and Tiede, Thorsten}, booktitle = {Systems Medicine}, editor = {Wolkenhauer, Olaf}, keywords = {myown}, pages = {532 - 543}, publisher = {Academic Press}, title = {Biomedical and Clinical Research Data Management}, year = 2021 }
Association of SARS-CoV-2 viral load at admission with in-hospital acute kidney injury: A retrospective cohort study. Paranjpe, Ishan; Chaudhary, Kumardeep; Johnson, Kipp W.; Jaladanki, Suraj K.; Zhao, Shan; Freitas, Jessica K. De; Pujdas, Elisabet; Chaudhry, Fayzan; Bottinger, Erwin P.; Levin, Matthew A.; Fayad, Zahi A.; Charney, Alexander W.; Houldsworth, Jane; Cordon-Cardo, Carlos; Glicksberg, Benjamin S.; Nadkarni, Girish N. in PLOS ONE, (A. L. Conroy, ed.) (2021). 16(2) e0247366.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Paranjpe2021, author = {Paranjpe, Ishan and Chaudhary, Kumardeep and Johnson, Kipp W. and Jaladanki, Suraj K. and Zhao, Shan and Freitas, Jessica K. De and Pujdas, Elisabet and Chaudhry, Fayzan and Bottinger, Erwin P. and Levin, Matthew A. and Fayad, Zahi A. and Charney, Alexander W. and Houldsworth, Jane and Cordon-Cardo, Carlos and Glicksberg, Benjamin S. and Nadkarni, Girish N.}, editor = {Conroy, Andrea L.}, journal = {{PLOS} {ONE}}, keywords = {boettinger hpims fb-boettinger}, month = {feb}, number = 2, pages = {e0247366}, publisher = {Public Library of Science ({PLoS})}, title = {Association of {SARS}-{CoV}-2 viral load at admission with in-hospital acute kidney injury: A retrospective cohort study}, volume = 16, year = 2021 }
Federated Learning of Electronic Health Records to Improve Mortality Prediction in Hospitalized Patients With COVID-19: Machine Learning Approach. Vaid, Akhil; Jaladanki, Suraj K; Xu, Jie; Teng, Shelly; Kumar, Arvind; Lee, Samuel; Somani, Sulaiman; Paranjpe, Ishan; Freitas, Jessica K De; Wanyan, Tingyi; Johnson, Kipp W; Bicak, Mesude; Klang, Eyal; Kwon, Young Joon; Costa, Anthony; Zhao, Shan; Miotto, Riccardo; Charney, Alexander W; Böttinger, Erwin; Fayad, Zahi A; Nadkarni, Girish N; Wang, Fei; Glicksberg, Benjamin S in JMIR Medical Informatics (2021). 9(1) e24207.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Vaid2021, author = {Vaid, Akhil and Jaladanki, Suraj K and Xu, Jie and Teng, Shelly and Kumar, Arvind and Lee, Samuel and Somani, Sulaiman and Paranjpe, Ishan and Freitas, Jessica K De and Wanyan, Tingyi and Johnson, Kipp W and Bicak, Mesude and Klang, Eyal and Kwon, Young Joon and Costa, Anthony and Zhao, Shan and Miotto, Riccardo and Charney, Alexander W and Böttinger, Erwin and Fayad, Zahi A and Nadkarni, Girish N and Wang, Fei and Glicksberg, Benjamin S}, journal = {{JMIR} Medical Informatics}, keywords = {boettinger hpims fb-boettinger}, month = {jan}, number = 1, pages = {e24207}, publisher = {{JMIR} Publications Inc.}, title = {Federated Learning of Electronic Health Records to Improve Mortality Prediction in Hospitalized Patients With {COVID}-19: Machine Learning Approach}, volume = 9, year = 2021 }
Differentially Private Federated Learning for Anomaly Detection in EHealth Networks. Cholakoska, Ana; Pfitzner, Bjarne; Gjoreski, Hristijan; Rakovic, Valentin; Arnrich, Bert; Kalendar, Marija in UbiComp ’21 (2021). 514–518.
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
Increasing number of ubiquitous devices are being used in the medical field to collect patient information. Those connected sensors can potentially be exploited by third parties who want to misuse personal information and compromise the security, which could ultimately result even in patient death. This paper addresses the security concerns in eHealth networks and suggests a new approach to dealing with anomalies. In particular we propose a concept for safe in-hospital learning from internet of health things (IoHT) device data while securing the network traffic with a collaboratively trained anomaly detection system using federated learning. That way, real time traffic anomaly detection is achieved, while maintaining collaboration between hospitals and keeping local data secure and private. Since not only the network metadata, but also the actual medical data is relevant to anomaly detection, we propose to use differential privacy (DP) for providing formal guarantees of the privacy spending accumulated during the federated learning.
@inproceedings{10.1145/3460418.3479365, abstract = {Increasing number of ubiquitous devices are being used in the medical field to collect patient information. Those connected sensors can potentially be exploited by third parties who want to misuse personal information and compromise the security, which could ultimately result even in patient death. This paper addresses the security concerns in eHealth networks and suggests a new approach to dealing with anomalies. In particular we propose a concept for safe in-hospital learning from internet of health things (IoHT) device data while securing the network traffic with a collaboratively trained anomaly detection system using federated learning. That way, real time traffic anomaly detection is achieved, while maintaining collaboration between hospitals and keeping local data secure and private. Since not only the network metadata, but also the actual medical data is relevant to anomaly detection, we propose to use differential privacy (DP) for providing formal guarantees of the privacy spending accumulated during the federated learning.}, address = {New York, NY, USA}, author = {Cholakoska, Ana and Pfitzner, Bjarne and Gjoreski, Hristijan and Rakovic, Valentin and Arnrich, Bert and Kalendar, Marija}, booktitle = {Adjunct Proceedings of the 2021 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2021 ACM International Symposium on Wearable Computers}, keywords = {bertarnrich bjarnepfitzner}, pages = {514–518}, publisher = {Association for Computing Machinery}, series = {UbiComp '21}, title = {Differentially Private Federated Learning for Anomaly Detection in EHealth Networks}, year = 2021 }
Temporal Trends in COVID-19 associated AKI from March to December 2020 in New York City. Dellepiane, Sergio; Vaid, Akhil; Jaladanki, Suraj K; Paranjpe, Ishan; Coca, Steven; Fayad, Zahi A; Charney, Alexander W; Bottinger, Erwin P; He, John Cijiang; Glicksberg, Benjamin S; Chan, Lili; Nadkarni, Girish (2021).
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Dellepiane2021, author = {Dellepiane, Sergio and Vaid, Akhil and Jaladanki, Suraj K and Paranjpe, Ishan and Coca, Steven and Fayad, Zahi A and Charney, Alexander W and Bottinger, Erwin P and He, John Cijiang and Glicksberg, Benjamin S and Chan, Lili and Nadkarni, Girish}, keywords = {boettinger hpims fb-boettinger}, month = {jan}, publisher = {Cold Spring Harbor Laboratory}, title = {Temporal Trends in {COVID}-19 associated {AKI} from March to December 2020 in New York City}, year = 2021 }
Knowledge bases and software support for variant interpretation in precision oncology. Borchert, Florian; Mock, Andreas; Tomczak, Aurelie; Hügel, Jonas; Alkarkoukly, Samer; Knurr, Alexander; Volckmar, Anna-Lena; Stenzinger, Albrecht; Schirmacher, Peter; Debus, Jürgen; Jäger, Dirk; Longerich, Thomas; Fröhling, Stefan; Eils, Roland; Bougatf, Nina; Sax, Ulrich; Schapranow, Matthieu-P in Briefings in Bioinformatics (2021). 22(6)
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
Precision oncology is a rapidly evolving interdisciplinary medical specialty. Comprehensive cancer panels are becoming increasingly available at pathology departments worldwide, creating the urgent need for scalable cancer variant annotation and molecularly informed treatment recommendations. A wealth of mainly academia-driven knowledge bases calls for software tools supporting the multi-step diagnostic process. We derive a comprehensive list of knowledge bases relevant for variant interpretation by a review of existing literature followed by a survey among medical experts from university hospitals in Germany. In addition, we review cancer variant interpretation tools, which integrate multiple knowledge bases. We categorize the knowledge bases along the diagnostic process in precision oncology and analyze programmatic access options as well as the integration of knowledge bases into software tools. The most commonly used knowledge bases provide good programmatic access options and have been integrated into a range of software tools. For the wider set of knowledge bases, access options vary across different parts of the diagnostic process. Programmatic access is limited for information regarding clinical classifications of variants and for therapy recommendations. The main issue for databases used for biological classification of pathogenic variants and pathway context information is the lack of standardized interfaces. There is no single cancer variant interpretation tool that integrates all identified knowledge bases. Specialized tools are available and need to be further developed for different steps in the diagnostic process.
@article{10.1093/bib/bbab134, abstract = {Precision oncology is a rapidly evolving interdisciplinary medical specialty. Comprehensive cancer panels are becoming increasingly available at pathology departments worldwide, creating the urgent need for scalable cancer variant annotation and molecularly informed treatment recommendations. A wealth of mainly academia-driven knowledge bases calls for software tools supporting the multi-step diagnostic process. We derive a comprehensive list of knowledge bases relevant for variant interpretation by a review of existing literature followed by a survey among medical experts from university hospitals in Germany. In addition, we review cancer variant interpretation tools, which integrate multiple knowledge bases. We categorize the knowledge bases along the diagnostic process in precision oncology and analyze programmatic access options as well as the integration of knowledge bases into software tools. The most commonly used knowledge bases provide good programmatic access options and have been integrated into a range of software tools. For the wider set of knowledge bases, access options vary across different parts of the diagnostic process. Programmatic access is limited for information regarding clinical classifications of variants and for therapy recommendations. The main issue for databases used for biological classification of pathogenic variants and pathway context information is the lack of standardized interfaces. There is no single cancer variant interpretation tool that integrates all identified knowledge bases. Specialized tools are available and need to be further developed for different steps in the diagnostic process.}, author = {Borchert, Florian and Mock, Andreas and Tomczak, Aurelie and Hügel, Jonas and Alkarkoukly, Samer and Knurr, Alexander and Volckmar, Anna-Lena and Stenzinger, Albrecht and Schirmacher, Peter and Debus, Jürgen and Jäger, Dirk and Longerich, Thomas and Fröhling, Stefan and Eils, Roland and Bougatf, Nina and Sax, Ulrich and Schapranow, Matthieu-P}, journal = {Briefings in Bioinformatics}, keywords = {HiGHmed myown fb-boettinger}, month = {05}, note = {bbab134}, number = 6, title = {Knowledge bases and software support for variant interpretation in precision oncology}, volume = 22, year = 2021 }
Factors Associated with Longitudinal Psychological and Physiological Stress in Health Care Workers During the COVID-19 Pandemic: Observational Study Using Apple Watch Data (Preprint). Hirten, Robert P; Danieletto, Matteo; Tomalin, Lewis; Choi, Katie Hyewon; Zweig, Micol; Golden, Eddye; Kaur, Sparshdeep; Helmus, Drew; Biello, Anthony; Pyzik, Renata; Calcogna, Claudia; Freeman, Robert; Sands, Bruce E; Charney, Dennis; Bottinger, Erwin P; Murrough, James W; Keefer, Laurie; Suarez-Farinas, Mayte; Nadkarni, Girish N; Fayad, Zahi A in Journal of Medical Internet Research (2021).
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Hirten2021, author = {Hirten, Robert P and Danieletto, Matteo and Tomalin, Lewis and Choi, Katie Hyewon and Zweig, Micol and Golden, Eddye and Kaur, Sparshdeep and Helmus, Drew and Biello, Anthony and Pyzik, Renata and Calcogna, Claudia and Freeman, Robert and Sands, Bruce E and Charney, Dennis and Bottinger, Erwin P and Murrough, James W and Keefer, Laurie and Suarez-Farinas, Mayte and Nadkarni, Girish N and Fayad, Zahi A}, journal = {Journal of Medical Internet Research}, keywords = {boettinger hpims fb-boettinger}, month = {jun}, publisher = {{JMIR} Publications Inc.}, title = {Factors Associated with Longitudinal Psychological and Physiological Stress in Health Care Workers During the {COVID}-19 Pandemic: Observational Study Using Apple Watch Data (Preprint)}, year = 2021 }
Kidney disease genetic risk variants alter lysosomal beta-mannosidase (MANBA) expression and disease severity. Gu, Xiangchen; Yang, Hongliu; Sheng, Xin; Ko, Yi-An; Qiu, Chengxiang; Park, Jihwan; Huang, Shizheng; Kember, Rachel; Judy, Renae L.; Park, Joseph; Damrauer, Scott M.; Nadkarni, Girish; Loos, Ruth J. F.; My, Vy Thi Ha; Chaudhary, Kumardeep; Bottinger, Erwin P.; Paranjpe, Ishan; Saha, Aparna; Brown, Christopher; Akilesh, Shreeram; Hung, Adriana M.; Palmer, Matthew; Baras, Aris; Overton, John D.; Reid, Jeffrey; Ritchie, Marylyn; Rader, Daniel J.; Susztak, Katalin in Science Translational Medicine (2021). 13(576) eaaz1458.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Gu2021, author = {Gu, Xiangchen and Yang, Hongliu and Sheng, Xin and Ko, Yi-An and Qiu, Chengxiang and Park, Jihwan and Huang, Shizheng and Kember, Rachel and Judy, Renae L. and Park, Joseph and Damrauer, Scott M. and Nadkarni, Girish and Loos, Ruth J. F. and My, Vy Thi Ha and Chaudhary, Kumardeep and Bottinger, Erwin P. and Paranjpe, Ishan and Saha, Aparna and Brown, Christopher and Akilesh, Shreeram and Hung, Adriana M. and Palmer, Matthew and Baras, Aris and Overton, John D. and Reid, Jeffrey and Ritchie, Marylyn and Rader, Daniel J. and Susztak, Katalin}, journal = {Science Translational Medicine}, keywords = {boettinger hpims fb-boettinger}, month = {jan}, number = 576, pages = {eaaz1458}, publisher = {American Association for the Advancement of Science ({AAAS})}, title = {Kidney disease genetic risk variants alter lysosomal beta-mannosidase ({MANBA}) expression and disease severity}, volume = 13, year = 2021 }
Monitoring of Sitting Postures With Sensor Networks in Controlled and Free-living Environments: Systematic Review. Kappattanavar, Arpita Mallikarjuna; Steckhan, Nico; Sachs, Jan Philipp; da Cruz, Harry Freitas; Bottinger, Erwin; Arnrich, Bert in JMIR Biomedical Engineering (2021). 6(1) e21105.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Kappattanavar2021, author = {Kappattanavar, Arpita Mallikarjuna and Steckhan, Nico and Sachs, Jan Philipp and da Cruz, Harry Freitas and Bottinger, Erwin and Arnrich, Bert}, journal = {{JMIR} Biomedical Engineering}, keywords = {boettinger fb-boettinger}, month = {mar}, number = 1, pages = {e21105}, publisher = {{JMIR} Publications Inc.}, title = {Monitoring of Sitting Postures With Sensor Networks in Controlled and Free-living Environments: Systematic Review}, volume = 6, year = 2021 }
Toward a fine-scale population health monitoring system. Belbin, Gillian M.; Cullina, Sinead; Wenric, Stephane; Soper, Emily R.; Glicksberg, Benjamin S.; Torre, Denis; Moscati, Arden; Wojcik, Genevieve L.; Shemirani, Ruhollah; Beckmann, Noam D.; Cohain, Ariella; Sorokin, Elena P.; Park, Danny S.; Ambite, Jose-Luis; Ellis, Steve; Auton, Adam; Bottinger, Erwin P.; Cho, Judy H.; Loos, Ruth J.F.; Abul-Husn, Noura S.; Zaitlen, Noah A.; Gignoux, Christopher R.; Kenny, Eimear E. in Cell (2021). 184(8) 2068–2083.e11.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Belbin2021, author = {Belbin, Gillian M. and Cullina, Sinead and Wenric, Stephane and Soper, Emily R. and Glicksberg, Benjamin S. and Torre, Denis and Moscati, Arden and Wojcik, Genevieve L. and Shemirani, Ruhollah and Beckmann, Noam D. and Cohain, Ariella and Sorokin, Elena P. and Park, Danny S. and Ambite, Jose-Luis and Ellis, Steve and Auton, Adam and Bottinger, Erwin P. and Cho, Judy H. and Loos, Ruth J.F. and Abul-Husn, Noura S. and Zaitlen, Noah A. and Gignoux, Christopher R. and Kenny, Eimear E.}, journal = {Cell}, keywords = {boettinger hpims fb-boettinger}, month = {apr}, number = 8, pages = {2068–2083.e11}, publisher = {Elsevier {BV}}, title = {Toward a fine-scale population health monitoring system}, volume = 184, year = 2021 }
A Resilience-Building App to Support the Mental Health of Health Care Workers in the COVID-19 Era: Design Process, Distribution, and Evaluation. Golden, Eddye A; Zweig, Micol; Danieletto, Matteo; Landell, Kyle; Nadkarni, Girish; Bottinger, Erwin; Katz, Lindsay; Somarriba, Ricardo; Sharma, Vansh; Katz, Craig L; Marin, Deborah B; DePierro, Jonathan; Charney, Dennis S in JMIR Formative Research (2021). 5(5) e26590.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Golden2021, author = {Golden, Eddye A and Zweig, Micol and Danieletto, Matteo and Landell, Kyle and Nadkarni, Girish and Bottinger, Erwin and Katz, Lindsay and Somarriba, Ricardo and Sharma, Vansh and Katz, Craig L and Marin, Deborah B and DePierro, Jonathan and Charney, Dennis S}, journal = {{JMIR} Formative Research}, keywords = {boettinger hpims fb-boettinger}, month = {may}, number = 5, pages = {e26590}, publisher = {{JMIR} Publications Inc.}, title = {A Resilience-Building App to Support the Mental Health of Health Care Workers in the {COVID}-19 Era: Design Process, Distribution, and Evaluation}, volume = 5, year = 2021 }
Predictive Approaches for Acute Dialysis Requirement and Death in COVID-19. Vaid, Akhil; Chan, Lili; Chaudhary, Kumardeep; Jaladanki, Suraj; Paranjpe, Ishan; Russak, Adam; Kia, Arash; Timsina, Prem; Levin, Matthew; He, John; Bottinger, Erwin; Charney, Alexander; Fayad, Zahi; Coca, Steven; Glicksberg, Benjamin; Nadkarni, Girish in Clinical Journal of the American Society of Nephrology (2021). CJN.17311120.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Vaid2021, author = {Vaid, Akhil and Chan, Lili and Chaudhary, Kumardeep and Jaladanki, Suraj and Paranjpe, Ishan and Russak, Adam and Kia, Arash and Timsina, Prem and Levin, Matthew and He, John and Bottinger, Erwin and Charney, Alexander and Fayad, Zahi and Coca, Steven and Glicksberg, Benjamin and Nadkarni, Girish}, journal = {Clinical Journal of the American Society of Nephrology}, keywords = {boettinger hpims fb-boettinger}, month = {may}, pages = {CJN.17311120}, publisher = {American Society of Nephrology ({ASN})}, title = {Predictive Approaches for Acute Dialysis Requirement and Death in {COVID}-19}, year = 2021 }
Use of Physiological Data From a Wearable Device to Identify SARS-CoV-2 Infection and Symptoms and Predict COVID-19 Diagnosis: Observational Study. Hirten, Robert P; Danieletto, Matteo; Tomalin, Lewis; Choi, Katie Hyewon; Zweig, Micol; Golden, Eddye; Kaur, Sparshdeep; Helmus, Drew; Biello, Anthony; Pyzik, Renata; Charney, Alexander; Miotto, Riccardo; Glicksberg, Benjamin S; Levin, Matthew; Nabeel, Ismail; Aberg, Judith; Reich, David; Charney, Dennis; Bottinger, Erwin P; Keefer, Laurie; Suarez-Farinas, Mayte; Nadkarni, Girish N; Fayad, Zahi A in Journal of Medical Internet Research (2021). 23(2) e26107.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Hirten2021, author = {Hirten, Robert P and Danieletto, Matteo and Tomalin, Lewis and Choi, Katie Hyewon and Zweig, Micol and Golden, Eddye and Kaur, Sparshdeep and Helmus, Drew and Biello, Anthony and Pyzik, Renata and Charney, Alexander and Miotto, Riccardo and Glicksberg, Benjamin S and Levin, Matthew and Nabeel, Ismail and Aberg, Judith and Reich, David and Charney, Dennis and Bottinger, Erwin P and Keefer, Laurie and Suarez-Farinas, Mayte and Nadkarni, Girish N and Fayad, Zahi A}, journal = {Journal of Medical Internet Research}, keywords = {boettinger hpims fb-boettinger}, month = {feb}, number = 2, pages = {e26107}, publisher = {{JMIR} Publications Inc.}, title = {Use of Physiological Data From a Wearable Device to Identify {SARS}-{CoV}-2 Infection and Symptoms and Predict {COVID}-19 Diagnosis: Observational Study}, volume = 23, year = 2021 }
A Comparison of Concept Embeddings for German Clinical Corpora. Rasheed, Aadil; Borchert, Florian; Kohlmeyer, Lasse; Henkenjohann, Richard; Schapranow, Matthieu-P. (2021). 2314–2321.
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
Clinical concept embeddings enable unsupervised learning of relationships among medical concepts. A range of benchmarks quantifies the degree to which learned representations capture medical semantics. However, training and evaluation of embeddings require a large amount of data. In addition, embeddings’ benchmark score varies in different languages because it differs with the size of the available corpora. Multi-modal data increases the corpus size, but data protection regulations limit access to clinical multi-modal data. We present an extendable pipeline for training clinical concept embeddings on various text corpora and evaluating the quality of trained embeddings on selected benchmark tasks. Our work provides different ways to identify clinical concepts in textual corpora. We train embeddings on selected German clinical text corpora and evaluate them on various benchmark scores. Our work can be extended to train embeddings in other languages in which a large multi-modal dataset is not available.
@inproceedings{rasheed_concept_embeddings, abstract = {Clinical concept embeddings enable unsupervised learning of relationships among medical concepts. A range of benchmarks quantifies the degree to which learned representations capture medical semantics. However, training and evaluation of embeddings require a large amount of data. In addition, embeddings’ benchmark score varies in different languages because it differs with the size of the available corpora. Multi-modal data increases the corpus size, but data protection regulations limit access to clinical multi-modal data. We present an extendable pipeline for training clinical concept embeddings on various text corpora and evaluating the quality of trained embeddings on selected benchmark tasks. Our work provides different ways to identify clinical concepts in textual corpora. We train embeddings on selected German clinical text corpora and evaluate them on various benchmark scores. Our work can be extended to train embeddings in other languages in which a large multi-modal dataset is not available.}, author = {Rasheed, Aadil and Borchert, Florian and Kohlmeyer, Lasse and Henkenjohann, Richard and Schapranow, Matthieu-P.}, booktitle = {2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)}, keywords = {nlp myown highmed fb-boettinger}, pages = {2314-2321}, title = {A Comparison of Concept Embeddings for German Clinical Corpora}, year = 2021 }

2020

Fast kernel-based rare-variant association tests integrating variant annotations from deep learning. Konigorski, S; Monti, R; Rautenstrauch, P; Lippert, C (2020). (Vol. 44) 495.
[ BibTeX ] [ URL ] [ DOI ]
 
@conference{konigorski2020kernelbased, author = {Konigorski, S and Monti, R and Rautenstrauch, P and Lippert, C}, booktitle = {Genetic Epidemiology}, keywords = {myown}, number = 5, pages = 495, title = {Fast kernel-based rare-variant association tests integrating variant annotations from deep learning}, volume = 44, year = 2020 }
The Care2Report System: Automated Medical Reporting as an Integrated Solution to Reduce Administrative Burden in Healthcare. Maas, Lientje; Geurtsen, Mathan; Nouwt, Florian; Schouten, Stefan F; Van De Water, Robin; Van Dulmen, Sandra; Dalpiaz, Fabiano; Van Deemter, Kees; Brinkkemper, Sjaak in Information Technology in Healthcare: IT Architectures and Implementations in Healthcare Environments (2020).
[ Abstract ] [ BibTeX ] [ URL ]
 
Documenting patient medical information in the electronic medical record is a time-consuming task at the expense of direct patient care. We propose an integrated solution to automate the process of medical reporting. This vision is enabled through the integration of speech and action recognition technology with semantic interpretation based on knowledge graphs. This paper presents our dialogue summarization pipeline that transforms speech into a medical report via transcription and formal representation. We discuss the functional and technical architecture of our Care2Report system along with an initial system evaluation with data of real consultation sessions.
@incollection{maas2020care2report, abstract = {Documenting patient medical information in the electronic medical record is a time-consuming task at the expense of direct patient care. We propose an integrated solution to automate the process of medical reporting. This vision is enabled through the integration of speech and action recognition technology with semantic interpretation based on knowledge graphs. This paper presents our dialogue summarization pipeline that transforms speech into a medical report via transcription and formal representation. We discuss the functional and technical architecture of our Care2Report system along with an initial system evaluation with data of real consultation sessions.}, author = {Maas, Lientje and Geurtsen, Mathan and Nouwt, Florian and Schouten, Stefan F and Van De Water, Robin and Van Dulmen, Sandra and Dalpiaz, Fabiano and Van Deemter, Kees and Brinkkemper, Sjaak}, booktitle = {Information Technology in Healthcare: IT Architectures and Implementations in Healthcare Environments}, keywords = {prior-hpi robinvandewater}, publisher = {Hawaii International Conference on System Sciences (HICSS)}, title = {The Care2Report System: Automated Medical Reporting as an Integrated Solution to Reduce Administrative Burden in Healthcare}, year = 2020 }
Hand in Hand: Wie KI und Ärzte in der Onkologie zusammenarbeiten. Schapranow, Matthieu-P. in Konkrete Anwendungsfälle von KI & Big-Data in der Industrie (2020). 69–74.
[ BibTeX ]
 
@article{noauthororeditor2020onkologie, author = {Schapranow, Matthieu-P.}, journal = {Konkrete Anwendungsfälle von KI & Big-Data in der Industrie}, keywords = {myown}, month = {feb}, pages = {69–74}, title = {Hand in Hand: Wie KI und Ärzte in der Onkologie zusammenarbeiten}, year = 2020 }
Utilization of Deep Learning for Subphenotype Identification in Sepsis-Associated Acute Kidney Injury. Chaudhary, Kumardeep; Vaid, Akhil; Duffy, Áine; Paranjpe, Ishan; Jaladanki, Suraj; Paranjpe, Manish; Johnson, Kipp; Gokhale, Avantee; Pattharanitima, Pattharawin; Chauhan, Kinsuk; O’Hagan, Ross; Vleck, Tielman Van; Coca, Steven G.; Cooper, Richard; Glicksberg, Benjamin; Bottinger, Erwin P.; Chan, Lili; Nadkarni, Girish N. in Clinical Journal of the American Society of Nephrology (2020). CJN.09330819.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Chaudhary2020, author = {Chaudhary, Kumardeep and Vaid, Akhil and Duffy, {{Á}}ine and Paranjpe, Ishan and Jaladanki, Suraj and Paranjpe, Manish and Johnson, Kipp and Gokhale, Avantee and Pattharanitima, Pattharawin and Chauhan, Kinsuk and O'Hagan, Ross and Vleck, Tielman Van and Coca, Steven G. and Cooper, Richard and Glicksberg, Benjamin and Bottinger, Erwin P. and Chan, Lili and Nadkarni, Girish N.}, journal = {Clinical Journal of the American Society of Nephrology}, keywords = {boettinger hpims fb-boettinger}, month = {oct}, pages = {CJN.09330819}, publisher = {American Society of Nephrology ({ASN})}, title = {Utilization of Deep Learning for Subphenotype Identification in Sepsis-Associated Acute Kidney Injury}, year = 2020 }
Powerful rare variant association testing in a copula-based joint analysis of multiple traits. Konigorski, Stefan; Yilmaz, Yildiz E.; Janke, Jürgen; Bergmann, Manuela M.; Boeing, Heiner; Pischon, Tobias in Genetic Epidemiology (2020). 44(1) 26–40.
[ BibTeX ] [ DOI ]
 
@article{konigorski2019powerful, author = {Konigorski, Stefan and Yilmaz, Yildiz E. and Janke, Jürgen and Bergmann, Manuela M. and Boeing, Heiner and Pischon, Tobias}, journal = {Genetic Epidemiology}, keywords = {myown}, number = 1, pages = {26-40}, title = {Powerful rare variant association testing in a copula-based joint analysis of multiple traits}, volume = 44, year = 2020 }
Self-prediction of seizures in drug resistance epilepsy using digital phenotyping: a concept study. Moontaha, Sidratul; Steckhan, Nico; Kappattanavar, Arpita; Surges, Rainer; Arnrich, Bert (2020). (Vol. 14)
[ Abstract ] [ BibTeX ] [ URL ]
 
Drug-resistance is a prevalent condition in children and adult patients with epilepsy. The quality of life of these patients is profoundly affected by the unpredictability of seizure occurrence. Some of these patients are capable of reporting self-prediction of their seizures by observing their affectivity. Some patients report no signs of feeling premonitory symptoms, prodromes, or aura. In this paper, we propose a concept study that will provide objective information to self-predict seizures for both the patient groups. We will develop a model using digital phenotyping which takes both ecological momentary assessment and data from sensor technology into consideration. This method will be able to provide a feedback of their premonitory symptoms so that a pre-emptive therapy can be associated to reduce seizure frequency or eliminate seizure occurrence.
@inproceedings{moontaha2020selfprediction, abstract = {Drug-resistance is a prevalent condition in children and adult patients with epilepsy. The quality of life of these patients is profoundly affected by the unpredictability of seizure occurrence. Some of these patients are capable of reporting self-prediction of their seizures by observing their affectivity. Some patients report no signs of feeling premonitory symptoms, prodromes, or aura. In this paper, we propose a concept study that will provide objective information to self-predict seizures for both the patient groups. We will develop a model using digital phenotyping which takes both ecological momentary assessment and data from sensor technology into consideration. This method will be able to provide a feedback of their premonitory symptoms so that a pre-emptive therapy can be associated to reduce seizure frequency or eliminate seizure occurrence.}, author = {Moontaha, Sidratul and Steckhan, Nico and Kappattanavar, Arpita and Surges, Rainer and Arnrich, Bert}, booktitle = {14th EAI International Conference on Pervasive Computing Technologies for Healthcare - Demos and Posters}, journal = {Pervasive Health}, keywords = {nicosteckhan bertarnrich sidratulmoontaha arpitakappattanavar}, month = {oct}, title = {Self-prediction of seizures in drug resistance epilepsy using digital phenotyping: a concept study}, volume = 14, year = 2020 }
IMU-Based Movement Trajectory Heatmaps for Human Activity Recognition. Konak, Orhan; Wegner, Pit; Arnrich, Bert in Sensors (Switzerland) (2020). 20(24) 1–15.
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
Recent trends in ubiquitous computing have led to a proliferation of studies that focus on human activity recognition (HAR) utilizing inertial sensor data that consist of acceleration, orientation and angular velocity. However, the performances of such approaches are limited by the amount of annotated training data, especially in fields where annotating data is highly time-consuming and requires specialized professionals, such as in healthcare. In image classification, this limitation has been mitigated by powerful oversampling techniques such as data augmentation. Using this technique, this work evaluates to what extent transforming inertial sensor data into movement trajectories and into 2D heatmap images can be advantageous for HAR when data are scarce. A convolutional long short-term memory (ConvLSTM) network that incorporates spatiotemporal correlations was used to classify the heatmap images. Evaluation was carried out on Deep Inertial Poser (DIP), a known dataset composed of inertial sensor data. The results obtained suggest that for datasets with large numbers of subjects, using state-of-the-art methods remains the best alternative. However, a performance advantage was achieved for small datasets, which is usually the case in healthcare. Moreover, movement trajectories provide a visual representation of human activities, which can help researchers to better interpret and analyze motion patterns.
@article{Konak2020, abstract = {Recent trends in ubiquitous computing have led to a proliferation of studies that focus on human activity recognition (HAR) utilizing inertial sensor data that consist of acceleration, orientation and angular velocity. However, the performances of such approaches are limited by the amount of annotated training data, especially in fields where annotating data is highly time-consuming and requires specialized professionals, such as in healthcare. In image classification, this limitation has been mitigated by powerful oversampling techniques such as data augmentation. Using this technique, this work evaluates to what extent transforming inertial sensor data into movement trajectories and into 2D heatmap images can be advantageous for HAR when data are scarce. A convolutional long short-term memory (ConvLSTM) network that incorporates spatiotemporal correlations was used to classify the heatmap images. Evaluation was carried out on Deep Inertial Poser (DIP), a known dataset composed of inertial sensor data. The results obtained suggest that for datasets with large numbers of subjects, using state-of-the-art methods remains the best alternative. However, a performance advantage was achieved for small datasets, which is usually the case in healthcare. Moreover, movement trajectories provide a visual representation of human activities, which can help researchers to better interpret and analyze motion patterns.}, author = {Konak, Orhan and Wegner, Pit and Arnrich, Bert}, journal = {Sensors (Switzerland)}, keywords = {bertarnrich orhankonak}, number = 24, pages = {1–15}, title = {IMU-Based Movement Trajectory Heatmaps for Human Activity Recognition}, volume = 20, year = 2020 }
Tangle Ledger for Decentralized Learning. Schmid, R.; Pfitzner, B.; Beilharz, J.; Arnrich, B.; Polze, A. (2020). 852–859.
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
Federated learning has the potential to make machine learning applicable to highly privacy-sensitive domains and distributed datasets. In some scenarios, however, a central server for aggregating the partial learning results is not available. In fully decentralized learning, a network of peer-to-peer nodes collaborates to form a consensus on a global model without a trusted aggregating party. Often, the network consists of Internet of Things (IoT) and Edge computing nodes.Previous approaches for decentralized learning map the gradient batching and averaging algorithm from traditional federated learning to blockchain architectures. In an open network of participating nodes, the threat of adversarial nodes introducing poisoned models into the network increases compared to a federated learning scenario which is controlled by a single authority. Hence, the decentralized architecture must additionally include a machine learning-aware fault tolerance mechanism to address the increased attack surface.We propose a tangle architecture for decentralized learning, where the validity of model updates is checked as part of the basic consensus. We provide an experimental evaluation of the proposed architecture, showing that it performs well in both model convergence and model poisoning protection.
@inproceedings{schmid2020tangle, abstract = {Federated learning has the potential to make machine learning applicable to highly privacy-sensitive domains and distributed datasets. In some scenarios, however, a central server for aggregating the partial learning results is not available. In fully decentralized learning, a network of peer-to-peer nodes collaborates to form a consensus on a global model without a trusted aggregating party. Often, the network consists of Internet of Things (IoT) and Edge computing nodes.Previous approaches for decentralized learning map the gradient batching and averaging algorithm from traditional federated learning to blockchain architectures. In an open network of participating nodes, the threat of adversarial nodes introducing poisoned models into the network increases compared to a federated learning scenario which is controlled by a single authority. Hence, the decentralized architecture must additionally include a machine learning-aware fault tolerance mechanism to address the increased attack surface.We propose a tangle architecture for decentralized learning, where the validity of model updates is checked as part of the basic consensus. We provide an experimental evaluation of the proposed architecture, showing that it performs well in both model convergence and model poisoning protection.}, author = {Schmid, R. and Pfitzner, B. and Beilharz, J. and Arnrich, B. and Polze, A.}, booktitle = {2020 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)}, keywords = {bertarnrich bjarnepfitzner}, month = {may}, pages = {852-859}, title = {Tangle Ledger for Decentralized Learning}, year = 2020 }
Tackling the SHL Challenge 2020 with Person-Specific Classifiers and Semi-Supervised Learning. Kalabakov, Stefan; Stankoski, Simon; Rescic, Nina; Kiprijanovska, Ivana; Andova, Andrejaana; Picard, Clement; Janko, Vito; Gjoreski, Martin; Lustrek, Mitja in UbiComp-ISWC ’20 (2020). 323–328.
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
The SHL recognition challenge 2020 was an open competition in activity recognition where the participants were tasked with recognizing eight different modes of locomotion and transportation with smartphone sensors. The main challenges were that the training data was recorded by a different person than the validation and test data, and that the smartphone location in the test data was unknown to the participants. We, team "Third time's a charm", tackled the first challenge by attempting to identify the persons with clustering, and then performed cluster/person-specific feature selection to build a separate classifier for each person. The smartphone location appears not to make much difference. We also used semi-supervised learning to classify the test data. Internal tests using this methodology yielded an accuracy of 81.01%.
@inproceedings{10.1145/3410530.3414848, abstract = {The SHL recognition challenge 2020 was an open competition in activity recognition where the participants were tasked with recognizing eight different modes of locomotion and transportation with smartphone sensors. The main challenges were that the training data was recorded by a different person than the validation and test data, and that the smartphone location in the test data was unknown to the participants. We, team "Third time's a charm", tackled the first challenge by attempting to identify the persons with clustering, and then performed cluster/person-specific feature selection to build a separate classifier for each person. The smartphone location appears not to make much difference. We also used semi-supervised learning to classify the test data. Internal tests using this methodology yielded an accuracy of 81.01\%.}, address = {New York, NY, USA}, author = {Kalabakov, Stefan and Stankoski, Simon and Rescic, Nina and Kiprijanovska, Ivana and Andova, Andrejaana and Picard, Clement and Janko, Vito and Gjoreski, Martin and Lustrek, Mitja}, booktitle = {Adjunct Proceedings of the 2020 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2020 ACM International Symposium on Wearable Computers}, keywords = {bertarnrich prior-hpi kalabakovstefan}, pages = {323–328}, publisher = {Association for Computing Machinery}, series = {UbiComp-ISWC '20}, title = {Tackling the SHL Challenge 2020 with Person-Specific Classifiers and Semi-Supervised Learning}, year = 2020 }
Spotlight on Women in Tech: Fostering an Inclusive Workforce when Exploring and Exploiting Digital Innovation Potentials. Schmitt, Franziska; Sundermeier, Janina; Bohn, Nicolai; Morassi Sasso, Ariane (2020). (Vol. 6)
[ BibTeX ]
 
@inproceedings{schmitt2020spotlight, author = {Schmitt, Franziska and Sundermeier, Janina and Bohn, Nicolai and Morassi Sasso, Ariane}, booktitle = {ICIS Proceedings}, keywords = {myown fb-boettinger dhc}, title = {Spotlight on Women in Tech: Fostering an Inclusive Workforce when Exploring and Exploiting Digital Innovation Potentials}, volume = 6, year = 2020 }
StudyU: a platform for designing and conducting innovative digital N-of-1 trials Konigorski, Stefan; Wernicke, Sarah; Slosarek, Tamara; Zenner, Alexander M.; Strelow, Nils; Ruether, Ferenc D.; Henschel, Florian; Manaswini, Manisha; Pottbäcker, Fabian; Edelman, Jonathan A.; Owoyele, Babajide; Danieletto, Matteo; Golden, Eddye; Zweig, Micol; Nadkarni, Girish; Böttinger, Erwin (2020).
[ BibTeX ] [ URL ]
 
@preprint{konigorski2020studyu, author = {Konigorski, Stefan and Wernicke, Sarah and Slosarek, Tamara and Zenner, Alexander M. and Strelow, Nils and Ruether, Ferenc D. and Henschel, Florian and Manaswini, Manisha and Pottbäcker, Fabian and Edelman, Jonathan A. and Owoyele, Babajide and Danieletto, Matteo and Golden, Eddye and Zweig, Micol and Nadkarni, Girish and Böttinger, Erwin}, journal = {arXiv:2012.14201}, keywords = {myown}, title = {StudyU: a platform for designing and conducting innovative digital N-of-1 trials}, year = 2020 }
IMU-Based Movement Trajectory Heatmaps for Human Activity Recognition. Konak, Orhan; Wegner, Pit; Arnrich, Bert in Sensors (2020). 20(24) 7179.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Konak2020, author = {Konak, Orhan and Wegner, Pit and Arnrich, Bert}, journal = {Sensors}, keywords = {arnrich myown bert fb-boettinger}, month = {dec}, number = 24, pages = 7179, publisher = {{MDPI} {AG}}, title = {{IMU}-Based Movement Trajectory Heatmaps for Human Activity Recognition}, volume = 20, year = 2020 }
Prototypical System to Detect Anxiety Manifestations by Acoustic Patterns in Patients with Dementia. Hernandez, Netzahualcoyotl; Garcia-Constantino, Matias; Beltran, Jessica; Hecker, Pascal; Favela, Jesus; Cleland, Ian; Lopez, Hussein; Arnrich, Bert; McChesney, Ian in EAI Endorsed Transactions on Pervasive Health and Technology (2020). 5(19)
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
INTRODUCTION: Dementia is a syndrome characterised by a decline in memory, language, and problem-solving that affects the ability of patients to perform everyday activities. Patients with dementia tend to experience episodes of anxiety and remain for extended periods, which affects their quality of life. OBJECTIVES: To design AnxiDetector, a system capable of detecting patterns of sounds associated before and during the manifestation of anxiety in patients with dementia. METHODS: We conducted a non-participatory observation of 70 diagnosed patients in-situ, and conducted semi-structured interviews with four caregivers at a residential centre. Using the findings from our observation and caregiver interviews, we developed the AnxiDetector prototype and tested this in an experimental setting where we defined nine classes of audio to represent two groups of sounds: (i) Disturbance which includes audio files that characterise sounds that trigger anxiety in patients with dementia, and (ii) Expression which includes audio files that characterise sounds expressed by the patients during episodes of anxiety. We conducted two experimental classifications of sounds using (i) a Neural Network model trained and (ii) a Support Vector Machine model. The first evaluation consists of a binary discriminating between the two groups of sounds; the second evaluation discriminates the nine classes of audio. The audio resources were retrieved from publicly available datasets. RESULTS: The qualitative results present the views of the caregivers on the adoption of AnxiDetector. The quantitative results from our binary discrimination show a classification accuracy of 98.1% and 99.2% for the Deep Neural Network and Support Vector Machine models, respectively. When classifying the nine classes of sound, our model shows a classification accuracy of 92.2%. Whereas, the Support Vector Machine model yielded an overall classification accuracy of 93.0%. CONCLUSION: In this paper, we presented the outcomes from an observational study in-site at a residential care centre, qualitative findings from interviews with caregivers, the design of AnxiDetector, and preliminary qualitative results of a methodology devised to detect relevant acoustic events associated with anxiety in patients with dementia. We conclude by signalling future plans to conduct in-situ validation of the effectiveness of AnxiDetector for anxiety detection.
@article{hernandez2020prototypical, abstract = {INTRODUCTION: Dementia is a syndrome characterised by a decline in memory, language, and problem-solving that affects the ability of patients to perform everyday activities. Patients with dementia tend to experience episodes of anxiety and remain for extended periods, which affects their quality of life. OBJECTIVES: To design AnxiDetector, a system capable of detecting patterns of sounds associated before and during the manifestation of anxiety in patients with dementia. METHODS: We conducted a non-participatory observation of 70 diagnosed patients in-situ, and conducted semi-structured interviews with four caregivers at a residential centre. Using the findings from our observation and caregiver interviews, we developed the AnxiDetector prototype and tested this in an experimental setting where we defined nine classes of audio to represent two groups of sounds: (i) Disturbance which includes audio files that characterise sounds that trigger anxiety in patients with dementia, and (ii) Expression which includes audio files that characterise sounds expressed by the patients during episodes of anxiety. We conducted two experimental classifications of sounds using (i) a Neural Network model trained and (ii) a Support Vector Machine model. The first evaluation consists of a binary discriminating between the two groups of sounds; the second evaluation discriminates the nine classes of audio. The audio resources were retrieved from publicly available datasets. RESULTS: The qualitative results present the views of the caregivers on the adoption of AnxiDetector. The quantitative results from our binary discrimination show a classification accuracy of 98.1% and 99.2% for the Deep Neural Network and Support Vector Machine models, respectively. When classifying the nine classes of sound, our model shows a classification accuracy of 92.2%. Whereas, the Support Vector Machine model yielded an overall classification accuracy of 93.0%. CONCLUSION: In this paper, we presented the outcomes from an observational study in-site at a residential care centre, qualitative findings from interviews with caregivers, the design of AnxiDetector, and preliminary qualitative results of a methodology devised to detect relevant acoustic events associated with anxiety in patients with dementia. We conclude by signalling future plans to conduct in-situ validation of the effectiveness of AnxiDetector for anxiety detection.}, author = {Hernandez, Netzahualcoyotl and Garcia-Constantino, Matias and Beltran, Jessica and Hecker, Pascal and Favela, Jesus and Cleland, Ian and Lopez, Hussein and Arnrich, Bert and McChesney, Ian}, journal = {EAI Endorsed Transactions on Pervasive Health and Technology}, keywords = {pascalhecker bertarnrich}, month = 8, number = 19, title = {Prototypical System to Detect Anxiety Manifestations by Acoustic Patterns in Patients with Dementia}, volume = 5, year = 2020 }
ALPS: A Web Platform for Analysing Multimodal Sensor Data in the Context of Digital Health. Musmann, F.; Sasso, A.; Arnrich, B. (2020). 1–12.
[ BibTeX ] [ URL ] [ DOI ]
 
@inproceedings{9374371, address = {Los Alamitos, CA, USA}, author = {Musmann, F. and Sasso, A. and Arnrich, B.}, booktitle = {2020 IEEE International Conference on Healthcare Informatics (ICHI)}, keywords = {bertarnrich fb-boettinger}, month = {dec}, pages = {1-12}, publisher = {IEEE Computer Society}, title = {ALPS: A Web Platform for Analysing Multimodal Sensor Data in the Context of Digital Health}, year = 2020 }
Using CEF Digital Service Infrastructures in the Smart4Health Project for the Exchange of Electronic Health Records. Slosarek, Tamara; Wohlbrandt, Attila; Böttinger, Erwin in arXiv preprint arXiv:2001.01477 (2020).
[ BibTeX ]
 
@article{slosarek2020cef, author = {Slosarek, Tamara and Wohlbrandt, Attila and Böttinger, Erwin}, journal = {arXiv preprint arXiv:2001.01477}, keywords = {myown fb-boettinger}, title = {Using CEF Digital Service Infrastructures in the Smart4Health Project for the Exchange of Electronic Health Records}, year = 2020 }
Will You Be My Quarantine: A Computer Vision and Inertial Sensor Based Home Exercise System. Albert, Justin; Zhou, Lin; Gloeckner, Pawel; Trautmann, Justin; Ihde, Lisa; Eilers, Justus; Kamal, Mohammed; Arnrich, Bert (2020). (Vol. 14)
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
The quarantine situation inflicted by the COVID-19 pandemic has left many people around the world isolated at home. Despite the large variety of mobile device-based self exercise tools for training plans, activity recognition or repetition counts, it remains challenging for an inexperienced person to perform fitness workouts or learn a new sport with the correct movements at home. As a proof of concept, a home exercise system has been developed in this contribution. The system takes computer vision and inertial sensor data recorded for the same type of exercise as two independent inputs, and processes the data from both sources into the same representations on the levels of raw inertial measurement unit (IMU) data and 3D movement trajectories. Moreover, a Key Performance Indicator (KPI) dashboard was developed for data import and visualization. The usability of the system was investigated with an example use case where the learner equipped with IMUs performed a kick movement and was able to compare it to that from a coach in the video.
@inproceedings{albert2020quarantine, abstract = {The quarantine situation inflicted by the COVID-19 pandemic has left many people around the world isolated at home. Despite the large variety of mobile device-based self exercise tools for training plans, activity recognition or repetition counts, it remains challenging for an inexperienced person to perform fitness workouts or learn a new sport with the correct movements at home. As a proof of concept, a home exercise system has been developed in this contribution. The system takes computer vision and inertial sensor data recorded for the same type of exercise as two independent inputs, and processes the data from both sources into the same representations on the levels of raw inertial measurement unit (IMU) data and 3D movement trajectories. Moreover, a Key Performance Indicator (KPI) dashboard was developed for data import and visualization. The usability of the system was investigated with an example use case where the learner equipped with IMUs performed a kick movement and was able to compare it to that from a coach in the video.}, author = {Albert, Justin and Zhou, Lin and Gloeckner, Pawel and Trautmann, Justin and Ihde, Lisa and Eilers, Justus and Kamal, Mohammed and Arnrich, Bert}, booktitle = {14th EAI International Conference on Pervasive Computing Technologies for Healthcare - Demos and Posters}, journal = {Pervasive Health}, keywords = {linzhou justinalbert bertarnrich}, month = 8, publisher = {EAI}, title = {Will You Be My Quarantine: A Computer Vision and Inertial Sensor Based Home Exercise System}, volume = 14, year = 2020 }
Good news: How data science helps us to better understand the Coronavirus pandemic. Schapranow, Matthieu-P. in Portal Wissen: The research magazine of the University of Potsdam (2020). 2(9) 14–19.
[ BibTeX ] [ DOI ]
 
@article{schapranow2020science, author = {Schapranow, Matthieu-P.}, journal = {Portal Wissen: The research magazine of the University of Potsdam}, keywords = {myown}, month = {nov}, number = 9, pages = {14–19}, title = {Good news: How data science helps us to better understand the Coronavirus pandemic}, volume = 2, year = 2020 }
Schöne neue Ärzte-Welt: Kümmern sich kluge Computer bald um unsere Gesundheitsprobleme?. Schapranow, Matthieu-P. in F.A.Z. Sonderbeliage Gesundheit (2020). (48) B2.
[ BibTeX ]
 
@article{schapranow2020aerztewelt, author = {Schapranow, Matthieu-P.}, journal = {F.A.Z. Sonderbeliage Gesundheit}, keywords = {myown}, month = {feb}, number = 48, pages = {B2}, title = {Schöne neue Ärzte-Welt: Kümmern sich kluge Computer bald um unsere Gesundheitsprobleme?}, year = 2020 }
HYPE: Predicting Blood Pressure from Photoplethysmograms in a Hypertensive Population. Morassi Sasso, Ariane; Datta, Suparno; Jeitler, Michael; Steckhan, Nico; Kessler, Christian S.; Michalsen, Andreas; Arnrich, Bert; Böttinger, Erwin M. Michalowski, R. Moskovitch (eds.) (2020). (Vol. 12299)
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
The state of the art for monitoring hypertension relies on measuring blood pressure (BP) using uncomfortable cuff-based devices. Hence, for increased adherence in monitoring, a better way of measuring BP is needed. That could be achieved through comfortable wearables that contain photoplethysmography (PPG) sensors. There have been several studies showing the possibility of statistically estimating systolic and diastolic BP (SBP/DBP) from PPG signals. However, they are either based on measurements of healthy subjects or on patients on (ICUs). Thus, there is a lack of studies with patients out of the normal range of BP and with daily life monitoring out of the ICUs. To address this, we created a dataset (HYPE) composed of data from hypertensive subjects that executed a stress test and had 24-h monitoring. We then trained and compared machine learning (ML) models to predict BP. We evaluated handcrafted feature extraction approaches vs image representation ones and compared different ML algorithms for both. Moreover, in order to evaluate the models in a different scenario, we used an openly available set from a stress test with healthy subjects (EVAL). The best results for our HYPE dataset were in the stress test and had a mean absolute error (MAE) in mmHg of 8.79 (±3.17) for SBP and 6.37 (±2.62) for DBP; for our EVAL dataset it was 14.74 (±4.06) and 7.12 (±2.32) respectively. Although having tested a range of signal processing and ML techniques, we were not able to reproduce the small error ranges claimed in the literature. The mixed results suggest a need for more comparative studies with subjects out of the intensive care and across all ranges of blood pressure. Until then, the clinical relevance of PPG-based predictions in daily life should remain an open question.
@inproceedings{MorassiSasso2020, abstract = {The state of the art for monitoring hypertension relies on measuring blood pressure (BP) using uncomfortable cuff-based devices. Hence, for increased adherence in monitoring, a better way of measuring BP is needed. That could be achieved through comfortable wearables that contain photoplethysmography (PPG) sensors. There have been several studies showing the possibility of statistically estimating systolic and diastolic BP (SBP/DBP) from PPG signals. However, they are either based on measurements of healthy subjects or on patients on (ICUs). Thus, there is a lack of studies with patients out of the normal range of BP and with daily life monitoring out of the ICUs. To address this, we created a dataset (HYPE) composed of data from hypertensive subjects that executed a stress test and had 24-h monitoring. We then trained and compared machine learning (ML) models to predict BP. We evaluated handcrafted feature extraction approaches vs image representation ones and compared different ML algorithms for both. Moreover, in order to evaluate the models in a different scenario, we used an openly available set from a stress test with healthy subjects (EVAL). The best results for our HYPE dataset were in the stress test and had a mean absolute error (MAE) in mmHg of 8.79 (±3.17) for SBP and 6.37 (±2.62) for DBP; for our EVAL dataset it was 14.74 (±4.06) and 7.12 (±2.32) respectively. Although having tested a range of signal processing and ML techniques, we were not able to reproduce the small error ranges claimed in the literature. The mixed results suggest a need for more comparative studies with subjects out of the intensive care and across all ranges of blood pressure. Until then, the clinical relevance of PPG-based predictions in daily life should remain an open question.}, author = {Morassi Sasso, Ariane and Datta, Suparno and Jeitler, Michael and Steckhan, Nico and Kessler, Christian S. and Michalsen, Andreas and Arnrich, Bert and Böttinger, Erwin}, booktitle = {Artificial Intelligence in Medicine. AIME 2020. Lecture Notes in Computer Science}, editor = {Michalowski, M. and Moskovitch, R.}, keywords = {nicosteckhan bertarnrich}, publisher = {Springer}, title = {HYPE: Predicting Blood Pressure from Photoplethysmograms in a Hypertensive Population}, volume = 12299, year = 2020 }
Physiological Data from a Wearable Device Identifies SARS-CoV-2 Infection and Symptoms and Predicts COVID-19 Diagnosis: Observational Study (Preprint). Hirten, Robert P; Danieletto, Matteo; Tomalin, Lewis; Choi, Katie Hyewon; Zweig, Micol; Golden, Eddye; Kaur, Sparshdeep; Helmus, Drew; Biello, Anthony; Pyzik, Renata; Charney, Alexander; Miotto, Riccardo; Glicksberg, Benjamin S; Levin, Matthew; Nabeel, Ismail; Aberg, Judith; Reich, David; Charney, Dennis; Bottinger, Erwin P; Keefer, Laurie; Suarez-Farinas, Mayte; Nadkarni, Girish N; Fayad, Zahi A in Journal of Medical Internet Research (2020).
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Hirten2020, author = {Hirten, Robert P and Danieletto, Matteo and Tomalin, Lewis and Choi, Katie Hyewon and Zweig, Micol and Golden, Eddye and Kaur, Sparshdeep and Helmus, Drew and Biello, Anthony and Pyzik, Renata and Charney, Alexander and Miotto, Riccardo and Glicksberg, Benjamin S and Levin, Matthew and Nabeel, Ismail and Aberg, Judith and Reich, David and Charney, Dennis and Bottinger, Erwin P and Keefer, Laurie and Suarez-Farinas, Mayte and Nadkarni, Girish N and Fayad, Zahi A}, journal = {Journal of Medical Internet Research}, keywords = {boettinger hpims fb-boettinger}, month = {nov}, publisher = {{JMIR} Publications Inc.}, title = {Physiological Data from a Wearable Device Identifies {SARS}-{CoV}-2 Infection and Symptoms and Predicts {COVID}-19 Diagnosis: Observational Study (Preprint)}, year = 2020 }
AKI in Hospitalized Patients with COVID-19. Chan, Lili; Chaudhary, Kumardeep; Saha, Aparna; Chauhan, Kinsuk; Vaid, Akhil; Zhao, Shan; Paranjpe, Ishan; Somani, Sulaiman; Richter, Felix; Miotto, Riccardo; Lala, Anuradha; Kia, Arash; Timsina, Prem; Li, Li; Freeman, Robert; Chen, Rong; Narula, Jagat; Just, Allan C.; Horowitz, Carol; Fayad, Zahi; Cordon-Cardo, Carlos; Schadt, Eric; Levin, Matthew A.; Reich, David L.; Fuster, Valentin; Murphy, Barbara; He, John C.; Charney, Alexander W.; Bottinger, Erwin P.; Glicksberg, Benjamin S.; Coca, Steven G.; Nadkarni, Girish N. in Journal of the American Society of Nephrology (2020). 32(1) 151–160.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Chan2020, author = {Chan, Lili and Chaudhary, Kumardeep and Saha, Aparna and Chauhan, Kinsuk and Vaid, Akhil and Zhao, Shan and Paranjpe, Ishan and Somani, Sulaiman and Richter, Felix and Miotto, Riccardo and Lala, Anuradha and Kia, Arash and Timsina, Prem and Li, Li and Freeman, Robert and Chen, Rong and Narula, Jagat and Just, Allan C. and Horowitz, Carol and Fayad, Zahi and Cordon-Cardo, Carlos and Schadt, Eric and Levin, Matthew A. and Reich, David L. and Fuster, Valentin and Murphy, Barbara and He, John C. and Charney, Alexander W. and Bottinger, Erwin P. and Glicksberg, Benjamin S. and Coca, Steven G. and Nadkarni, Girish N.}, journal = {Journal of the American Society of Nephrology}, keywords = {boettinger hpims fb-boettinger}, month = {sep}, number = 1, pages = {151–160}, publisher = {American Society of Nephrology ({ASN})}, title = {AKI in Hospitalized Patients with {COVID}-19}, volume = 32, year = 2020 }
The effect of LRRK2 loss-of-function variants in humans. Whiffin, Nicola; Armean, and Irina M.; Kleinman, Aaron; Marshall, Jamie L.; Minikel, Eric V.; Goodrich, Julia K.; Quaife, Nicholas M.; Cole, Joanne B.; Wang, Qingbo; Karczewski, Konrad J.; Cummings, Beryl B.; Francioli, Laurent; Laricchia, Kristen; Guan, Anna; Alipanahi, Babak; Morrison, Peter; Baptista, Marco A. S.; Merchant, Kalpana M.; Ware, James S.; Havulinna, Aki S.; Iliadou, Bozenna; Lee, Jung-Jin; Nadkarni, Girish N.; Whiteman, Cole; Daly, Mark; Esko, T~onu; Hultman, Christina; Loos, Ruth J. F.; Milani, Lili; Palotie, Aarno; Pato, Carlos; Pato, Michele; Saleheen, Danish; Sullivan, Patrick F.; Alföldi, Jessica; Cannon, Paul; MacArthur, Daniel G.; and in Nature Medicine (2020). 26(6) 869–877.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Whiffin2020, author = {Whiffin, Nicola and and Irina M. Armean and Kleinman, Aaron and Marshall, Jamie L. and Minikel, Eric V. and Goodrich, Julia K. and Quaife, Nicholas M. and Cole, Joanne B. and Wang, Qingbo and Karczewski, Konrad J. and Cummings, Beryl B. and Francioli, Laurent and Laricchia, Kristen and Guan, Anna and Alipanahi, Babak and Morrison, Peter and Baptista, Marco A. S. and Merchant, Kalpana M. and Ware, James S. and Havulinna, Aki S. and Iliadou, Bozenna and Lee, Jung-Jin and Nadkarni, Girish N. and Whiteman, Cole and Daly, Mark and Esko, T{\ {o}}nu and Hultman, Christina and Loos, Ruth J. F. and Milani, Lili and Palotie, Aarno and Pato, Carlos and Pato, Michele and Saleheen, Danish and Sullivan, Patrick F. and Alf{ö}ldi, Jessica and Cannon, Paul and MacArthur, Daniel G. and and}, journal = {Nature Medicine}, keywords = {boettinger hpims fb-boettinger}, month = {may}, number = 6, pages = {869–877}, publisher = {Springer Science and Business Media {LLC}}, title = {The effect of {LRRK}2 loss-of-function variants in humans}, volume = 26, year = 2020 }
Outcomes of Patients on Maintenance Dialysis Hospitalized with COVID-19. Chan, Lili; Jaladanki, Suraj K.; Somani, Sulaiman; Paranjpe, Ishan; Kumar, Arvind; Zhao, Shan; Kaufman, Lewis; Leisman, Staci; Sharma, Shuchita; He, John Cijiang; Murphy, Barbara; Fayad, Zahi A.; Levin, Matthew A.; Bottinger, Erwin P.; Charney, Alexander W.; Glicksberg, Benjamin S.; Coca, Steven G.; Nadkarni, Girish N. in Clinical Journal of the American Society of Nephrology (2020). 16(3) 452–455.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Chan2020, author = {Chan, Lili and Jaladanki, Suraj K. and Somani, Sulaiman and Paranjpe, Ishan and Kumar, Arvind and Zhao, Shan and Kaufman, Lewis and Leisman, Staci and Sharma, Shuchita and He, John Cijiang and Murphy, Barbara and Fayad, Zahi A. and Levin, Matthew A. and Bottinger, Erwin P. and Charney, Alexander W. and Glicksberg, Benjamin S. and Coca, Steven G. and Nadkarni, Girish N.}, journal = {Clinical Journal of the American Society of Nephrology}, keywords = {boettinger hpims fb-boettinger}, month = {oct}, number = 3, pages = {452–455}, publisher = {American Society of Nephrology ({ASN})}, title = {Outcomes of Patients on Maintenance Dialysis Hospitalized with {COVID}-19}, volume = 16, year = 2020 }
Rapid response to the alpha-1 adrenergic agent phenylephrine in the perioperative period is impacted by genomics and ancestry. Wenric, Stephane; Jeff, Janina M.; Joseph, Thomas; Yee, Muh-Ching; Belbin, Gillian M.; Obeng, Aniwaa Owusu; Ellis, Stephen B.; Bottinger, Erwin P.; Gottesman, Omri; Levin, Matthew A.; Kenny, Eimear E. in The Pharmacogenomics Journal (2020). 21(2) 174–189.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Wenric2020, author = {Wenric, Stephane and Jeff, Janina M. and Joseph, Thomas and Yee, Muh-Ching and Belbin, Gillian M. and Obeng, Aniwaa Owusu and Ellis, Stephen B. and Bottinger, Erwin P. and Gottesman, Omri and Levin, Matthew A. and Kenny, Eimear E.}, journal = {The Pharmacogenomics Journal}, keywords = {boettinger fb-boettinger}, month = {nov}, number = 2, pages = {174–189}, publisher = {Springer Science and Business Media {LLC}}, title = {Rapid response to the alpha-1 adrenergic agent phenylephrine in the perioperative period is impacted by genomics and ancestry}, volume = 21, year = 2020 }
Validation of an IMU Gait Analysis Algorithm for Gait Monitoring in Daily Life Situations. Zhou, Lin; Tunca, Can; Fischer, Eric; Brahms, Clemens Markus; Ersoy, Cem; Granacher, Urs; Arnrich, Bert (2020).
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
Gait is an essential function for humans, and gait patterns in daily life provide meaningful information about a person’s cognitive and physical health conditions. Inertial measurement units (IMUs) have emerged as a promising tool for low-cost, unobtrusive gait analysis. However, large varieties of IMU gait analysis algorithms and the lack of consensus for their validation make it difficult for researchers to assess the reliability of the algorithms for specific use cases. In daily life,individuals adapt their gait patterns in response to changes in the environment, making it necessary for IMU gait analysis algorithms to provide accurate measurements despite these gait variations. In this paper, we reviewed common types of IMU gait analysis algorithms and appropriate analysis methods to evaluate the accuracy of gait parameters extracted from IMU measurements. We then evaluated stride lengths and stride times calculated from a comprehensive double integration based IMU gait analysis algorithm using an optoelectric walkway as gold standard. In total, 729 strides from five healthy subjects and three different walking patterns were analyzed. Correlation analyses and Bland-Altman plots showed that this method is accurate and robust against large variations in walking patterns (stride length: correlation coefficient (r) was 0.99, root mean square error (RMSE) was 3% and average limits of agreement (LoA) was 6%; stride time: r was 0.95, RMSE was 4% and average LoA was 7%), making it suitable for gait evaluation in daily life situations. Due to the small sample size, our preliminary findings should be verified in future studies.
@inproceedings{zhou2020validation, abstract = {Gait is an essential function for humans, and gait patterns in daily life provide meaningful information about a person’s cognitive and physical health conditions. Inertial measurement units (IMUs) have emerged as a promising tool for low-cost, unobtrusive gait analysis. However, large varieties of IMU gait analysis algorithms and the lack of consensus for their validation make it difficult for researchers to assess the reliability of the algorithms for specific use cases. In daily life,individuals adapt their gait patterns in response to changes in the environment, making it necessary for IMU gait analysis algorithms to provide accurate measurements despite these gait variations. In this paper, we reviewed common types of IMU gait analysis algorithms and appropriate analysis methods to evaluate the accuracy of gait parameters extracted from IMU measurements. We then evaluated stride lengths and stride times calculated from a comprehensive double integration based IMU gait analysis algorithm using an optoelectric walkway as gold standard. In total, 729 strides from five healthy subjects and three different walking patterns were analyzed. Correlation analyses and Bland-Altman plots showed that this method is accurate and robust against large variations in walking patterns (stride length: correlation coefficient (r) was 0.99, root mean square error (RMSE) was 3% and average limits of agreement (LoA) was 6%; stride time: r was 0.95, RMSE was 4% and average LoA was 7%), making it suitable for gait evaluation in daily life situations. Due to the small sample size, our preliminary findings should be verified in future studies.}, author = {Zhou, Lin and Tunca, Can and Fischer, Eric and Brahms, Clemens Markus and Ersoy, Cem and Granacher, Urs and Arnrich, Bert}, booktitle = {2020 42nd Annual International Conference of the IEEE Engineering in Medicine Biology Society (EMBC)}, keywords = {linzhou bertarnrich}, month = {july}, publisher = {IEEE}, title = {Validation of an IMU Gait Analysis Algorithm for Gait Monitoring in Daily Life Situations}, year = 2020 }
Phe2vec: Automated Disease Phenotyping based on Unsupervised Embeddings from Electronic Health Records. Freitas, Jessica K. De; Johnson, Kipp W.; Golden, Eddye; Nadkarni, Girish N.; Dudley, Joel T.; Bottinger, Erwin P.; Glicksberg, Benjamin S.; Miotto, Riccardo (2020).
[ BibTeX ] [ URL ] [ DOI ]
 
@article{DeFreitas2020, author = {Freitas, Jessica K. De and Johnson, Kipp W. and Golden, Eddye and Nadkarni, Girish N. and Dudley, Joel T. and Bottinger, Erwin P. and Glicksberg, Benjamin S. and Miotto, Riccardo}, keywords = {boettinger hpims fb-boettinger}, month = {nov}, publisher = {Cold Spring Harbor Laboratory}, title = {Phe2vec: Automated Disease Phenotyping based on Unsupervised Embeddings from Electronic Health Records}, year = 2020 }
Position Matters: Sensor Placement for SittingPosture Classification. Kappattanavar, A. M.; da Cruz, H. F.; Arnrich, B.; Böttinger, E. (2020).
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
Prolonged sitting behavior and postures that cause strain on the spine and muscles have been reported to increase the probability of low back pain. To address this issue, many commercially available sensors already provide feedback about whether a person is 'slouching' or 'not slouching'. However, they do not provide information on a person's posture, which would give insights into the strain caused by a specific posture. Hence, in this pilot study, we attempt to find the optimum number of inertial measurement unit sensors required and the best locations to place them using six mock postures. Data is collected from these sensors and features are extracted. The number of features are reduced and the best features are selected using the Recursive Feature Elimination method with Cross-Validation. The reduced number of features is then trained and tested on Logistic Regression, Support Vector Machine and Hierarchical Model. Among the three models, the Support Vector Machine algorithm had the highest accuracy of 93.68%, obtained for the thoracic, hip and sacral region sensor combinations. While these findings will be validated in a larger study in an uncontrolled environment, this pilot study quantitatively highlights the importance of sensor placement in shaping discriminative performance in sitting posture classification tasks.
@inproceedings{kappattanavar2020position, abstract = {Prolonged sitting behavior and postures that cause strain on the spine and muscles have been reported to increase the probability of low back pain. To address this issue, many commercially available sensors already provide feedback about whether a person is 'slouching' or 'not slouching'. However, they do not provide information on a person's posture, which would give insights into the strain caused by a specific posture. Hence, in this pilot study, we attempt to find the optimum number of inertial measurement unit sensors required and the best locations to place them using six mock postures. Data is collected from these sensors and features are extracted. The number of features are reduced and the best features are selected using the Recursive Feature Elimination method with Cross-Validation. The reduced number of features is then trained and tested on Logistic Regression, Support Vector Machine and Hierarchical Model. Among the three models, the Support Vector Machine algorithm had the highest accuracy of 93.68%, obtained for the thoracic, hip and sacral region sensor combinations. While these findings will be validated in a larger study in an uncontrolled environment, this pilot study quantitatively highlights the importance of sensor placement in shaping discriminative performance in sitting posture classification tasks.}, author = {Kappattanavar, A. M. and da Cruz, H. F. and Arnrich, B. and Böttinger, E.}, booktitle = {ICHI '20: Proceedings of the 2020 IEEE International Conference on Healthcare Informatics}, keywords = {bertarnrich arpitakappattanavar fb-boettinger}, publisher = {IEEE}, title = {Position Matters: Sensor Placement for SittingPosture Classification}, year = 2020 }
Coronavirus 2019 and People Living With Human Immunodeficiency Virus: Outcomes for Hospitalized Patients in New York City. Sigel, Keith; Swartz, Talia; Golden, Eddye; Paranjpe, Ishan; Somani, Sulaiman; Richter, Felix; Freitas, Jessica K De; Miotto, Riccardo; Zhao, Shan; Polak, Paz; Mutetwa, Tinaye; Factor, Stephanie; Mehandru, Saurabh; Mullen, Michael; Cossarini, Francesca; Bottinger, Erwin; Fayad, Zahi; Merad, Miriam; Gnjatic, Sacha; Aberg, Judith; Charney, Alexander; Nadkarni, Girish; Glicksberg, Benjamin S in Clinical Infectious Diseases (2020).
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Sigel2020, author = {Sigel, Keith and Swartz, Talia and Golden, Eddye and Paranjpe, Ishan and Somani, Sulaiman and Richter, Felix and Freitas, Jessica K De and Miotto, Riccardo and Zhao, Shan and Polak, Paz and Mutetwa, Tinaye and Factor, Stephanie and Mehandru, Saurabh and Mullen, Michael and Cossarini, Francesca and Bottinger, Erwin and Fayad, Zahi and Merad, Miriam and Gnjatic, Sacha and Aberg, Judith and Charney, Alexander and Nadkarni, Girish and Glicksberg, Benjamin S}, journal = {Clinical Infectious Diseases}, keywords = {boettinger hpims fb-boettinger}, month = {jun}, publisher = {Oxford University Press ({OUP})}, title = {Coronavirus 2019 and People Living With Human Immunodeficiency Virus: Outcomes for Hospitalized Patients in New York City}, year = 2020 }
Characterization of Patients Who Return to Hospital Following Discharge from Hospitalization for COVID-19. Somani, Sulaiman S.; Richter, and Felix; Fuster, Valentin; Freitas, Jessica K. De; Naik, Nidhi; Sigel, Keith; Bottinger, Erwin P; Levin, Matthew A.; Fayad, Zahi; Just, Allan C.; Charney, Alexander W.; Zhao, Shan; Glicksberg, Benjamin S.; Lala, Anuradha; Nadkarni, Girish N. in Journal of General Internal Medicine (2020). 35(10) 2838–2844.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Somani2020, author = {Somani, Sulaiman S. and and Felix Richter and Fuster, Valentin and Freitas, Jessica K. De and Naik, Nidhi and Sigel, Keith and Bottinger, Erwin P and Levin, Matthew A. and Fayad, Zahi and Just, Allan C. and Charney, Alexander W. and Zhao, Shan and Glicksberg, Benjamin S. and Lala, Anuradha and Nadkarni, Girish N.}, journal = {Journal of General Internal Medicine}, keywords = {boettinger hpims fb-boettinger}, month = {aug}, number = 10, pages = {2838–2844}, publisher = {Springer Science and Business Media {LLC}}, title = {Characterization of Patients Who Return to Hospital Following Discharge from Hospitalization for {COVID}-19}, volume = 35, year = 2020 }
Data Science für Digitale Medizin. Fehr, J; Konigorski, S; Lippert, C D. Matusiewicz, M. Henningsen, J. Ehlers (eds.) (2020). (Vol. Digitale Medizin – Kompendium für Studium und Praxis)
[ BibTeX ] [ URL ]
 
@inbook{fehr2020science, author = {Fehr, J and Konigorski, S and Lippert, C}, editor = {Matusiewicz, D and Henningsen, M and Ehlers, J}, keywords = {myown}, publisher = {Medizinisch Wissenschaftliche Verlagsgesellschaft Berlin}, title = {Data Science für Digitale Medizin}, volume = {Digitale Medizin – Kompendium für Studium und Praxis}, year = 2020 }
Constrained expectation maximisation algorithm for estimating ARMA models in state space representation. Galka, Andreas; Moontaha, Sidratul; SIniatchkin, Siniatchkin in EURASIP Journal on Advances in Signal Processing 2020.1 (2020). 1–37.
[ BibTeX ] [ URL ]
 
@article{galka2020constrained, author = {Galka, Andreas and Moontaha, Sidratul and SIniatchkin, Siniatchkin}, journal = {EURASIP Journal on Advances in Signal Processing 2020.1}, keywords = {sidratulmoontaha}, pages = {1-37}, title = {Constrained expectation maximisation algorithm for estimating ARMA models in state space representation.}, year = 2020 }
The SARS-CoV-2 effective reproduction rate has a high correlation with a contact index derived from large-scale individual location data using GPS-enabled mobile phones in Germany Rüdiger, S; Konigorski, S; Edelman, J; Zernick, D; Lippert, C; Thieme, A (2020).
[ BibTeX ] [ URL ]
 
@preprint{noauthororeditor, author = {Rüdiger, S and Konigorski, S and Edelman, J and Zernick, D and Lippert, C and Thieme, A}, keywords = {myown}, title = {The SARS-CoV-2 effective reproduction rate has a high correlation with a contact index derived from large-scale individual location data using GPS-enabled mobile phones in Germany}, year = 2020 }
Latente Tuberkulose bei medizinischem Personal in Deutschland nach Auslandseinsatz. Meier, I; Schablon, A; Nienhaus, A; Konigorski, S in Pneumologie (2020). 74 1–7.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{meier2020latente, author = {Meier, I and Schablon, A and Nienhaus, A and Konigorski, S}, journal = {Pneumologie}, keywords = {myown}, pages = {1-7}, title = {Latente Tuberkulose bei medizinischem Personal in Deutschland nach Auslandseinsatz}, volume = 74, year = 2020 }
Outcomes of Patients on Maintenance Dialysis Hospitalized with COVID-19. Chan, Lili; Jaladanki, Suraj K.; Somani, Sulaiman; Paranjpe, Ishan; Kumar, Arvind; Zhao, Shan; Kaufman, Lewis; Leisman, Staci; Sharma, Shuchita; He, John Cijiang; Murphy, Barbara; Fayad, Zahi A.; Levin, Matthew A.; Bottinger, Erwin P.; Charney, Alexander W.; Glicksberg, Benjamin S.; Coca, Steven G.; Nadkarni, Girish N. in Clinical Journal of the American Society of Nephrology (2020). CJN.12360720.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Chan2020, author = {Chan, Lili and Jaladanki, Suraj K. and Somani, Sulaiman and Paranjpe, Ishan and Kumar, Arvind and Zhao, Shan and Kaufman, Lewis and Leisman, Staci and Sharma, Shuchita and He, John Cijiang and Murphy, Barbara and Fayad, Zahi A. and Levin, Matthew A. and Bottinger, Erwin P. and Charney, Alexander W. and Glicksberg, Benjamin S. and Coca, Steven G. and Nadkarni, Girish N.}, journal = {Clinical Journal of the American Society of Nephrology}, keywords = {boettinger hpims fb-boettinger}, month = {oct}, pages = {CJN.12360720}, publisher = {American Society of Nephrology ({ASN})}, title = {Outcomes of Patients on Maintenance Dialysis Hospitalized with {COVID}-19}, year = 2020 }
Good News: Wie Data Science dabei hilft, die Corona-Pandemie besser zu verstehen. Schapranow, Matthieu-P. in Portal Wissen: Das Forschungsmagazin der Universität Potsdam (2020). 9(2) 14–19.
[ BibTeX ] [ DOI ]
 
@article{schapranow2020science, author = {Schapranow, Matthieu-P.}, journal = {Portal Wissen: Das Forschungsmagazin der Universität Potsdam}, keywords = {myown}, month = {sep}, number = 2, pages = {14–19}, title = {Good News: Wie Data Science dabei hilft, die Corona-Pandemie besser zu verstehen}, volume = 9, year = 2020 }
Machine Learning to Predict Mortality and Critical Events in a Cohort of Patients With COVID-19 in New York City: Model Development and Validation. Vaid, Akhil; Somani, Sulaiman; Russak, Adam J; Freitas, Jessica K De; Chaudhry, Fayzan F; Paranjpe, Ishan; Johnson, Kipp W; Lee, Samuel J; Miotto, Riccardo; Richter, Felix; Zhao, Shan; Beckmann, Noam D; Naik, Nidhi; Kia, Arash; Timsina, Prem; Lala, Anuradha; Paranjpe, Manish; Golden, Eddye; Danieletto, Matteo; Singh, Manbir; Meyer, Dara; OtextquotesingleReilly, Paul F; Huckins, Laura; Kovatch, Patricia; Finkelstein, Joseph; Freeman, Robert M.; Argulian, Edgar; Kasarskis, Andrew; Percha, Bethany; Aberg, Judith A; Bagiella, Emilia; Horowitz, Carol R; Murphy, Barbara; Nestler, Eric J; Schadt, Eric E; Cho, Judy H; Cordon-Cardo, Carlos; Fuster, Valentin; Charney, Dennis S; Reich, David L; Bottinger, Erwin P; Levin, Matthew A; Narula, Jagat; Fayad, Zahi A; Just, Allan C; Charney, Alexander W; Nadkarni, Girish N; Glicksberg, Benjamin S in Journal of Medical Internet Research (2020). 22(11) e24018.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Vaid2020, author = {Vaid, Akhil and Somani, Sulaiman and Russak, Adam J and Freitas, Jessica K De and Chaudhry, Fayzan F and Paranjpe, Ishan and Johnson, Kipp W and Lee, Samuel J and Miotto, Riccardo and Richter, Felix and Zhao, Shan and Beckmann, Noam D and Naik, Nidhi and Kia, Arash and Timsina, Prem and Lala, Anuradha and Paranjpe, Manish and Golden, Eddye and Danieletto, Matteo and Singh, Manbir and Meyer, Dara and O{\textquotesingle}Reilly, Paul F and Huckins, Laura and Kovatch, Patricia and Finkelstein, Joseph and Freeman, Robert M. and Argulian, Edgar and Kasarskis, Andrew and Percha, Bethany and Aberg, Judith A and Bagiella, Emilia and Horowitz, Carol R and Murphy, Barbara and Nestler, Eric J and Schadt, Eric E and Cho, Judy H and Cordon-Cardo, Carlos and Fuster, Valentin and Charney, Dennis S and Reich, David L and Bottinger, Erwin P and Levin, Matthew A and Narula, Jagat and Fayad, Zahi A and Just, Allan C and Charney, Alexander W and Nadkarni, Girish N and Glicksberg, Benjamin S}, journal = {Journal of Medical Internet Research}, keywords = {boettinger hpims fb-boettinger}, month = {nov}, number = 11, pages = {e24018}, publisher = {{JMIR} Publications Inc.}, title = {Machine Learning to Predict Mortality and Critical Events in a Cohort of Patients With {COVID}-19 in New York City: Model Development and Validation}, volume = 22, year = 2020 }
Using Interpretability Approaches to Update Black-Box Clinical Prediction Models: an External Validation Study in Nephrology. da Cruz, Harry Freitas; Pfahringer, Boris; Martensen, Tom; Schneider, Frederic; Meyer, Alexander; Bottinger, Erwin; Schapranow, Matthieu-P. in Artificial Intelligence in Medicine (2020). 101982.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{daCruz2020, author = {da Cruz, Harry Freitas and Pfahringer, Boris and Martensen, Tom and Schneider, Frederic and Meyer, Alexander and Bottinger, Erwin and Schapranow, Matthieu-P.}, journal = {Artificial Intelligence in Medicine}, keywords = {boettinger fb-boettinger}, month = {nov}, pages = 101982, publisher = {Elsevier {BV}}, title = {Using Interpretability Approaches to Update Black-Box Clinical Prediction Models: an External Validation Study in Nephrology}, year = 2020 }
GGPONC: A Corpus of German Medical Text with Rich Metadata Based on Clinical Practice Guidelines. Borchert, Florian; Lohr, Christina; Modersohn, Luise; Langer, Thomas; Follmann, Markus; Sachs, Jan Philipp; Hahn, Udo; Schapranow, Matthieu-P. (2020). 38–48.
[ Abstract ] [ BibTeX ] [ URL ]
 
The lack of publicly accessible text corpora is a major obstacle for progress in natural language processing. For medical applications, unfortunately, all language communities other than English are low-resourced. In this work, we present GGPONC (German Guideline Program in Oncology NLP Corpus), a freely distributable German language corpus based on clinical practice guidelines for oncology. This corpus is one of the largest ever built from German medical documents. Unlike clinical documents, clinical guidelines do not contain any patient-related information and can therefore be used without data protection restrictions. Moreover, GGPONC is the first corpus for the German language covering diverse conditions in a large medical subfield and provides a variety of metadata, such as literature references and evidence levels. By applying and evaluating existing medical information extraction pipelines for German text, we are able to draw comparisons for the use of medical language to other corpora, medical and non-medical ones.
@inproceedings{borchert-etal-2020-ggponc, abstract = {The lack of publicly accessible text corpora is a major obstacle for progress in natural language processing. For medical applications, unfortunately, all language communities other than English are low-resourced. In this work, we present GGPONC (German Guideline Program in Oncology NLP Corpus), a freely distributable German language corpus based on clinical practice guidelines for oncology. This corpus is one of the largest ever built from German medical documents. Unlike clinical documents, clinical guidelines do not contain any patient-related information and can therefore be used without data protection restrictions. Moreover, GGPONC is the first corpus for the German language covering diverse conditions in a large medical subfield and provides a variety of metadata, such as literature references and evidence levels. By applying and evaluating existing medical information extraction pipelines for German text, we are able to draw comparisons for the use of medical language to other corpora, medical and non-medical ones.}, address = {Online}, author = {Borchert, Florian and Lohr, Christina and Modersohn, Luise and Langer, Thomas and Follmann, Markus and Sachs, Jan Philipp and Hahn, Udo and Schapranow, Matthieu-P.}, booktitle = {Proceedings of the 11th International Workshop on Health Text Mining and Information Analysis}, keywords = {nlp HiGHmed myown fb-boettinger}, month = {nov}, pages = {38–48}, publisher = {Association for Computational Linguistics}, title = {{GGPONC}: A Corpus of {G}erman Medical Text with Rich Metadata Based on Clinical Practice Guidelines}, year = 2020 }
#nCoVStats: Wie Data Science hilft die Coronavirus-Pandemie zu verstehen. Schapranow, Matthieu-P. in gesundhyte.de: Das Magazin für Digitale Gesundheit in Deutschland (2020). 13 34–37.
[ BibTeX ]
 
@article{schapranow2020ncovstats, author = {Schapranow, Matthieu-P.}, journal = {gesundhyte.de: Das Magazin für Digitale Gesundheit in Deutschland}, keywords = {myown}, month = {dec}, pages = {34–37}, title = {#nCoVStats: Wie Data Science hilft die Coronavirus-Pandemie zu verstehen}, volume = 13, year = 2020 }
"Herr Doktor, verstehen Sie mich?“: Wie lernende Systeme helfen medizinische Fachsprache zu verstehen und welche Rolle klinische Leitlinien dabei spielen. Borchert, Florian; Lohr, Christina; Modersohn, Luise; Hahn, Udo; Langer, Thomas; Wenzel, Gregor; Follmann, Markus; Schapranow, Matthieu-P. in gesundhyte.de: Das Magazin für Digitale Gesundheit in Deutschland (2020). 13 19–22.
[ BibTeX ]
 
@article{borchert2020doktor, author = {Borchert, Florian and Lohr, Christina and Modersohn, Luise and Hahn, Udo and Langer, Thomas and Wenzel, Gregor and Follmann, Markus and Schapranow, Matthieu-P.}, journal = {gesundhyte.de: Das Magazin für Digitale Gesundheit in Deutschland}, keywords = {HiGHmed myown}, month = {dec}, pages = {19–22}, title = {"Herr Doktor, verstehen Sie mich?“: Wie lernende Systeme helfen medizinische Fachsprache zu verstehen und welche Rolle klinische Leitlinien dabei spielen}, volume = 13, year = 2020 }
It is time to reality check the promises of machine learning-powered precision medicine. Wilkinson, Jack; Arnold, Kellyn F; Murray, Eleanor J; van Smeden, Maarten; Carr, Kareem; Sippy, Rachel; de Kamps, Marc; Beam, Andrew; Konigorski, Stefan; Lippert, Christoph; Gilthorpe, Mark S; Tennant, Peter WG in The Lancet Digital Health (2020).
[ BibTeX ] [ URL ] [ DOI ]
 
@article{noauthororeditor, author = {Wilkinson, Jack and Arnold, Kellyn F and Murray, Eleanor J and van Smeden, Maarten and Carr, Kareem and Sippy, Rachel and de Kamps, Marc and Beam, Andrew and Konigorski, Stefan and Lippert, Christoph and Gilthorpe, Mark S and Tennant, Peter WG}, journal = {The Lancet Digital Health}, keywords = {myown}, title = {It is time to reality check the promises of machine learning-powered precision medicine}, year = 2020 }
Evaluation of the Pose Tracking Performance of the Azure Kinect and Kinect v2 for Gait Analysis in Comparison with a Gold Standard: A Pilot Study. Albert, Justin; Owolabi, Victor; Gebel, Arnd; Brahms, Markus Clemens; Granacher, Urs; Arnrich, Bert in MDPI Sensors (2020). 20(18)
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
Gait analysis is an important tool for the early detection of neurological diseases and for the assessment of risk of falling in elderly people. The availability of low-cost camera hardware on the market today and recent advances in Machine Learning enable a wide range of clinical and health-related applications, such as patient monitoring or exercise recognition at home. In this study, we evaluated the motion tracking performance of the latest generation of the Microsoft Kinect camera, Azure Kinect, compared to its predecessor Kinect v2 in terms of treadmill walking usinggold standard Vicon multi-camera motion capturing system and the 39 marker Plug-in Gait model. Five young and healthy subjects walked on a treadmill at three different velocities while data were recorded simultaneously with all three camera systems. An easy-to-administer camera calibration method developed here was used to spatially align the 3D skeleton data from both Kinect cameras and the Vicon system. With this calibration, the spatial agreement of joint positions between the two Kinect cameras and the reference system was evaluated. In addition, we compared the accuracy of certain spatio-temporal gait parameters, i.e., step length, step time, step width, and stride time calculated from the Kinect data, with the gold standard system. Our results showed that the improved hardware and the motion tracking algorithm of the Azure Kinect camera led to a significantly higher accuracy of the spatial gait parameters than the predecessor Kinect v2, while no significant differences were found between the temporal parameters. Furthermore, we explain in detail how this experimental setup could be used to continuously monitor the progress during gait rehabilitation in older people.
@article{albert2020evaluation, abstract = {Gait analysis is an important tool for the early detection of neurological diseases and for the assessment of risk of falling in elderly people. The availability of low-cost camera hardware on the market today and recent advances in Machine Learning enable a wide range of clinical and health-related applications, such as patient monitoring or exercise recognition at home. In this study, we evaluated the motion tracking performance of the latest generation of the Microsoft Kinect camera, Azure Kinect, compared to its predecessor Kinect v2 in terms of treadmill walking usinggold standard Vicon multi-camera motion capturing system and the 39 marker Plug-in Gait model. Five young and healthy subjects walked on a treadmill at three different velocities while data were recorded simultaneously with all three camera systems. An easy-to-administer camera calibration method developed here was used to spatially align the 3D skeleton data from both Kinect cameras and the Vicon system. With this calibration, the spatial agreement of joint positions between the two Kinect cameras and the reference system was evaluated. In addition, we compared the accuracy of certain spatio-temporal gait parameters, i.e., step length, step time, step width, and stride time calculated from the Kinect data, with the gold standard system. Our results showed that the improved hardware and the motion tracking algorithm of the Azure Kinect camera led to a significantly higher accuracy of the spatial gait parameters than the predecessor Kinect v2, while no significant differences were found between the temporal parameters. Furthermore, we explain in detail how this experimental setup could be used to continuously monitor the progress during gait rehabilitation in older people.}, author = {Albert, Justin and Owolabi, Victor and Gebel, Arnd and Brahms, Markus Clemens and Granacher, Urs and Arnrich, Bert}, journal = {MDPI Sensors}, keywords = {justinalbert bertarnrich}, title = {Evaluation of the Pose Tracking Performance of the Azure Kinect and Kinect v2 for Gait Analysis in Comparison with a Gold Standard: A Pilot Study}, volume = {20(18)}, year = 2020 }
Literature Review on Transfer Learning for Human Activity Recognition Using Mobile and Wearable Devices with Environmental Technology. Hernandez, Netzahualcoyotl; Lundström, Jens; Favela, Jesus; McChesney, Ian; Arnrich, Bert in SN Computer Science (2020). 1(2) 66.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Hernandez2020, author = {Hernandez, Netzahualcoyotl and Lundstr{ö}m, Jens and Favela, Jesus and McChesney, Ian and Arnrich, Bert}, journal = {SN Computer Science}, keywords = {bertarnrich}, month = {feb}, number = 2, pages = 66, title = {Literature Review on Transfer Learning for Human Activity Recognition Using Mobile and Wearable Devices with Environmental Technology}, volume = 1, year = 2020 }
Directed Acyclic Graphs and causal thinking in clinical risk prediction modeling. Piccininni, Marco; Konigorski, Stefan; Rohmann, Jessica L; Kurth, Tobias in BMC Medical Research Methodology (2020). 20 179.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{noauthororeditor, author = {Piccininni, Marco and Konigorski, Stefan and Rohmann, Jessica L and Kurth, Tobias}, journal = {BMC Medical Research Methodology}, keywords = {myown}, pages = 179, title = {Directed Acyclic Graphs and causal thinking in clinical risk prediction modeling}, volume = 20, year = 2020 }
Clinical Characteristics of Hospitalized Covid-19 Patients in New York City. Paranjpe, Ishan; Russak, Adam; Freitas, Jessica K De; Lala, Anuradha; Miotto, Riccardo; Vaid, Akhil; Johnson, Kipp W; Danieletto, Matteo; Golden, Eddye; Meyer, Dara; Singh, Manbir; Somani, Sulaiman; Manna, Sayan; Nangia, Udit; Kapoor, Arjun; OtextquotesingleHagan, Ross; OtextquotesingleReilly, Paul F; Huckins, Laura M; Glowe, Patricia; Kia, Arash; Timsina, Prem; Freeman, Robert M; Levin, Matthew A; Jhang, Jeffrey; Firpo, Adolfo; Kovatch, Patricia; Finkelstein, Joseph; Aberg, Judith A; Bagiella, Emilia; Horowitz, Carol R; Murphy, Barbara; Fayad, Zahi A; Narula, Jagat; Nestler, Eric J; Fuster, Valentin; Cordon-Cardo, Carlos; Charney, Dennis S; Reich, David L; Just, Allan C; Bottinger, Erwin P; Charney, Alexander W; Glicksberg, Benjamin S; Nadkarni, Girish in medRxiv (2020). (I) Version 1 (April 23, 2020 – 03:18).
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
ABSTRACT Background: The coronavirus 2019 (Covid-19) pandemic is a global public health crisis, with over 1.6 million cases and 95,000 deaths worldwide. Data are needed regarding the clinical course of hospitalized patients, particularly in the United States. Methods Demographic, clinical, and outcomes data for patients admitted to five Mount Sinai Health System hospitals with confirmed Covid-19 between February 27 and April 2, 2020 were identified through institutional electronic health records. We conducted a descriptive study of patients who had in-hospital mortality or were discharged alive. Results A total of 2,199 patients with Covid-19 were hospitalized during the study period. As of April 2nd, 1,121 (51%) patients remained hospitalized, and 1,078 (49%) completed their hospital course. Of the latter, the overall mortality was 29%, and 36% required intensive care. The median age was 65 years overall and 75 years in those who died. Pre-existing conditions were present in 65% of those who died and 46% of those discharged. In those who died, the admission median lymphocyte percentage was 11.7%, D-dimer was 2.4 ug/ml, C-reactive protein was 162 mg/L, and procalcitonin was 0.44 ng/mL. In those discharged, the admission median lymphocyte percentage was 16.6%, D-dimer was 0.93 ug/ml, C-reactive protein was 79 mg/L, and procalcitonin was 0.09 ng/mL. Conclusions This is the largest and most diverse case series of hospitalized patients with Covid-19 in the United States to date. Requirement of intensive care and mortality were high. Patients who died typically had pre-existing conditions and severe perturbations in inflammatory markers.
@article{Paranjpe2020, abstract = {ABSTRACT Background: The coronavirus 2019 (Covid-19) pandemic is a global public health crisis, with over 1.6 million cases and 95,000 deaths worldwide. Data are needed regarding the clinical course of hospitalized patients, particularly in the United States. Methods Demographic, clinical, and outcomes data for patients admitted to five Mount Sinai Health System hospitals with confirmed Covid-19 between February 27 and April 2, 2020 were identified through institutional electronic health records. We conducted a descriptive study of patients who had in-hospital mortality or were discharged alive. Results A total of 2,199 patients with Covid-19 were hospitalized during the study period. As of April 2nd, 1,121 (51%) patients remained hospitalized, and 1,078 (49%) completed their hospital course. Of the latter, the overall mortality was 29%, and 36% required intensive care. The median age was 65 years overall and 75 years in those who died. Pre-existing conditions were present in 65% of those who died and 46% of those discharged. In those who died, the admission median lymphocyte percentage was 11.7%, D-dimer was 2.4 ug/ml, C-reactive protein was 162 mg/L, and procalcitonin was 0.44 ng/mL. In those discharged, the admission median lymphocyte percentage was 16.6%, D-dimer was 0.93 ug/ml, C-reactive protein was 79 mg/L, and procalcitonin was 0.09 ng/mL. Conclusions This is the largest and most diverse case series of hospitalized patients with Covid-19 in the United States to date. Requirement of intensive care and mortality were high. Patients who died typically had pre-existing conditions and severe perturbations in inflammatory markers.}, author = {Paranjpe, Ishan and Russak, Adam and Freitas, Jessica K De and Lala, Anuradha and Miotto, Riccardo and Vaid, Akhil and Johnson, Kipp W and Danieletto, Matteo and Golden, Eddye and Meyer, Dara and Singh, Manbir and Somani, Sulaiman and Manna, Sayan and Nangia, Udit and Kapoor, Arjun and O{\textquotesingle}Hagan, Ross and O{\textquotesingle}Reilly, Paul F and Huckins, Laura M and Glowe, Patricia and Kia, Arash and Timsina, Prem and Freeman, Robert M and Levin, Matthew A and Jhang, Jeffrey and Firpo, Adolfo and Kovatch, Patricia and Finkelstein, Joseph and Aberg, Judith A and Bagiella, Emilia and Horowitz, Carol R and Murphy, Barbara and Fayad, Zahi A and Narula, Jagat and Nestler, Eric J and Fuster, Valentin and Cordon-Cardo, Carlos and Charney, Dennis S and Reich, David L and Just, Allan C and Bottinger, Erwin P and Charney, Alexander W and Glicksberg, Benjamin S and Nadkarni, Girish}, journal = {medRxiv}, keywords = {boettinger hpims fb-boettinger}, month = {April 2020}, number = {I}, pages = {Version 1 (April 23, 2020 - 03:18)}, publisher = {Cold Spring Harbor Laboratory}, title = {Clinical Characteristics of Hospitalized Covid-19 Patients in New York City}, year = 2020 }
Eatomics: Shiny exploration of quantitative proteomics data. Kraus, Milena; Mathew Stephen, Mariet; Schapranow, Matthieu-P in Journal of Proteome Research, (S. Weintraub, ed.) (2020).
[ BibTeX ] [ URL ] [ DOI ]
 
@article{kraus2020eatomics, author = {Kraus, Milena and Mathew Stephen, Mariet and Schapranow, Matthieu-P}, editor = {Weintraub, Susan}, journal = {Journal of Proteome Research}, keywords = {myown fb-boettinger smart}, publisher = {American Chemical Society}, title = {Eatomics: Shiny exploration of quantitative proteomics data}, year = 2020 }
Economic impact of clinical decision support interventions based on electronic health records. Lewkowicz, Daniel; Wohlbrandt, Attila; Boettinger, Erwin in BMC Health Services Research (2020). 20, 871(1)
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Lewkowicz2020, author = {Lewkowicz, Daniel and Wohlbrandt, Attila and Boettinger, Erwin}, journal = {BMC Health Services Research}, keywords = {myown bottinger bottinger-not-dhc dhc}, month = {09}, number = 1, publisher = {Springer Science and Business Media {LLC}}, title = {Economic impact of clinical decision support interventions based on electronic health records.}, volume = {20, 871}, year = 2020 }
HYPE: Predicting Blood Pressure from Photoplethysmograms in a Hypertensive Population. Sasso, Ariane Morassi; Datta, Suparno; Jeitler, Michael; Steckhan, Nico; Kessler, Christian S; Michalsen, Andreas; Arnrich, Bert; Boettinger, Erwin (2020). 325–335.
[ BibTeX ]
 
@inproceedings{sasso2020hype, author = {Sasso, Ariane Morassi and Datta, Suparno and Jeitler, Michael and Steckhan, Nico and Kessler, Christian S and Michalsen, Andreas and Arnrich, Bert and Boettinger, Erwin}, booktitle = {International Conference on Artificial Intelligence in Medicine}, keywords = {machinelearning digitalhealth fb-boettinger dhc}, organization = {Springer}, pages = {325–335}, title = {HYPE: Predicting Blood Pressure from Photoplethysmograms in a Hypertensive Population}, year = 2020 }
Association of APOL1 Risk Genotype and Air Pollution for Kidney Disease. Paranjpe, Ishan; Chaudhary, Kumardeep; Paranjpe, Manish; O’Hagan, Ross; Manna, Sayan; Jaladanki, Suraj; Kapoor, Arjun; Horowitz, Carol; DeFelice, Nicholas; Cooper, Richard; Glicksberg, Benjamin; Bottinger, Erwin P.; Just, Allan C.; Nadkarni, Girish N. in Clinical Journal of the American Society of Nephrology (2020). 15(3) 401–403.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Paranjpe2020, author = {Paranjpe, Ishan and Chaudhary, Kumardeep and Paranjpe, Manish and O'Hagan, Ross and Manna, Sayan and Jaladanki, Suraj and Kapoor, Arjun and Horowitz, Carol and DeFelice, Nicholas and Cooper, Richard and Glicksberg, Benjamin and Bottinger, Erwin P. and Just, Allan C. and Nadkarni, Girish N.}, journal = {Clinical Journal of the American Society of Nephrology}, keywords = {boettinger hpims fb-boettinger}, month = {feb}, number = 3, pages = {401–403}, publisher = {American Society of Nephrology ({ASN})}, title = {Association of {APOL}1 Risk Genotype and Air Pollution for Kidney Disease}, volume = 15, year = 2020 }
Towards the automatic detection of social biomarkers in autism spectrum disorder: introducing the simulated interaction task (SIT). Drimalla, Hanna; Scheffer, Tobias; Landwehr, Niels; Baskow, Irina; Roepke, Stefan; Behnia, Behnoush; Dziobek, Isabel in npj digital medicine (2020). 3(25)
[ BibTeX ] [ DOI ]
 
@article{drimalla2020towards, author = {Drimalla, Hanna and Scheffer, Tobias and Landwehr, Niels and Baskow, Irina and Roepke, Stefan and Behnia, Behnoush and Dziobek, Isabel}, journal = {npj digital medicine}, keywords = {myown face empathy machine learning fb-boettinger}, number = 25, title = {Towards the automatic detection of social biomarkers in autism spectrum disorder: introducing the simulated interaction task (SIT)}, volume = 3, year = 2020 }
Federated Learning in a Medical Context: A Systematic Literature Review. Pfitzner, Bjarne; Steckhan, Nico; Arnrich, Bert in ACM Transactions on Internet Technology (TOIT) Special Issue on Security and Privacy of Medical Data for Smart Healthcare (2020).
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
Data privacy is a very important issue. Especially in fields like medicine, it is paramount to abide by the existing privacy regulations to preserve patients’ anonymity. On the other hand, data is required for research and training machine learning models that could help gain insight into complex correlations or personalised treatments that may otherwise stay undiscovered. Those models generally scale with the amount of data available, but the current situation often prohibits building large databases across sites. So it would be beneficial to be able to combine similar or related data from different sites all over the world while still preserving data privacy. Federated learning has been proposed as a solution for this, because it relies on the sharing of machine learning models, instead of the raw data itself. That means private data never leaves the site or device it was collected on. Federated learning is an emerging research area and many domains have been identified for the application of those methods. This systematic literature review provides an extensive look at the concept of and research into federated learning and its applicability for confidential healthcare datasets.
@article{pfitzner2020federated, abstract = {Data privacy is a very important issue. Especially in fields like medicine, it is paramount to abide by the existing privacy regulations to preserve patients’ anonymity. On the other hand, data is required for research and training machine learning models that could help gain insight into complex correlations or personalised treatments that may otherwise stay undiscovered. Those models generally scale with the amount of data available, but the current situation often prohibits building large databases across sites. So it would be beneficial to be able to combine similar or related data from different sites all over the world while still preserving data privacy. Federated learning has been proposed as a solution for this, because it relies on the sharing of machine learning models, instead of the raw data itself. That means private data never leaves the site or device it was collected on. Federated learning is an emerging research area and many domains have been identified for the application of those methods. This systematic literature review provides an extensive look at the concept of and research into federated learning and its applicability for confidential healthcare datasets.}, author = {Pfitzner, Bjarne and Steckhan, Nico and Arnrich, Bert}, journal = {ACM Transactions on Internet Technology (TOIT) Special Issue on Security and Privacy of Medical Data for Smart Healthcare}, keywords = {nicosteckhan bertarnrich bjarnepfitzner}, title = {Federated Learning in a Medical Context: A Systematic Literature Review}, year = 2020 }
The Influence of Reward on Facial Mimicry: No Evidence for a Significant Effect of Oxytocin. Trilla, Irene; Drimalla, Hanna; Bajbouj, Malek; Dziobek, Isabel in Frontiers in Behavioural Neuroscience (2020).
[ BibTeX ] [ URL ] [ DOI ]
 
@article{trilla2020influence, author = {Trilla, Irene and Drimalla, Hanna and Bajbouj, Malek and Dziobek, Isabel}, journal = {Frontiers in Behavioural Neuroscience}, keywords = {myown}, title = {The Influence of Reward on Facial Mimicry: No Evidence for a Significant Effect of Oxytocin}, year = 2020 }
Event Log Generation in a Health System: A Case Study. Remy, Simon; Pufahl, Luise; Sachs, Jan Philipp; Böttinger, Erwin; Weske, Mathias in Lecture Notes in Computer Science (2020). 505–522.
[ BibTeX ] [ URL ] [ DOI ]
 
@incollection{Remy2020, author = {Remy, Simon and Pufahl, Luise and Sachs, Jan Philipp and B{ö}ttinger, Erwin and Weske, Mathias}, booktitle = {Lecture Notes in Computer Science}, keywords = {boettinger hpims fb-boettinger}, pages = {505–522}, publisher = {Springer International Publishing}, title = {Event Log Generation in a Health System: A Case Study}, year = 2020 }
AKI in Hospitalized Patients with COVID-19. Chan, Lili; Chaudhary, Kumardeep; Saha, Aparna; Chauhan, Kinsuk; Vaid, Akhil; Zhao, Shan; Paranjpe, Ishan; Somani, Sulaiman; Richter, Felix; Miotto, Riccardo; Lala, Anuradha; Kia, Arash; Timsina, Prem; Li, Li; Freeman, Robert; Chen, Rong; Narula, Jagat; Just, Allan C.; Horowitz, Carol; Fayad, Zahi; Cordon-Cardo, Carlos; Schadt, Eric; Levin, Matthew A.; Reich, David L.; Fuster, Valentin; Murphy, Barbara; He, John C.; Charney, Alexander W.; Böttinger, Erwin P.; Glicksberg, Benjamin S.; Coca, Steven G.; Nadkarni, Girish N.; Li, Li in Journal of the American Society of Nephrology (2020). ASN.2020050615.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Chan2020, author = {Chan, Lili and Chaudhary, Kumardeep and Saha, Aparna and Chauhan, Kinsuk and Vaid, Akhil and Zhao, Shan and Paranjpe, Ishan and Somani, Sulaiman and Richter, Felix and Miotto, Riccardo and Lala, Anuradha and Kia, Arash and Timsina, Prem and Li, Li and Freeman, Robert and Chen, Rong and Narula, Jagat and Just, Allan C. and Horowitz, Carol and Fayad, Zahi and Cordon-Cardo, Carlos and Schadt, Eric and Levin, Matthew A. and Reich, David L. and Fuster, Valentin and Murphy, Barbara and He, John C. and Charney, Alexander W. and Böttinger, Erwin P. and Glicksberg, Benjamin S. and Coca, Steven G. and Nadkarni, Girish N. and Li, Li}, journal = {Journal of the American Society of Nephrology}, keywords = {boettinger hpims fb-boettinger}, month = {sep}, pages = {ASN.2020050615}, publisher = {American Society of Nephrology ({ASN})}, title = {{AKI} in Hospitalized Patients with {COVID}-19}, year = 2020 }
Genetic Studies of Leptin Concentrations Implicate Leptin in the Regulation of Early Adiposity. Yaghootkar, Hanieh; Zhang, Yiying; Spracklen, Cassandra N; Karaderi, Tugce; Huang, Lam Opal; Bradfield, Jonathan; Schurmann, Claudia; Fine, Rebecca S; Preuss, Michael H; Kutalik, Zoltan; Wittemans, Laura Bl; Lu, Yingchang; Metz, Sophia; Willems, Sara M; Li-Gao, Ruifang; Grarup, Niels; Wang, Shuai; Molnos, Sophie; Sandoval-Zárate, América A; Nalls, Mike A; Lange, Leslie A; Haesser, Jeffrey; Guo, Xiuqing; Lyytikäinen, Leo-Pekka; Feitosa, Mary F; Sitlani, Colleen M; Venturini, Cristina; Mahajan, Anubha; Kacprowski, Tim; Wang, Carol A; Chasman, Daniel I; Amin, Najaf; Broer, Linda; Robertson, Neil; Young, Kristin L; Allison, Matthew; Auer, Paul L; Blüher, Matthias; Borja, Judith B; Bork-Jensen, Jette; Carrasquilla, Germán D; Christofidou, Paraskevi; Demirkan, Ayse; Doege, Claudia A; Garcia, Melissa E; Graff, Mariaelisa; Guo, Kaiying; Hakonarson, Hakon; Hong, Jaeyoung; Ida Chen, Yii-Der; Jackson, Rebecca; Jakupović, Hermina; Jousilahti, Pekka; Justice, Anne E; Kähönen, Mika; Kizer, Jorge R; Kriebel, Jennifer; LeDuc, Charles A; Li, Jin; Lind, Lars; Luan, Jian’an; Mackey, David; Mangino, Massimo; Männistö, Satu; Martin Carli, Jayne F; Medina-Gomez, Carolina; Mook-Kanamori, Dennis O; Morris, Andrew P; de Mutsert, Renée; Nauck, Matthias; Nedeljkovic, Ivana; Pennell, Craig E; Pradhan, Arund D; Psaty, Bruce M; Raitakari, Olli T; Scott, Robert A; Skaaby, Tea; Strauch, Konstantin; Taylor, Kent D; Teumer, Alexander; Uitterlinden, Andre G; Wu, Ying; Yao, Jie; Walker, Mark; North, Kari E; Kovacs, Peter; Ikram, M Arfan; van Duijn, Cornelia M; Ridker, Paul M; Lye, Stephen; Homuth, Georg; Ingelsson, Erik; Spector, Tim D; McKnight, Barbara; Province, Michael A; Lehtimäki, Terho; Adair, Linda S; Rotter, Jerome I; Reiner, Alexander P; Wilson, James G; Harris, Tamara B; Ripatti, Samuli; Grallert, Harald; Meigs, James B; Salomaa, Veikko; Hansen, Torben; Willems van Dijk, Ko; Wareham, Nicholas J; Grant, Struan Fa; Langenberg, Claudia; Frayling, Timothy M; Lindgren, Cecilia M; Mohlke, Karen L; Leibel, Rudolph L; Loos, Ruth Jf; Kilpeläinen, Tuomas O in Diabetes (2020).
[ BibTeX ] [ URL ] [ DOI ]
 
@article{noauthororeditor2020genetic, author = {Yaghootkar, Hanieh and Zhang, Yiying and Spracklen, Cassandra N and Karaderi, Tugce and Huang, Lam Opal and Bradfield, Jonathan and Schurmann, Claudia and Fine, Rebecca S and Preuss, Michael H and Kutalik, Zoltan and Wittemans, Laura Bl and Lu, Yingchang and Metz, Sophia and Willems, Sara M and Li-Gao, Ruifang and Grarup, Niels and Wang, Shuai and Molnos, Sophie and Sandoval-Zárate, América A and Nalls, Mike A and Lange, Leslie A and Haesser, Jeffrey and Guo, Xiuqing and Lyytikäinen, Leo-Pekka and Feitosa, Mary F and Sitlani, Colleen M and Venturini, Cristina and Mahajan, Anubha and Kacprowski, Tim and Wang, Carol A and Chasman, Daniel I and Amin, Najaf and Broer, Linda and Robertson, Neil and Young, Kristin L and Allison, Matthew and Auer, Paul L and Blüher, Matthias and Borja, Judith B and Bork-Jensen, Jette and Carrasquilla, Germán D and Christofidou, Paraskevi and Demirkan, Ayse and Doege, Claudia A and Garcia, Melissa E and Graff, Mariaelisa and Guo, Kaiying and Hakonarson, Hakon and Hong, Jaeyoung and Ida Chen, Yii-Der and Jackson, Rebecca and Jakupović, Hermina and Jousilahti, Pekka and Justice, Anne E and Kähönen, Mika and Kizer, Jorge R and Kriebel, Jennifer and LeDuc, Charles A and Li, Jin and Lind, Lars and Luan, Jian'an and Mackey, David and Mangino, Massimo and Männistö, Satu and Martin Carli, Jayne F and Medina-Gomez, Carolina and Mook-Kanamori, Dennis O and Morris, Andrew P and de Mutsert, Renée and Nauck, Matthias and Nedeljkovic, Ivana and Pennell, Craig E and Pradhan, Arund D and Psaty, Bruce M and Raitakari, Olli T and Scott, Robert A and Skaaby, Tea and Strauch, Konstantin and Taylor, Kent D and Teumer, Alexander and Uitterlinden, Andre G and Wu, Ying and Yao, Jie and Walker, Mark and North, Kari E and Kovacs, Peter and Ikram, M Arfan and van Duijn, Cornelia M and Ridker, Paul M and Lye, Stephen and Homuth, Georg and Ingelsson, Erik and Spector, Tim D and McKnight, Barbara and Province, Michael A and Lehtimäki, Terho and Adair, Linda S and Rotter, Jerome I and Reiner, Alexander P and Wilson, James G and Harris, Tamara B and Ripatti, Samuli and Grallert, Harald and Meigs, James B and Salomaa, Veikko and Hansen, Torben and Willems van Dijk, Ko and Wareham, Nicholas J and Grant, Struan Fa and Langenberg, Claudia and Frayling, Timothy M and Lindgren, Cecilia M and Mohlke, Karen L and Leibel, Rudolph L and Loos, Ruth Jf and Kilpeläinen, Tuomas O}, journal = {Diabetes}, keywords = {myown cs_prior_hpi}, title = {Genetic Studies of Leptin Concentrations Implicate Leptin in the Regulation of Early Adiposity}, year = 2020 }
Proteomic analysis reveals upregulation of ACE2, the putative SARS-CoV-2 receptor in pressure- but not volume-overloaded human hearts. Stegbauer, Johannes Stegbauer; Kraus, Milena; Nordmeyer, Sarah; Kirchner, Marieluise; Ziehm, Matthias Ziehm; Dommisch, Henrik; Kelle, Sebastian; Kelm, Marcus; Baczko, Istvan; Landmesser, Ulf; Tschope, Carsten; Knosalla, Christoph; Falcke, Martin; Schapranow, Matthieu-P.; Regitz-Zagrosek, Vera; Mertins, Philipp; Kühne, Titus in Hypertension (2020).
[ BibTeX ] [ DOI ]
 
@article{stegbauer2020proteomic, author = {Stegbauer, Johannes Stegbauer and Kraus, Milena and Nordmeyer, Sarah and Kirchner, Marieluise and Ziehm, Matthias Ziehm and Dommisch, Henrik and Kelle, Sebastian and Kelm, Marcus and Baczko, Istvan and Landmesser, Ulf and Tschope, Carsten and Knosalla, Christoph and Falcke, Martin and Schapranow, Matthieu-P. and Regitz-Zagrosek, Vera and Mertins, Philipp and Kühne, Titus}, journal = {Hypertension}, keywords = {myown}, title = {Proteomic analysis reveals upregulation of ACE2, the putative SARS-CoV-2 receptor in pressure- but not volume-overloaded human hearts}, year = 2020 }
Exome sequencing and characterization of 49,960 individuals in the UK Biobank. Van Hout, Cristopher V; Tachmazidou, Ioanna; Backman, Joshua D; Hoffman, Joshua D; Liu, Daren; Pandey, Ashutosh K; Gonzaga-Jauregui, Claudia; Khalid, Shareef; Ye, Bin; Banerjee, Nilanjana; Li, Alexander H; O’Dushlaine, Colm; Marcketta, Anthony; Staples, Jeffrey; Schurmann, Claudia; Hawes, Alicia; Maxwell, Evan; Barnard, Leland; Lopez, Alexander; Penn, John; Habegger, Lukas; Blumenfeld, Andrew L; Bai, Xiaodong; O’Keeffe, Sean; Yadav, Ashish; Praveen, Kavita; Jones, Marcus; Salerno, William J; Chung, Wendy K; Surakka, Ida; Willer, Cristen J; Hveem, Kristian; Leader, Joseph B; Carey, David J; Ledbetter, David H; Cardon, Lon; Yancopoulos, George D; Economides, Aris; Coppola, Giovanni; Shuldiner, Alan R; Balasubramanian, Suganthi; Cantor, Michael; Nelson, Matthew R; Whittaker, John; Reid, Jeffrey G; Marchini, Jonathan; Overton, John D; Scott, Robert A; Abecasis, Gonçalo R; Yerges-Armstrong, Laura; Baras, Aris in Nature (2020).
[ Abstract ] [ BibTeX ] [ DOI ]
 
The UK Biobank is a prospective study of 502,543 individuals, combining extensive phenotypic and genotypic data with streamlined access for researchers around the world(1). Here we describe the release of exome-sequence data for the first 49,960 study participants, revealing approximately 4 million coding variants (of which around 98.6\% have a frequency of less than 1\%). The data include 198,269 autosomal predicted loss-of-function (LOF) variants, a more than 14-fold increase compared to the imputed sequence. Nearly all genes (more than 97\%) had at least one carrier with a LOF variant, and most genes (more than 69\%) had at least ten carriers with a LOF variant. We illustrate the power of characterizing LOF variants in this population through association analyses across 1,730 phenotypes. In addition to replicating established associations, we found novel LOF variants with large effects on disease traits, including PIEZO1 on varicose veins, COL6A1 on corneal resistance, MEPE on bone density, and IQGAP2 and GMPR on blood cell traits. We further demonstrate the value of exome sequencing by surveying the prevalence of pathogenic variants of clinical importance, and show that 2% of this population has a medically actionable variant. Furthermore, we characterize the penetrance of cancer in carriers of pathogenic BRCA1 and BRCA2 variants. Exome sequences from the first 49,960 participants highlight the promise of genome sequencing in large population-based studies and are now accessible to the scientific community.
@article{VanHout2020, abstract = {The UK Biobank is a prospective study of 502,543 individuals, combining extensive phenotypic and genotypic data with streamlined access for researchers around the world(1). Here we describe the release of exome-sequence data for the first 49,960 study participants, revealing approximately 4 million coding variants (of which around 98.6{\%} have a frequency of less than 1{\%}). The data include 198,269 autosomal predicted loss-of-function (LOF) variants, a more than 14-fold increase compared to the imputed sequence. Nearly all genes (more than 97{\%}) had at least one carrier with a LOF variant, and most genes (more than 69{\%}) had at least ten carriers with a LOF variant. We illustrate the power of characterizing LOF variants in this population through association analyses across 1,730 phenotypes. In addition to replicating established associations, we found novel LOF variants with large effects on disease traits, including PIEZO1 on varicose veins, COL6A1 on corneal resistance, MEPE on bone density, and IQGAP2 and GMPR on blood cell traits. We further demonstrate the value of exome sequencing by surveying the prevalence of pathogenic variants of clinical importance, and show that 2{\%} of this population has a medically actionable variant. Furthermore, we characterize the penetrance of cancer in carriers of pathogenic BRCA1 and BRCA2 variants. Exome sequences from the first 49,960 participants highlight the promise of genome sequencing in large population-based studies and are now accessible to the scientific community.}, author = {{Van Hout}, Cristopher V and Tachmazidou, Ioanna and Backman, Joshua D and Hoffman, Joshua D and Liu, Daren and Pandey, Ashutosh K and Gonzaga-Jauregui, Claudia and Khalid, Shareef and Ye, Bin and Banerjee, Nilanjana and Li, Alexander H and O'Dushlaine, Colm and Marcketta, Anthony and Staples, Jeffrey and Schurmann, Claudia and Hawes, Alicia and Maxwell, Evan and Barnard, Leland and Lopez, Alexander and Penn, John and Habegger, Lukas and Blumenfeld, Andrew L and Bai, Xiaodong and O'Keeffe, Sean and Yadav, Ashish and Praveen, Kavita and Jones, Marcus and Salerno, William J and Chung, Wendy K and Surakka, Ida and Willer, Cristen J and Hveem, Kristian and Leader, Joseph B and Carey, David J and Ledbetter, David H and Cardon, Lon and Yancopoulos, George D and Economides, Aris and Coppola, Giovanni and Shuldiner, Alan R and Balasubramanian, Suganthi and Cantor, Michael and Nelson, Matthew R and Whittaker, John and Reid, Jeffrey G and Marchini, Jonathan and Overton, John D and Scott, Robert A and Abecasis, Gonçalo R and Yerges-Armstrong, Laura and Baras, Aris}, institution = {Geisinger-Regeneron DiscovEHR Collaboration}, journal = {Nature}, keywords = {myown cs_prior_hpi}, month = {oct}, title = {{Exome sequencing and characterization of 49,960 individuals in the UK Biobank.}}, year = 2020 }
How We Found Our IMU: Guidelines to IMU Selection and a Comparison of Seven IMUs for Pervasive Healthcare Applications. Zhou, Lin; Fischer, Eric; Tunca, Can; Brahms, Clemens Markus; Ersoy, Cem; Granacher, Urs; Arnrich, Bert in Sensors (2020).
[ BibTeX ] [ URL ] [ DOI ]
 
@article{zhou2020found, author = {Zhou, Lin and Fischer, Eric and Tunca, Can and Brahms, Clemens Markus and Ersoy, Cem and Granacher, Urs and Arnrich, Bert}, journal = {Sensors}, keywords = {linzhou bertarnrich}, title = {How We Found Our IMU: Guidelines to IMU Selection and a Comparison of Seven IMUs for Pervasive Healthcare Applications}, year = 2020 }

2019

A Machine Learning Approach for Non-Invasive Diagnosis of Metabolic Syndrome. Datta, Suparno; Schraplau, Anne; da Cruz, Harry Freitas; Sachs, Jan Philipp; Mayer, Frank; Böttinger, Erwin (2019). 933–940.
[ BibTeX ]
 
@inproceedings{datta2019machine, author = {Datta, Suparno and Schraplau, Anne and da Cruz, Harry Freitas and Sachs, Jan Philipp and Mayer, Frank and B{ö}ttinger, Erwin}, booktitle = {2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)}, keywords = {myown hpims machinelearning digitalhealth fb-boettinger dhc}, organization = {IEEE}, pages = {933–940}, title = {A Machine Learning Approach for Non-Invasive Diagnosis of Metabolic Syndrome}, year = 2019 }
Unobtrusive Measurement of Blood Pressure During Lifestyle Interventions. Morassi Sasso, Ariane; Datta, Suparno; Pfitzner, Bjarne; Zhou, Lin; Steckhan, Nico; Boettinger, Erwin; Arnrich, Bert (2019).
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
Hypertension is one of the most prevalent chronic diseases worldwide. Early diagnosis of this condition can prevent the incidence of stroke and also, cardiovascular diseases (CVDs) such as myocardial infarction and heart failure. Lifestyle interventions, such as intermittent fasting (IF), aim to lower blood pressure (BP) levels and increase the health of patients with cardiometabolic conditions. However, for monitoring BP, we still rely on a cuff that slows the �ow of blood, which is both uncomfortable and makes continuous monitoring implausible. Recent research has shown that BP can be estimated using comfortable sensors such as the photoplethysmography (PPG) and the electrocardiography (ECG). Features that can be used for the estimation of BP are systolic upstroke time (SUT) and diastolic time (DT) extracted from the PPG signal, and pulse arrival and transit time (PAT/PTT) derived from the combination of ECG and PPG signals. In this paper we present: (1) a study design to collect continuous physiological signals, before and after a 7-days intermittent fasting (IF) intervention from both cardiometabolic and non-hypertensive patients using wearable devices and (2) initial results for predicting continuous blood pressure from the PPG and ECG signals using statistical and machine learning methods.
@inproceedings{MorassiSasso2019, abstract = {Hypertension is one of the most prevalent chronic diseases worldwide. Early diagnosis of this condition can prevent the incidence of stroke and also, cardiovascular diseases (CVDs) such as myocardial infarction and heart failure. Lifestyle interventions, such as intermittent fasting (IF), aim to lower blood pressure (BP) levels and increase the health of patients with cardiometabolic conditions. However, for monitoring BP, we still rely on a cuff that slows the �ow of blood, which is both uncomfortable and makes continuous monitoring implausible. Recent research has shown that BP can be estimated using comfortable sensors such as the photoplethysmography (PPG) and the electrocardiography (ECG). Features that can be used for the estimation of BP are systolic upstroke time (SUT) and diastolic time (DT) extracted from the PPG signal, and pulse arrival and transit time (PAT/PTT) derived from the combination of ECG and PPG signals. In this paper we present: (1) a study design to collect continuous physiological signals, before and after a 7-days intermittent fasting (IF) intervention from both cardiometabolic and non-hypertensive patients using wearable devices and (2) initial results for predicting continuous blood pressure from the PPG and ECG signals using statistical and machine learning methods.}, address = {Trento}, author = {Morassi Sasso, Ariane and Datta, Suparno and Pfitzner, Bjarne and Zhou, Lin and Steckhan, Nico and Boettinger, Erwin and Arnrich, Bert}, booktitle = {Proceedings of the 13th EAI International Conference on Pervasive Computing Technologies for Healthcare - Demos and Posters}, keywords = {linzhou nicosteckhan bertarnrich bjarnepfitzner}, publisher = {EAI}, title = {Unobtrusive Measurement of Blood Pressure During Lifestyle Interventions}, year = 2019 }
An Information and Communication Platform Supporting Analytics for Elderly Care. Konak, Orhan; Freitas Da Cruz, Harry; Thiele, Marvin; Golla, David; Schapranow, Matthieu-P. (2019).
[ BibTeX ]
 
@inproceedings{konak2019information, author = {Konak, Orhan and Freitas Da Cruz, Harry and Thiele, Marvin and Golla, David and Schapranow, Matthieu-P.}, booktitle = {5th International Conference on Information for Ageing Well, Communication Technologies e Health}, keywords = {orhankonak}, title = {An Information and Communication Platform Supporting Analytics for Elderly Care}, year = 2019 }
MORPHER – A Platform to Support Modeling of Outcome and Risk Prediction in Health Research. Freitas da Cruz, Harry; Bergner, Benjamin; Konak, Orhan; Schneider, Frederic; Bode, Philipp; Lempert, Conrad; Schapranow, Matthieu-P. (2019).
[ BibTeX ]
 
@conference{freitasdacruz2019morpher, author = {Freitas da Cruz, Harry and Bergner, Benjamin and Konak, Orhan and Schneider, Frederic and Bode, Philipp and Lempert, Conrad and Schapranow, Matthieu-P.}, booktitle = {Proceedings of the 19th IEEE International Conference on Bioinformatics and Biomedicine}, keywords = {orhankonak}, title = {MORPHER – A Platform to Support Modeling of Outcome and Risk Prediction in Health Research}, year = 2019 }
Bewertung von Therapieeffekten bei Epilepsie: Eine vergleichende Analyse zwischen Cox-Stuart-Berechnung und Zustandsraum-Modellierung Scharlach, Sascha; Moontaha, Sirdatul; von Spiczak, Sarah; Stephani, Ulrich; Siniatchkin, Michael; May, Theodor; Galka, Andreas; Meurer, Thomas (2019).
[ BibTeX ] [ URL ]
 
@presentation{scharlach2019bewertung, author = {Scharlach, Sascha and Moontaha, Sirdatul and von Spiczak, Sarah and Stephani, Ulrich and Siniatchkin, Michael and May, Theodor and Galka, Andreas and Meurer, Thomas}, journal = {11. Gemeinsame Jahrestagung der Deutschen und Österreichischen Gesellschaft für Epileptologie sowie der Schweizerischen Epilepsie-Liga}, keywords = {prior-hpi sidratulmoontaha}, title = {Bewertung von Therapieeffekten bei Epilepsie: Eine vergleichende Analyse zwischen Cox-Stuart-Berechnung und Zustandsraum-Modellierung}, year = 2019 }
Association of dietary intake of milk and dairy products with blood concentrations of insulin-like growth factor 1 (IGF-1) in Bavarian adults. Romo Ventura, E; Konigorski, S; Rohrmann, S; Schneider, H; Stalla, GK; Pischon, T; Linseisen, J; Nimptsch, K in European Journal of Nutrition (2019). 59 1413–1420.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{romoventura2019dietary, author = {Romo Ventura, E and Konigorski, S and Rohrmann, S and Schneider, H and Stalla, GK and Pischon, T and Linseisen, J and Nimptsch, K}, journal = {European Journal of Nutrition}, keywords = {myown}, pages = {1413–1420}, title = {Association of dietary intake of milk and dairy products with blood concentrations of insulin-like growth factor 1 (IGF-1) in Bavarian adults}, volume = 59, year = 2019 }
Integrative Network Analysis Of Microbiome-Immune Axis In Metabolic Syndrome Patients During A Fasting Intervention. Avery, Ellen G; Balogh, András; Bartolomaeus, Hendrik; Löber, Ulrike; Steckhan, Nico; Markó, Lajos; Wilck, Nicola; Hamad, Ibrahim; Šušnjar, Urša; Mähler, Anja; Hohmann, Christoph; Lesker, Till R; Strowig, Till; Dechend, Ralf; Bzdok, Danilo; Kleinewietfeld, Markus; Andreas, Michalsen; Müller, Dominik N; Forslund, Sofia K in Hypertension (2019). 74(Suppl_1)
[ BibTeX ] [ DOI ]
 
@article{noauthororeditor2019integrative, author = {Avery, Ellen G and Balogh, András and Bartolomaeus, Hendrik and Löber, Ulrike and Steckhan, Nico and Markó, Lajos and Wilck, Nicola and Hamad, Ibrahim and Šušnjar, Urša and Mähler, Anja and Hohmann, Christoph and Lesker, Till R and Strowig, Till and Dechend, Ralf and Bzdok, Danilo and Kleinewietfeld, Markus and Andreas, Michalsen and Müller, Dominik N and Forslund, Sofia K}, journal = {Hypertension}, keywords = {nicosteckhan}, number = {Suppl_1}, title = {Integrative Network Analysis Of Microbiome-Immune Axis In Metabolic Syndrome Patients During A Fasting Intervention}, volume = 74, year = 2019 }
Digital Transformation of Complementary and Alternative Medicine (Accepted Presubmission). Steckhan, Nico; Arnrich, Bert in Complementary Medicine Research (2019).
[ BibTeX ] [ URL ]
 
@article{steckhandigital, author = {Steckhan, Nico and Arnrich, Bert}, journal = {Complementary Medicine Research}, keywords = {nicosteckhan bertarnrich}, title = {Digital Transformation of Complementary and Alternative Medicine (Accepted Presubmission)}, year = 2019 }
Stress detection in daily life scenarios using smart phones and wearable sensors: A survey. Yekta Said, Can; Arnrich, Bert; Ersoy, Cem in Journal of Biomedical Informatics (2019). 92 103139.
[ BibTeX ]
 
@article{yektasaid2019stress, author = {Yekta Said, Can and Arnrich, Bert and Ersoy, Cem}, journal = {Journal of Biomedical Informatics}, keywords = {bertarnrich}, pages = 103139, title = {Stress detection in daily life scenarios using smart phones and wearable sensors: A survey}, volume = 92, year = 2019 }
An Exploratory Study to Detect Temporal Orientation Using Bluetooth’s sensor. Netzahualcoyotl, Hernandez; Demiray, Burcu; Arnrich, Bert; Favela, Jesus (2019). (Vol. 13) 292–297.
[ BibTeX ]
 
@inproceedings{netzahualcoyotl2019exploratory, author = {Netzahualcoyotl, Hernandez and Demiray, Burcu and Arnrich, Bert and Favela, Jesus}, booktitle = {13th EAI International Conference on Pervasive Computing Technologies for Healthcare}, journal = {Pervasive Health}, keywords = {bertarnrich}, month = 6, pages = {292-297}, publisher = {EAI}, title = {An Exploratory Study to Detect Temporal Orientation Using Bluetooth's sensor}, volume = 13, year = 2019 }
From face to face: the contribution of facial mimicry to cognitive and emotional empathy. Drimalla, Hanna; Landwehr, Niels; Hess, Ursula; Dziobek, Isabel in Cognition and Emotion (2019). 33(8) 1672–1686.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{doi:10.1080/02699931.2019.1596068, author = {Drimalla, Hanna and Landwehr, Niels and Hess, Ursula and Dziobek, Isabel}, journal = {Cognition and Emotion}, keywords = {myown face mimicry empathy fb-boettinger}, note = {PMID: 30898024}, number = 8, pages = {1672-1686}, publisher = {Routledge}, title = {From face to face: the contribution of facial mimicry to cognitive and emotional empathy}, volume = 33, year = 2019 }
A multi-site study on walkability, data sharing and privacy perception using mobile sensing data gathered from the mk-sense platform. Hernández, N; Arnrich, Bert; Favela, J; Ersoy, C; Demiray, Burcu; Fontecha, J in Journal of Ambient Intelligence and Humanized Computing (2019). 10 2199–2211.
[ BibTeX ]
 
@article{hernandez2019multisite, author = {Hernández, N and Arnrich, Bert and Favela, J and Ersoy, C and Demiray, Burcu and Fontecha, J}, journal = {Journal of Ambient Intelligence and Humanized Computing}, keywords = {bertarnrich}, pages = {2199-2211}, title = {A multi-site study on walkability, data sharing and privacy perception using mobile sensing data gathered from the mk-sense platform}, volume = 10, year = 2019 }
SVD Square-root Iterated Extended Kalman Filter for Modeling of Epileptic Seizure Count Time Series with External Inputs. Moontaha, Sidratul; Galka, Andreas; Siniatchkin, Michael; Scharlach, Sascha; von Spiczak, Sarah; Stephani, Ulrich; May, Theodor; Meurer, Thomas (2019). (Vol. 41) 616–619.
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
In this paper a nonlinear filtering algorithm for count time series is developed that takes the non-negativity of the data into account and preserves positive definiteness of the covariance matrices of the model. For this purpose, a recently proposed variant of Kalman Filtering based on Singular Value Decomposition is incorporated into Iterative Extended Kalman Filtering, in order to estimate the states of a nonlinear state space model. The resulting algorithm is applied to the evaluation and design of therapies for patients suffering from Myoclonic Astatic Epilepsy, employing time series of daily seizure rate. The analysis provides a decision whether for a specific patient a particular anti-epileptic drug is increasing or reducing the seizure rate. Through a simulation study the proposed algorithm is validated. Additionally, for clinical data results obtained by the proposed algorithm are compared with the results from a Cox-Stuart trend test as well as with the visual assessment of experienced pediatric epileptologists.
@inproceedings{moontaha2019squareroot, abstract = {In this paper a nonlinear filtering algorithm for count time series is developed that takes the non-negativity of the data into account and preserves positive definiteness of the covariance matrices of the model. For this purpose, a recently proposed variant of Kalman Filtering based on Singular Value Decomposition is incorporated into Iterative Extended Kalman Filtering, in order to estimate the states of a nonlinear state space model. The resulting algorithm is applied to the evaluation and design of therapies for patients suffering from Myoclonic Astatic Epilepsy, employing time series of daily seizure rate. The analysis provides a decision whether for a specific patient a particular anti-epileptic drug is increasing or reducing the seizure rate. Through a simulation study the proposed algorithm is validated. Additionally, for clinical data results obtained by the proposed algorithm are compared with the results from a Cox-Stuart trend test as well as with the visual assessment of experienced pediatric epileptologists.}, author = {Moontaha, Sidratul and Galka, Andreas and Siniatchkin, Michael and Scharlach, Sascha and von Spiczak, Sarah and Stephani, Ulrich and May, Theodor and Meurer, Thomas}, booktitle = {41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society}, keywords = {prior-hpi sidratulmoontaha}, pages = {616-619}, publisher = {IEEE}, title = {SVD Square-root Iterated Extended Kalman Filter for Modeling of Epileptic Seizure Count Time Series with External Inputs}, volume = 41, year = 2019 }
Poisoning Attacks with Generative Adversarial Nets. Muñoz-González, Luis; Pfitzner, Bjarne; Russo, Matteo; Carnerero-Cano, Javier; Lupu, Emil C (2019).
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
Machine learning algorithms are vulnerable to poisoning attacks: An adversary can inject malicious points in the training dataset to influence the learning process and degrade the algorithm’s performance. Optimal poisoning attacks have already been proposed to evaluate worst-case scenarios, modelling attacks as a bi-level optimization problem. Solving these problems is computationally demanding and has limited applicability for some models such as deep networks. In this paper we introduce a novel generative model to craft systematic poisoning attacks against machine learning classifiers generating adversarial training examples, i.e. samples that look like genuine data points but that degrade the classifier’s accuracy when used for training. We propose a Generative Adversarial Net with three components: generator, discriminator, and the target classifier. This approach allows us to model naturally the detectability constrains that can be expected in realistic attacks and to identify the regions of the underlying data distribution that can be more vulnerable to data poisoning. Our experimental evaluation shows the effectiveness of our attack to compromise machine learning classifiers, including deep networks.
@misc{munozgonzalez2019poisoning, abstract = {Machine learning algorithms are vulnerable to poisoning attacks: An adversary can inject malicious points in the training dataset to influence the learning process and degrade the algorithm’s performance. Optimal poisoning attacks have already been proposed to evaluate worst-case scenarios, modelling attacks as a bi-level optimization problem. Solving these problems is computationally demanding and has limited applicability for some models such as deep networks. In this paper we introduce a novel generative model to craft systematic poisoning attacks against machine learning classifiers generating adversarial training examples, i.e. samples that look like genuine data points but that degrade the classifier’s accuracy when used for training. We propose a Generative Adversarial Net with three components: generator, discriminator, and the target classifier. This approach allows us to model naturally the detectability constrains that can be expected in realistic attacks and to identify the regions of the underlying data distribution that can be more vulnerable to data poisoning. Our experimental evaluation shows the effectiveness of our attack to compromise machine learning classifiers, including deep networks.}, author = {Muñoz-González, Luis and Pfitzner, Bjarne and Russo, Matteo and Carnerero-Cano, Javier and Lupu, Emil C}, journal = {arXiv:1906.07773}, keywords = {bjarnepfitzner prior-hpi}, title = {Poisoning Attacks with Generative Adversarial Nets}, year = 2019 }
Qualitative Comparison of Selected Indel Detection Methods for RNA-Seq Data. Slosarek, Tamara; Kraus, Milena; Schapranow, Matthieu-P; Bottinger, Erwin (2019). 166–177.
[ BibTeX ]
 
@inproceedings{slosarek2019qualitative, author = {Slosarek, Tamara and Kraus, Milena and Schapranow, Matthieu-P and Bottinger, Erwin}, booktitle = {International Work-Conference on Bioinformatics and Biomedical Engineering}, keywords = {myown fb-boettinger smart}, organization = {Springer}, pages = {166-177}, title = {Qualitative Comparison of Selected Indel Detection Methods for RNA-Seq Data}, year = 2019 }
A Federated In-memory Database System for Life Sciences. Schapranow, Matthieu-P.; others, and in Real-Time Business Intelligence and Analytics. BIRTE 2015, BIRTE 2016, BIRTE 2017, M. Castellanos, P. Chrysanthis, K. Pelechrinis (eds.) (2019). (Vol. 337)
[ BibTeX ]
 
@incollection{schapranow2019federated, author = {Schapranow, Matthieu-P. and and others}, booktitle = {Real-Time Business Intelligence and Analytics. BIRTE 2015, BIRTE 2016, BIRTE 2017}, editor = {Castellanos, M. and Chrysanthis, P. and Pelechrinis, K.}, keywords = {myown}, publisher = {Springer, Cham}, series = {Lecture Notes in Business Information Processing}, title = {A Federated In-memory Database System for Life Sciences}, volume = 337, year = 2019 }
Genetic analyses of diverse populations improves discovery for complex traits. Wojcik, Genevieve L; Graff, Mariaelisa; Nishimura, Katherine K; Tao, Ran; Haessler, Jeffrey; Gignoux, Christopher R; Highland, Heather M; Patel, Yesha M; Sorokin, Elena P; Avery, Christy L; Belbin, Gillian M; Bien, Stephanie A; Cheng, Iona; Cullina, Sinead; Hodonsky, Chani J; Hu, Yao; Huckins, Laura M; Jeff, Janina; Justice, Anne E; Kocarnik, Jonathan M; Lim, Unhee; Lin, Bridget M; Lu, Yingchang; Nelson, Sarah C; Park, Sung-Shim L; Poisner, Hannah; Preuss, Michael H; Richard, Melissa A; Schurmann, Claudia; Setiawan, Veronica W; Sockell, Alexandra; Vahi, Karan; Verbanck, Marie; Vishnu, Abhishek; Walker, Ryan W; Young, Kristin L; Zubair, Niha; Acuna-Alonso, Victor; Ambite, Jose Luis; Barnes, Kathleen C; Boerwinkle, Eric; Bottinger, Erwin P; Bustamante, Carlos D; Caberto, Christian; Canizales-Quinteros, Samuel; Conomos, Matthew P; Deelman, Ewa; Do, Ron; Doheny, Kimberly; Fernandez-Rhodes, Lindsay; Fornage, Myriam; Hailu, Benyam; Heiss, Gerardo; Henn, Brenna M; Hindorff, Lucia A; Jackson, Rebecca D; Laurie, Cecelia A; Laurie, Cathy C; Li, Yuqing; Lin, Dan-Yu; Moreno-Estrada, Andres; Nadkarni, Girish; Norman, Paul J; Pooler, Loreall C; Reiner, Alexander P; Romm, Jane; Sabatti, Chiara; Sandoval, Karla; Sheng, Xin; Stahl, Eli A; Stram, Daniel O; Thornton, Timothy A; Wassel, Christina L; Wilkens, Lynne R; Winkler, Cheryl A; Yoneyama, Sachi; Buyske, Steven; Haiman, Christopher A; Kooperberg, Charles; Le Marchand, Loic; Loos, Ruth J F; Matise, Tara C; North, Kari E; Peters, Ulrike; Kenny, Eimear E; Carlson, Christopher S in Nature (2019). 570(7762) 514–518.
[ Abstract ] [ BibTeX ] [ DOI ]
 
Genome-wide association studies (GWAS) have laid the foundation for investigations into the biology of complex traits, drug development and clinical guidelines. However, the majority of discovery efforts are based on data from populations of European ancestry(1-3). In light of the differential genetic architecture that is known to exist between populations, bias in representation can exacerbate existing disease and healthcare disparities. Critical variants may be missed if they have a low frequency or are completely absent in European populations, especially as the field shifts its attention towards rare variants, which are more likely to be population-specific(4-10). Additionally, effect sizes and their derived risk prediction scores derived in one population may not accurately extrapolate to other populations(11,12). Here we demonstrate the value of diverse, multi-ethnic participants in large-scale genomic studies. The Population Architecture using Genomics and Epidemiology (PAGE) study conducted a GWAS of 26 clinical and behavioural phenotypes in 49,839 non-European individuals. Using strategies tailored for analysis of multi-ethnic and admixed populations, we describe a framework for analysing diverse populations, identify 27 novel loci and 38 secondary signals at known loci, as well as replicate 1,444 GWAS catalogue associations across these traits. Our data show evidence of effect-size heterogeneity across ancestries for published GWAS associations, substantial benefits for fine-mapping using diverse cohorts and insights into clinical implications. In the United States-where minority populations have a disproportionately higher burden of chronic conditions(13)-the lack of representation of diverse populations in genetic research will result in inequitable access to precision medicine for those with the highest burden of disease. We strongly advocate for continued, large genome-wide efforts in diverse populations to maximize genetic discovery and reduce health disparities.
@article{Wojcik2019, abstract = {Genome-wide association studies (GWAS) have laid the foundation for investigations into the biology of complex traits, drug development and clinical guidelines. However, the majority of discovery efforts are based on data from populations of European ancestry(1-3). In light of the differential genetic architecture that is known to exist between populations, bias in representation can exacerbate existing disease and healthcare disparities. Critical variants may be missed if they have a low frequency or are completely absent in European populations, especially as the field shifts its attention towards rare variants, which are more likely to be population-specific(4-10). Additionally, effect sizes and their derived risk prediction scores derived in one population may not accurately extrapolate to other populations(11,12). Here we demonstrate the value of diverse, multi-ethnic participants in large-scale genomic studies. The Population Architecture using Genomics and Epidemiology (PAGE) study conducted a GWAS of 26 clinical and behavioural phenotypes in 49,839 non-European individuals. Using strategies tailored for analysis of multi-ethnic and admixed populations, we describe a framework for analysing diverse populations, identify 27 novel loci and 38 secondary signals at known loci, as well as replicate 1,444 GWAS catalogue associations across these traits. Our data show evidence of effect-size heterogeneity across ancestries for published GWAS associations, substantial benefits for fine-mapping using diverse cohorts and insights into clinical implications. In the United States-where minority populations have a disproportionately higher burden of chronic conditions(13)-the lack of representation of diverse populations in genetic research will result in inequitable access to precision medicine for those with the highest burden of disease. We strongly advocate for continued, large genome-wide efforts in diverse populations to maximize genetic discovery and reduce health disparities.}, author = {Wojcik, Genevieve L and Graff, Mariaelisa and Nishimura, Katherine K and Tao, Ran and Haessler, Jeffrey and Gignoux, Christopher R and Highland, Heather M and Patel, Yesha M and Sorokin, Elena P and Avery, Christy L and Belbin, Gillian M and Bien, Stephanie A and Cheng, Iona and Cullina, Sinead and Hodonsky, Chani J and Hu, Yao and Huckins, Laura M and Jeff, Janina and Justice, Anne E and Kocarnik, Jonathan M and Lim, Unhee and Lin, Bridget M and Lu, Yingchang and Nelson, Sarah C and Park, Sung-Shim L and Poisner, Hannah and Preuss, Michael H and Richard, Melissa A and Schurmann, Claudia and Setiawan, Veronica W and Sockell, Alexandra and Vahi, Karan and Verbanck, Marie and Vishnu, Abhishek and Walker, Ryan W and Young, Kristin L and Zubair, Niha and Acuna-Alonso, Victor and Ambite, Jose Luis and Barnes, Kathleen C and Boerwinkle, Eric and Bottinger, Erwin P and Bustamante, Carlos D and Caberto, Christian and Canizales-Quinteros, Samuel and Conomos, Matthew P and Deelman, Ewa and Do, Ron and Doheny, Kimberly and Fernandez-Rhodes, Lindsay and Fornage, Myriam and Hailu, Benyam and Heiss, Gerardo and Henn, Brenna M and Hindorff, Lucia A and Jackson, Rebecca D and Laurie, Cecelia A and Laurie, Cathy C and Li, Yuqing and Lin, Dan-Yu and Moreno-Estrada, Andres and Nadkarni, Girish and Norman, Paul J and Pooler, Loreall C and Reiner, Alexander P and Romm, Jane and Sabatti, Chiara and Sandoval, Karla and Sheng, Xin and Stahl, Eli A and Stram, Daniel O and Thornton, Timothy A and Wassel, Christina L and Wilkens, Lynne R and Winkler, Cheryl A and Yoneyama, Sachi and Buyske, Steven and Haiman, Christopher A and Kooperberg, Charles and {Le Marchand}, Loic and Loos, Ruth J F and Matise, Tara C and North, Kari E and Peters, Ulrike and Kenny, Eimear E and Carlson, Christopher S}, journal = {Nature}, keywords = {myown claudia.schurmann hpims fb-boettinger}, month = {jun}, number = 7762, pages = {514–518}, title = {{Genetic analyses of diverse populations improves discovery for complex traits.}}, volume = 570, year = 2019 }
External Validation of a Black-Box Clinical Predictive Model in Nephrology: Can Interpretability Methods Help Illuminate Performance Differences?. Freitas da Cruz, Harry; Pfahringer, Boris; Schneider, Frederic; Meyer, Alexander; Schapranow, Matthieu-P. (2019). 191–201.
[ BibTeX ] [ DOI ]
 
@inproceedings{freitasdacruzprediction, author = {Freitas da Cruz, Harry and Pfahringer, Boris and Schneider, Frederic and Meyer, Alexander and Schapranow, Matthieu-P.}, booktitle = {Proceedings of 17th Conference on Artificial Intelligence in Medicine}, keywords = {BigMedilytics fb-boettinger}, pages = {191-201}, title = {External Validation of a Black-Box Clinical Predictive Model in Nephrology: Can Interpretability Methods Help Illuminate Performance Differences?}, year = 2019 }
An Information and Communication Platform Supporting Analytics for Elderly Care. Konak, Orhan; Freitas Da Cruz, Harry; Thiele, Marvin; Golla, David; Schapranow, Matthieu-P. (2019).
[ BibTeX ]
 
@inproceedings{konak2019information, author = {Konak, Orhan and Freitas Da Cruz, Harry and Thiele, Marvin and Golla, David and Schapranow, Matthieu-P.}, booktitle = {5th International Conference on Information for Ageing Well, Communication Technologies e Health}, keywords = {myown SAHRA fb-boettinger}, title = {An Information and Communication Platform Supporting Analytics for Elderly Care}, year = 2019 }
Prediction of Acute Kidney Injury in Cardiac Surgery Patients: Interpretation using Local Interpretable Model-agnostic Explanations. Freitas da Cruz, Harry; Schneider, Frederic; Schapranow, Matthieu-P. (2019). (Vol. 5) 380–387.
[ BibTeX ]
 
@conference{Cruz2018, author = {Freitas da Cruz, Harry and Schneider, Frederic and Schapranow, Matthieu-P.}, booktitle = {Proceedings of the 12th International Conference on Biomedical Engineering Systems and Technologies}, keywords = {myown SAHRA fb-boettinger}, pages = {380-387}, title = {Prediction of Acute Kidney Injury in Cardiac Surgery Patients: Interpretation using Local Interpretable Model-agnostic Explanations}, volume = 5, year = 2019 }
Imitation und Erkennung von Emotionen bei Autismus-Spektrum-Störungen - eine computerbasierte Analyse des fazialen Emotionsausdrucks. Drimalla, Hanna; Baskow, Irina; Roepke, Stefan; Behnia, Behnoush; Dziobek, Isabel in 12. Wissenschaftliche Tagung Autismus-Spektrum (2019).
[ BibTeX ]
 
@article{drimalla2018imitation, author = {Drimalla, Hanna and Baskow, Irina and Roepke, Stefan and Behnia, Behnoush and Dziobek, Isabel}, journal = {12. Wissenschaftliche Tagung Autismus-Spektrum}, keywords = {myown machine learning fb-boettinger}, title = {Imitation und Erkennung von Emotionen bei Autismus-Spektrum-Störungen - eine computerbasierte Analyse des fazialen Emotionsausdrucks}, year = 2019 }
Knowledge Distillation from Machine Learning Models for Prediction of Hemodialysis Outcomes. Freitas da Cruz, Harry; Horschig, Siegfried; Nusshag, Christian; Schapranow, Matthieu-P. in International Journal On Advances in Life Sciences (2019). 11(1-2) 33–43.
[ Abstract ] [ BibTeX ]
 
In order to compensate severe impairments of renal function, artificial, extracorporeal devices, so called dialyzers, have been developed to enable renal replacement therapy. The parameters utilized in this form of therapy and the specific patient characteristics substantially affect individual patient outcomes and overall disease progression. In this paper, we present a clinical prediction model for outcomes of critically ill patients that underwent a specific form of renal replacement, hemodialysis. For this purpose, we employed two categories of machine learning models: interpretable (Bayesian rule lists and logistic regression) and non-interpretable (multilayer perceptron and random forest). To provide more transparency to the latter category, we applied mimic learning and feature importance metrics. Results show that non-interpretable models outperform the rule-based classifier (c-statistic ≥ 0.9). Despite this result, the use of interpretability methods enables more thorough model scrutiny by a medical experts, revealing possible model biases, which might have been otherwise disregarded.
@article{freitasdacruz2019knowledge, abstract = {In order to compensate severe impairments of renal function, artificial, extracorporeal devices, so called dialyzers, have been developed to enable renal replacement therapy. The parameters utilized in this form of therapy and the specific patient characteristics substantially affect individual patient outcomes and overall disease progression. In this paper, we present a clinical prediction model for outcomes of critically ill patients that underwent a specific form of renal replacement, hemodialysis. For this purpose, we employed two categories of machine learning models: interpretable (Bayesian rule lists and logistic regression) and non-interpretable (multilayer perceptron and random forest). To provide more transparency to the latter category, we applied mimic learning and feature importance metrics. Results show that non-interpretable models outperform the rule-based classifier (c-statistic ≥ 0.9). Despite this result, the use of interpretability methods enables more thorough model scrutiny by a medical experts, revealing possible model biases, which might have been otherwise disregarded.}, author = {Freitas da Cruz, Harry and Horschig, Siegfried and Nusshag, Christian and Schapranow, Matthieu-P.}, journal = {International Journal On Advances in Life Sciences}, keywords = {myown bigmedilytics fb-boettinger}, month = {June}, number = {1-2}, pages = {33-43}, title = {Knowledge Distillation from Machine Learning Models for Prediction of Hemodialysis Outcomes}, volume = 11, year = 2019 }
Diagnosis of obesity and use of obesity biomarkers in science and clinical medicine. Nimptsch, Katharina; Konigorski, Stefan; Pischon, Tobias in Metabolism (2019). 92 61–70.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Nimptsch_2019, author = {Nimptsch, Katharina and Konigorski, Stefan and Pischon, Tobias}, journal = {Metabolism}, keywords = {myown}, month = {mar}, pages = {61–70}, publisher = {Elsevier {BV}}, title = {Diagnosis of obesity and use of obesity biomarkers in science and clinical medicine}, volume = 92, year = 2019 }
MORPHER – A Platform to Support Modeling of Outcome and Risk Prediction in Health Research. Freitas da Cruz, Harry; Bergner, Benjamin; Konak, Orhan; Schneider, Frederic; Bode, Philipp; Lempert, Conrad; Schapranow, Matthieu-P. (2019).
[ BibTeX ]
 
@conference{freitasdacruz2019morpher, author = {Freitas da Cruz, Harry and Bergner, Benjamin and Konak, Orhan and Schneider, Frederic and Bode, Philipp and Lempert, Conrad and Schapranow, Matthieu-P.}, booktitle = {Proceedings of the 19th IEEE International Conference on Bioinformatics and Biomedicine}, keywords = {myown bigmedilytics fb-boettinger}, title = {MORPHER – A Platform to Support Modeling of Outcome and Risk Prediction in Health Research}, year = 2019 }
Kernel-based tests integrating variant effect predictions from deep learning for genetic association tests of rare variants. Konigorski, Stefan; Monti, Remo; Lippert, Christoph (2019).
[ BibTeX ] [ URL ] [ DOI ]
 
@conference{stefan2019kernelbased, author = {Konigorski, Stefan and Monti, Remo and Lippert, Christoph}, booktitle = {64. Jahrestagung der Deutschen Gesellschaft für Medizinische Informatik, Biometrie und Epidemiologie e. V. (GMDS)}, keywords = {myown}, title = {Kernel-based tests integrating variant effect predictions from deep learning for genetic association tests of rare variants}, year = 2019 }
Prediction of circulating adipokine levels based on body fat compartments and adipose tissue gene expression. Konigorski, Stefan; Janke, Jürgen; Drogan, Dagmar; Bergmann, Manuela M.; Hierholzer, Johannes; Kaaks, Rudolf; Boeing, Heiner; Pischon, Tobias in Obesity Facts (2019). 12 590–605.
[ BibTeX ] [ DOI ]
 
@article{stefanprediction, author = {Konigorski, Stefan and Janke, Jürgen and Drogan, Dagmar and Bergmann, Manuela M. and Hierholzer, Johannes and Kaaks, Rudolf and Boeing, Heiner and Pischon, Tobias}, journal = {Obesity Facts}, keywords = {myown}, pages = {590-605}, title = {Prediction of circulating adipokine levels based on body fat compartments and adipose tissue gene expression}, volume = 12, year = 2019 }
Cross-dataset deep transfer learning for activity recognition. Gjoreski, Martin; Kalabakov, Stefan; Luštrek, MItja; Gams, Matjaž; Gjoreski, Hristijan in Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers (2019). 714–718.
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
Convolution Neural Network (CNN) filters learned on one domain can be used as feature extractors on another similar domain. Transferring filters allow reusing datasets across domains and reducing labelling costs. In this paper, four activity recognition datasets were analyzed to study the effects of transferring filters across the datasets. A spectro-temporal ResNet was implemented as a deep, end-to-end learning architecture. We analyzed the number of transferred CNN residual blocks with respect to the size of the target-adaptation data. The analysis showed that transfer learning using small adaptation subsets is more useful when the target domain contains a small number of different activities. Furthermore, the similarity between the domains, participating in the transfer learning scenario, seems to play a role in its success. The most successful transfer achieved an F1-score of 93%, which is an increase of 9 percentage points compared to a domain-specific baseline model.
@incollection{crossdataset, abstract = {Convolution Neural Network (CNN) filters learned on one domain can be used as feature extractors on another similar domain. Transferring filters allow reusing datasets across domains and reducing labelling costs. In this paper, four activity recognition datasets were analyzed to study the effects of transferring filters across the datasets. A spectro-temporal ResNet was implemented as a deep, end-to-end learning architecture. We analyzed the number of transferred CNN residual blocks with respect to the size of the target-adaptation data. The analysis showed that transfer learning using small adaptation subsets is more useful when the target domain contains a small number of different activities. Furthermore, the similarity between the domains, participating in the transfer learning scenario, seems to play a role in its success. The most successful transfer achieved an F1-score of 93%, which is an increase of 9 percentage points compared to a domain-specific baseline model.}, author = {Gjoreski, Martin and Kalabakov, Stefan and Luštrek, MItja and Gams, Matjaž and Gjoreski, Hristijan}, booktitle = {Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers}, keywords = {bertarnrich prior-hpi kalabakovstefan}, pages = {714–718}, publisher = {Association for Computing Machinery}, title = {Cross-dataset deep transfer learning for activity recognition}, year = 2019 }
Für bessere Diagnosen und Therapien: Wie Ärzte und KI in der Krebsbehandlung zusammenarbeiten. Schapranow, Matthieu-P. (2019, December).
[ BibTeX ] [ URL ]
 
@misc{schapranow2019bessere, author = {Schapranow, Matthieu-P.}, howpublished = {publicly published}, keywords = {myown}, month = {dec}, title = {Für bessere Diagnosen und Therapien: Wie Ärzte und KI in der Krebsbehandlung zusammenarbeiten}, year = 2019 }
Towards a fine-scale population health monitoring system. Belbin, Gillian M; Wenric, Stephane; Cullina, Sinead; Glicksberg, Benjamin S; Moscati, Arden; Wojcik, Genevieve L; Shemirani, Ruhollah; Beckmann, Noam D; Cohain, Ariella; Sorokin, Elena P; Park, Danny S; Ambite, Jose-Luis; Ellis, Steve; Auton, Adam; Bottinger, Erwin P.; Cho, Judy H; Loos, Ruth JF; Abul husn, Noura S; Zaitlen, Noah A; Gignoux, Christopher R; Kenny, Eimear E; and (2019).
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Belbin2019, author = {Belbin, Gillian M and Wenric, Stephane and Cullina, Sinead and Glicksberg, Benjamin S and Moscati, Arden and Wojcik, Genevieve L and Shemirani, Ruhollah and Beckmann, Noam D and Cohain, Ariella and Sorokin, Elena P and Park, Danny S and Ambite, Jose-Luis and Ellis, Steve and Auton, Adam and Bottinger, Erwin P. and Cho, Judy H and Loos, Ruth JF and Abul husn, Noura S and Zaitlen, Noah A and Gignoux, Christopher R and Kenny, Eimear E and and}, keywords = {boettinger hpims fb-boettinger}, month = {sep}, publisher = {Cold Spring Harbor Laboratory}, title = {Towards a fine-scale population health monitoring system}, year = 2019 }

2018

HPI-DHC at TREC 2018 Precision Medicine Track. Oleynik, M; Faessler, E; Sasso, A.M; Kappattanavar, A.; Bergner, B.; da Cruz, H.F.; Sachs, J.-P.; Datta, S.; Boettinger, E (2018).
[ BibTeX ] [ URL ]
 
@inproceedings{oleynik2018hpidhc, author = {Oleynik, M and Faessler, E and Sasso, A.M and Kappattanavar, A. and Bergner, B. and da Cruz, H.F. and Sachs, J.-P. and Datta, S. and Boettinger, E}, keywords = {arpitakappattanavar}, title = {HPI-DHC at TREC 2018 Precision Medicine Track}, year = 2018 }
Interactive Data Exploration Supporting Elderly Care Planning. Freitas da Cruz, Harry; Gebhardt, Marie; Becher, Felix; Schapranow, Matthieu-P. (2018).
[ BibTeX ]
 
@conference{hcruz2018healthinfo, author = {Freitas da Cruz, Harry and Gebhardt, Marie and Becher, Felix and Schapranow, Matthieu-P.}, booktitle = {Proceedings of the 10th International Conference on eHealth, Telemedicine, and Social Medicine}, keywords = {myown SAHRA fb-boettinger}, title = {Interactive Data Exploration Supporting Elderly Care Planning}, year = 2018 }
Prediction of Patient Outcomes after Renal Replacement Therapy in Intensive Care. Freitas da Cruz, Harry; Horschig, Siegfried; Nusshag, Christian; Schapranow, Matthieu-P. (2018).
[ BibTeX ]
 
@inproceedings{dacruz2018, author = {Freitas da Cruz, Harry and Horschig, Siegfried and Nusshag, Christian and Schapranow, Matthieu-P.}, booktitle = {Proceedings of the 3rd International Conference on Informatics and Assistive Technologies for Health-Care, Medical Support and Wellbeing}, keywords = {myown SAHRA fb-boettinger}, title = {Prediction of Patient Outcomes after Renal Replacement Therapy in Intensive Care}, year = 2018 }
Integrating omics and MRI data with kernel-based tests and CNNs to identify rare genetic markers for Alzheimer’s disease. Konigorski, Stefan; Khorasani, Shahryar; Lippert, Christoph (2018).
[ BibTeX ] [ URL ]
 
@inproceedings{noauthororeditor, author = {Konigorski, Stefan and Khorasani, Shahryar and Lippert, Christoph}, booktitle = {Machine Learning for Health (ML4H) Workshop at NeurIPS 2018, arXiv:1812.00448}, keywords = {myown}, title = {Integrating omics and MRI data with kernel-based tests and CNNs to identify rare genetic markers for Alzheimer's disease}, year = 2018 }
Analysis of the effects of medication for the treatment of epilepsy by ensemble Iterative Extended Kalman Filtering. Moontaha, Sidratul; Galka, Andreas; Meurer, Thomas; Siniatchkin, Michael (2018). (Vol. 40) 187–190.
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
This paper proposes an objective methodology for the analysis of epileptic seizure count time series by developing a non-linear state space model. An iterative extended Kalman filter (IEKF) is employed for the estimation of the states of the non-linear state space model. In order to improve convergence of the IEKF, the recently proposed Levenberg-Marquardt variant of the IEKF is explored. As external inputs time-dependent dosages of several simultaneously administered anticonvulsants are included. The aim of the analysis is to decide whether each anticonvulsant decreases or increases the number of seizures per day. The performance of the analysis is analyzed for simulated data, as well as for real data from a patient suffering from myoclonic-astatic epilepsy.
@inproceedings{moontaha2018analysis, abstract = {This paper proposes an objective methodology for the analysis of epileptic seizure count time series by developing a non-linear state space model. An iterative extended Kalman filter (IEKF) is employed for the estimation of the states of the non-linear state space model. In order to improve convergence of the IEKF, the recently proposed Levenberg-Marquardt variant of the IEKF is explored. As external inputs time-dependent dosages of several simultaneously administered anticonvulsants are included. The aim of the analysis is to decide whether each anticonvulsant decreases or increases the number of seizures per day. The performance of the analysis is analyzed for simulated data, as well as for real data from a patient suffering from myoclonic-astatic epilepsy.}, author = {Moontaha, Sidratul and Galka, Andreas and Meurer, Thomas and Siniatchkin, Michael}, booktitle = {40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society}, keywords = {prior-hpi sidratulmoontaha}, pages = {187-190}, publisher = {IEEE}, title = {Analysis of the effects of medication for the treatment of epilepsy by ensemble Iterative Extended Kalman Filtering}, volume = 40, year = 2018 }
DEAME-Differential Expression Analysis Made Easy. Kraus, Milena; Hesse, Guenter; Slosarek, Tamara; Danner, Marius; Kesar, Ajay; Bhushan, Akshay; Schapranow, Matthieu-P in Heterogeneous Data Management, Polystores, and Analytics for Healthcare (2018). 162–174.
[ BibTeX ]
 
@incollection{kraus2018deame, author = {Kraus, Milena and Hesse, Guenter and Slosarek, Tamara and Danner, Marius and Kesar, Ajay and Bhushan, Akshay and Schapranow, Matthieu-P}, booktitle = {Heterogeneous Data Management, Polystores, and Analytics for Healthcare}, keywords = {myown fb-boettinger smart}, pages = {162–174}, publisher = {Springer}, title = {DEAME-Differential Expression Analysis Made Easy}, type = {Publication}, year = 2018 }
Senska - Towards an Enterprise Streaming Benchmark. Hesse, Guenter; Reissaus, Benjamin; Matthies, Christoph; Lorenz, Martin; Kraus, Milena; Uflacker, Matthias (2018). 25–40.
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
In the light of growing data volumes and continuing digitization in fields such as Industry 4.0 or Internet of Things, data stream processing have gained popularity and importance. Especially enterprises can benefit from this development by augmenting their vital, core business data with up-to-date streaming information. Enriching this transactional data with detailed information from high-frequency data streams allows answering new analytical questions as well as improving current analyses, e.g., regarding predictive maintenance. Comparing such data stream processing architectures for use in an enterprise context, i.e., when combining streaming and business data, is currently a challenging task as there is no suitable benchmark.
@inproceedings{hesse2018senska, abstract = {In the light of growing data volumes and continuing digitization in fields such as Industry 4.0 or Internet of Things, data stream processing have gained popularity and importance. Especially enterprises can benefit from this development by augmenting their vital, core business data with up-to-date streaming information. Enriching this transactional data with detailed information from high-frequency data streams allows answering new analytical questions as well as improving current analyses, e.g., regarding predictive maintenance. Comparing such data stream processing architectures for use in an enterprise context, i.e., when combining streaming and business data, is currently a challenging task as there is no suitable benchmark.}, author = {Hesse, Guenter and Reissaus, Benjamin and Matthies, Christoph and Lorenz, Martin and Kraus, Milena and Uflacker, Matthias}, booktitle = {Performance Evaluation and Benchmarking for the Analytics Era: 9th TPC Technology Conference, TPCTC 2017, Munich, Germany, August 28, 2017, Revised Selected Papers}, keywords = {myown}, pages = {25-40}, publisher = {Springer International Publishing}, title = {Senska - Towards an Enterprise Streaming Benchmark}, type = {Publication}, year = 2018 }
Kernel-based tests for very rare variants. Konigorski, S; Lippert, C (2018). (Vol. 42) 711.
[ BibTeX ] [ URL ] [ DOI ]
 
@conference{konigorski2018kernelbased, author = {Konigorski, S and Lippert, C}, booktitle = {Genetic Epidemiology}, keywords = {myown}, number = 7, pages = 711, title = {Kernel-based tests for very rare variants}, volume = 42, year = 2018 }
MetaExp: Interactive Explanation and Exploration of Large Knowledge Graphs. Behrens, Freya; Bischoff, Sebastian; Ladenburger, Pius; Rückin, Julius; Seidel, Laurenz; Stolp, Fabian; Vaichenker, Michael; Ziegler, Adrian; Mottin, Davide; Aghaei, Fatemeh; Müller, Emmanuel; Preusse, Martin; Müller, Nikola; Hunger, Michael (2018). 199–202.
[ BibTeX ] [ URL ]
 
@inproceedings{behrens2018metaexp, author = {Behrens, Freya and Bischoff, Sebastian and Ladenburger, Pius and Rückin, Julius and Seidel, Laurenz and Stolp, Fabian and Vaichenker, Michael and Ziegler, Adrian and Mottin, Davide and Aghaei, Fatemeh and Müller, Emmanuel and Preusse, Martin and Müller, Nikola and Hunger, Michael}, booktitle = {Companion Proceedings of the The Web Conference 2018}, keywords = {prior-hpi fabianstolp}, pages = {199–202}, title = {MetaExp: Interactive Explanation and Exploration of Large Knowledge Graphs}, year = 2018 }

2017

Olelo: a web application for intuitive exploration of biomedical literature. Kraus, Milena; Niedermeier, Julian; Jankrift, Marcel; Tietboehl, Soeren; Stachewicz, Toni; Folkerts, Hendrik; Uflacker, Matthias; Neves, Mariana in Nucleic acids research (2017).
[ BibTeX ]
 
@article{kraus2017olelo, author = {Kraus, Milena and Niedermeier, Julian and Jankrift, Marcel and Tietboehl, Soeren and Stachewicz, Toni and Folkerts, Hendrik and Uflacker, Matthias and Neves, Mariana}, journal = {Nucleic acids research}, keywords = {myown smart}, title = {Olelo: a web application for intuitive exploration of biomedical literature}, year = 2017 }
Geometric Algebra Computing for Heterogeneous Systems. Hildenbrand, D.; Albert, Justin; Charrier, P.; Steinmetz, C. in Advances in Applied Clifford Algebras (2017). 27 599–620.
[ BibTeX ] [ URL ] [ DOI ]
 
@article{Hildenbrand2017GeometricAC, author = {Hildenbrand, D. and Albert, Justin and Charrier, P. and Steinmetz, C.}, journal = {Advances in Applied Clifford Algebras}, keywords = {justinalbert prior-hpi}, pages = {599-620}, title = {Geometric Algebra Computing for Heterogeneous Systems}, volume = 27, year = 2017 }
Anti-adenoviral artificial MicroRNAs expressed from AAV9 vectors inhibit human adenovirus infection in immunosuppressed Syrian hamsters. Schaar, Katrin; Geisler, Anja; Kraus, Milena; Pinkert, Sandra; Pryshliak, Markian; Spencer, Jacqueline F; Tollefson, Ann E; Ying, Baoling; Kurreck, Jens; Wold, William S; others in Molecular Therapy-Nucleic Acids (2017). 8 300–316.
[ BibTeX ]
 
@article{schaar2017anti, author = {Schaar, Katrin and Geisler, Anja and Kraus, Milena and Pinkert, Sandra and Pryshliak, Markian and Spencer, Jacqueline F and Tollefson, Ann E and Ying, Baoling and Kurreck, Jens and Wold, William S and others}, journal = {Molecular Therapy-Nucleic Acids}, keywords = {myown}, pages = {300–316}, publisher = {Elsevier}, title = {Anti-adenoviral artificial MicroRNAs expressed from AAV9 vectors inhibit human adenovirus infection in immunosuppressed Syrian hamsters}, volume = 8, year = 2017 }
A web-based information system for a regional public mental healthcare service network in Brazil. Yoshiura, Vinicius Tohoru; Azevedo-Marques, Joao Mazzoncini; Rzewuska, Magdalena; Vinci, Andre Luiz Teixeira; Sasso, Ariane Morassi; Miyoshi, Newton Shydeo Brandao; Furegato, Antonia Regina Ferreira; Rijo, Rui Pedro Charters Lopes; Del-Ben, Cristina Marta; Alves, Domingos in International journal of mental health systems (2017). 11(1) 1.
[ BibTeX ]
 
@article{yoshiura2017web, author = {Yoshiura, Vinicius Tohoru and Azevedo-Marques, Joao Mazzoncini and Rzewuska, Magdalena and Vinci, Andre Luiz Teixeira and Sasso, Ariane Morassi and Miyoshi, Newton Shydeo Brandao and Furegato, Antonia Regina Ferreira and Rijo, Rui Pedro Charters Lopes and Del-Ben, Cristina Marta and Alves, Domingos}, journal = {International journal of mental health systems}, keywords = {myown health-information-system mental-health}, number = 1, pages = 1, publisher = {BioMed Central}, title = {A web-based information system for a regional public mental healthcare service network in Brazil}, volume = 11, year = 2017 }
Die digitale Transformation mitgestalten — Der Datenspendeausweis: Souveräner Umgang mit persönlichen Gesundheitsdaten. Schapranow, Matthieu-P. in Plattform Life Sciences, (H. Garbs, ed.) (2017). (1) 38–39.
[ BibTeX ]
 
@article{schapranow2017digitale, author = {Schapranow, Matthieu-P.}, editor = {Garbs, Holger}, journal = {Plattform Life Sciences}, keywords = {myown SAHRA}, month = {mar}, number = 1, pages = {38–39}, title = {Die digitale Transformation mitgestalten — Der Datenspendeausweis: Souveräner Umgang mit persönlichen Gesundheitsdaten}, year = 2017 }
Olelo: A Question Answering Application for Biomedicine. Neves, Mariana; Folkerts, Hendrik; Jankrift, Marcel; Niedermeier, Julian; Stachewicz, Toni; Tietböhl, Sören; Kraus, Milena; Uflacker, Matthias (2017).
[ BibTeX ]
 
@inproceedings{neves2017, author = {Neves, Mariana and Folkerts, Hendrik and Jankrift, Marcel and Niedermeier, Julian and Stachewicz, Toni and Tietböhl, Sören and Kraus, Milena and Uflacker, Matthias}, booktitle = {ACL'17 Demo}, keywords = {myown}, title = {Olelo: A Question Answering Application for Biomedicine}, year = 2017 }
An In-Memory Database Platform for Systems Medicine. Kraus, Milena; Schapranow, Matthieu-P. (2017). 93–100.
[ BibTeX ]
 
@inproceedings{kraus2017inmemory, author = {Kraus, Milena and Schapranow, Matthieu-P.}, booktitle = {Proceedings of the International Conference on Bioinformatics and Computational Biology}, keywords = {myown SMART}, number = 9, organization = {The International Society for Computers and Their Applications (ISCA)}, pages = {93–100}, title = {An In-Memory Database Platform for Systems Medicine}, year = 2017 }
The Data Donation Pass: Enabling Sovereign Control of Personal Healthcare Data. Schapranow, Matthieu-P.; Brauer, Janos; Plattner, Hasso (2017).
[ BibTeX ]
 
@inproceedings{schapranow2017donation, author = {Schapranow, Matthieu-P. and Brauer, Janos and Plattner, Hasso}, booktitle = {Proceedings of the World Congress in Computer Science, Computer Engineering, and Applied Computing}, keywords = {myown}, month = {07}, publisher = {CSCE}, title = {The Data Donation Pass: Enabling Sovereign Control of Personal Healthcare Data}, year = 2017 }

2016

Die In-Memory-Technologie in der personalisierten Medizin. Schapranow, Matthieu-P. (2016, February).
[ BibTeX ] [ URL ]
 
@misc{schapranow2016inmemorytechnologie, author = {Schapranow, Matthieu-P.}, journal = {SAP News}, keywords = {myown}, month = {feb}, title = {Die In-Memory-Technologie in der personalisierten Medizin}, year = 2016 }
Real-time Exploration of Healthcare Data using In-Memory Database Technology Rückert, Lars (2016).
[ BibTeX ]
 
@mastersthesis{ruckert2016realtime, author = {Rückert, Lars}, keywords = {SAHRA}, title = {Real-time Exploration of Healthcare Data using In-Memory Database Technology}, year = 2016 }
Prediction of Health Research Data using In-Memory Database Technology Horschig, Friedrich (2016).
[ BibTeX ]
 
@mastersthesis{horschig2016prediction, author = {Horschig, Friedrich}, keywords = {SAHRA}, title = {Prediction of Health Research Data using In-Memory Database Technology}, year = 2016 }
ADRiAS: Acute Disease Risk Assessment System Cruz, H.; Grasnick, S.; Dinger, H. (2016).
[ BibTeX ]
 
@presentation{cruz2016adrias, author = {Cruz, H. and Grasnick, S. and Dinger, H.}, keywords = {myown}, title = {ADRiAS: Acute Disease Risk Assessment System}, year = 2016 }
Datenspendeausweis für ­Bürger: Ein Plädoyer für mündige Patienten, die die eigenen Gesundheitsdaten am besten verstehen. Schapranow, Matthieu-P. in Management & Krankenhaus (2016). (9)
[ BibTeX ]
 
@article{schapranow2016datenspendeausweis, author = {Schapranow, Matthieu-P.}, journal = {Management & Krankenhaus}, keywords = {myown SAHRA}, month = {sep}, number = 9, title = {Datenspendeausweis für ­Bürger: Ein Plädoyer für mündige Patienten, die die eigenen Gesundheitsdaten am besten verstehen.}, year = 2016 }
Towards An Integrated Health Research Process: A Cloud-based Approach. Schapranow, Matthieu-P.; Uflacker, Matthias; Sariyar, Murat; Semler, Sebastian; Fichte, Johannes; Schielke, Dietmar; Ekinci, Kismet; Zahn, Thomas in Proceedings of The IEEE International Conference on Big Data (2016). 2813–2818.
[ Abstract ] [ BibTeX ] [ URL ]
 
Today, health research and health care generate a steadily increasing amount of data. Making these available for secondary use cases is essential for efficiency gains in health research, e.g. by reducing time-and costs-intensive acquisition of data. In this contribution, we introduce our SAHRA software platform enabling reproducible research, e.g. by combining multiple data sources, performing data de-identification, and content filtering. We define an innovative research process combining retrospective and prospective research for the first time. Thus, authorized users, e.g. clinical researchers, are able to gain access through our system relevant research data and to perform interactive analyses. As a result, existing sensitive health data is securely transformed into de-identified research data, which can be used to improve future health research.
@article{noauthororeditortowards, abstract = {Today, health research and health care generate a steadily increasing amount of data. Making these available for secondary use cases is essential for efficiency gains in health research, e.g. by reducing time-and costs-intensive acquisition of data. In this contribution, we introduce our SAHRA software platform enabling reproducible research, e.g. by combining multiple data sources, performing data de-identification, and content filtering. We define an innovative research process combining retrospective and prospective research for the first time. Thus, authorized users, e.g. clinical researchers, are able to gain access through our system relevant research data and to perform interactive analyses. As a result, existing sensitive health data is securely transformed into de-identified research data, which can be used to improve future health research.}, author = {Schapranow, Matthieu-P. and Uflacker, Matthias and Sariyar, Murat and Semler, Sebastian and Fichte, Johannes and Schielke, Dietmar and Ekinci, Kismet and Zahn, Thomas}, journal = {Proceedings of The IEEE International Conference on Big Data}, keywords = {SAHRA}, pages = {2813–2818}, title = {Towards An Integrated Health Research Process: A Cloud-based Approach}, year = 2016 }
Early Detection of Acute Kidney Injury with Bayesian Networks. Freitas da Cruz, Harry; Grasnick, Bastien; Dinger, Henriette; Bier, Frank; Meinel, Christoph (2016). 29–36.
[ BibTeX ]
 
@inproceedings{Harry2016a, author = {Freitas da Cruz, Harry and Grasnick, Bastien and Dinger, Henriette and Bier, Frank and Meinel, Christoph}, booktitle = {Proceedings of the 7th International Symposium on Semantic Mining in Biomedicine}, howpublished = {Proceedings of the 7th International Symposium on Semantic Mining in Biomedicine}, keywords = {nephrology}, pages = {29-36}, title = {Early Detection of Acute Kidney Injury with Bayesian Networks}, year = 2016 }
IMDBfs: Bridging the Gap between In-Memory Database Technology and File-Based Tools for Life Sciences. Schapranow, Matthieu-P.; Kraus, Milena; Danner, Marius; Plattner, Hasso (2016). 1133–1139.
[ BibTeX ]
 
@conference{Matthieu-P.2016a, author = {Schapranow, Matthieu-P. and Kraus, Milena and Danner, Marius and Plattner, Hasso}, booktitle = {Proceedings of the IEEE International Conference on Bioinformatics and Biomedicine}, keywords = {myown SMART smart}, organization = {IEEE}, pages = {1133–1139}, title = {IMDBfs: Bridging the Gap between In-Memory Database Technology and File-Based Tools for Life Sciences}, year = 2016 }
Geographical Exploration of Key Performance Indicators for Elderly Care Planning Postel, Malek (2016).
[ BibTeX ]
 
@mastersthesis{postel2016geographical, author = {Postel, Malek}, keywords = {SAHRA}, title = {Geographical Exploration of Key Performance Indicators for Elderly Care Planning}, year = 2016 }
BioMedLAT Corpus: Annotation of the Lexical Answer Type for Biomedical Questions. Neves, Mariana; Kraus, Milena (2016). 49.
[ BibTeX ]
 
@conference{Mariana2016a, author = {Neves, Mariana and Kraus, Milena}, booktitle = {Open Knowledge Base and Question Answering Workshop at the 26th International Conference on Computational Linguistics (Coling)}, howpublished = {Open Knowledge Base and Question Answering Workshop at the 26th International Conference on Computational Linguistics (Coling)}, journal = {OKBQA 2016}, keywords = {myown}, pages = 49, title = {BioMedLAT Corpus: Annotation of the Lexical Answer Type for Biomedical Questions}, year = 2016 }

2015

The Medical Knowledge Cockpit: Real-time Analysis of Big Medical Data Enabling Precision Medicine. Schapranow, Matthieu-P.; Kraus, Milena; Perscheid, Cindy; Bock, Cornelius; Liedtke, Franz; Plattner, Hasso (2015). 770–775.
[ BibTeX ]
 
@inproceedings{Matthieu2015a, author = {Schapranow, Matthieu-P. and Kraus, Milena and Perscheid, Cindy and Bock, Cornelius and Liedtke, Franz and Plattner, Hasso}, booktitle = {Proceedings of the IEEE International Conference on Bioinformatics and Biomedicine (BIBM)}, keywords = {myown}, pages = {770-775}, title = {The Medical Knowledge Cockpit: Real-time Analysis of Big Medical Data Enabling Precision Medicine}, year = 2015 }
Facing the Genome Data Deluge: Efficiently Identifying Genetic Variants with In-Memory Database Technology. Fähnrich, Cindy; Schapranow, Matthieu-P.; Plattner, Hasso (2015).
[ BibTeX ]
 
@conference{Cindy2015a, author = {Fähnrich, Cindy and Schapranow, Matthieu-P. and Plattner, Hasso}, booktitle = {Proceedings of the ACM Symposium on Applied Computing}, keywords = {myown}, title = {Facing the Genome Data Deluge: Efficiently Identifying Genetic Variants with In-Memory Database Technology}, year = 2015 }
IT-Aided Business Process Enabling Real-time Analysis of Candidates for Clinical Trials. Schapranow, Matthieu-P.; Perscheid, Cindy; Plattner, Hasso (2015). 67–73.
[ Abstract ] [ BibTeX ]
 
Recruitment of participants for clinical trials is a complex task involving screening of hundreds of thousands of candidates, e.g., testing for trial-specific inclusion and exclusion criteria. Today, a significant amount of time is spent on manual screening as improper selected candidates have impact on the overall study results. We introduce a candidate eligibility metric, which allows systematic ranking and classification of candidates based on trial-specific filter criteria in an automatic way. It is implemented as part of our web application, which enables real-time analysis of patient data and assessment of candidates. Thus, the time for identification of eligible candidates is tremendously reduced whilst additional degrees of freedom for assessing the relevance of individual candidates are available.
@inproceedings{Matthieu-P.2015b, abstract = {Recruitment of participants for clinical trials is a complex task involving screening of hundreds of thousands of candidates, e.g., testing for trial-specific inclusion and exclusion criteria. Today, a significant amount of time is spent on manual screening as improper selected candidates have impact on the overall study results. We introduce a candidate eligibility metric, which allows systematic ranking and classification of candidates based on trial-specific filter criteria in an automatic way. It is implemented as part of our web application, which enables real-time analysis of patient data and assessment of candidates. Thus, the time for identification of eligible candidates is tremendously reduced whilst additional degrees of freedom for assessing the relevance of individual candidates are available.}, author = {Schapranow, Matthieu-P. and Perscheid, Cindy and Plattner, Hasso}, booktitle = {Proceedings of the 4th International Conference on Global Health Challenges}, keywords = {myown}, pages = {67-73}, publisher = {IARIA}, title = {IT-Aided Business Process Enabling Real-time Analysis of Candidates for Clinical Trials}, year = 2015 }
„Surveillance and Outbreak Response Management and Analysis System (SORMAS)“ ermöglicht Kontrolle von Ebola-Infizierten in Westafrika. Denecke, Kerstin; Mall, Sabine; Fähnrich, Cindy; Perscheid, Cindy; Adeoye, Olawunmi Olubunmi; Benzler, Justus; Claus, Hermann; Kirchner, Göran; Richter, Ralph; Schapranow, Matthieu-P.; Schwarz, Norbert; Reigl, Lisa; Tom-Aba, Daniel; Gidado, Saheed; Waziri, Ndadilnasiya Endie; Uflacker, Matthias; Krause, Gérard; Poggensee, Gabriele (2015).
[ BibTeX ]
 
@conference{Kerstin2015a, author = {Denecke, Kerstin and Mall, Sabine and Fähnrich, Cindy and Perscheid, Cindy and Adeoye, Olawunmi Olubunmi and Benzler, Justus and Claus, Hermann and Kirchner, Göran and Richter, Ralph and Schapranow, Matthieu-P. and Schwarz, Norbert and Reigl, Lisa and Tom-Aba, Daniel and Gidado, Saheed and Waziri, Ndadilnasiya Endie and Uflacker, Matthias and Krause, Gérard and Poggensee, Gabriele}, booktitle = {10. Jahrestagung der Deutschen Gesellschaft für Epidemiologie (DGEpi)}, keywords = {myown}, month = 9, title = {„Surveillance and Outbreak Response Management and Analysis System (SORMAS)“ ermöglicht Kontrolle von Ebola-Infizierten in Westafrika}, year = 2015 }
Surveillance and Outbreak Response Management System (SORMAS) to support the control of the Ebola virus disease outbreak in West Africa. Fähnrich, Cindy; Denecke, Kerstin; Adeoye, Olawunmi; Benzler, Justus; Claus, Hermann; Kirchner, Göran; Mall, Sabine; Richter, Ralph; Schapranow, Matthieu-P.; Schwarz, Norbert G.; Tom-Aba, Daniel; Uflacker, Matthias; Poggensee, Gabriele; Krause, Gerard in Euro Surveillance (2015).
[ BibTeX ]
 
@article{Cindy2015a, author = {Fähnrich, Cindy and Denecke, Kerstin and Adeoye, Olawunmi and Benzler, Justus and Claus, Hermann and Kirchner, Göran and Mall, Sabine and Richter, Ralph and Schapranow, Matthieu-P. and Schwarz, Norbert G. and Tom-Aba, Daniel and Uflacker, Matthias and Poggensee, Gabriele and Krause, Gerard}, journal = {Euro Surveillance}, keywords = {myown}, title = {Surveillance and Outbreak Response Management System (SORMAS) to support the control of the Ebola virus disease outbreak in West Africa}, year = 2015 }
An Ontology for TNM Clinical Stage Inference. Massicano, Felipe; Sasso, Ariane; Tomaz, Henrique; Oleynik, Michel; Nobrega, Calebe; Patrao, Diogo FC (2015). (Vol. 1442)
[ BibTeX ]
 
@inproceedings{massicano2015ontology, author = {Massicano, Felipe and Sasso, Ariane and Tomaz, Henrique and Oleynik, Michel and Nobrega, Calebe and Patrao, Diogo FC}, booktitle = {ONTOBRAS}, keywords = {myown oncology tnm ontology}, title = {An Ontology for TNM Clinical Stage Inference.}, volume = 1442, year = 2015 }
Recruit-An Ontology Based Information Retrieval System for Clinical Trials Recruitment. Patrao, Diogo FC; Oleynik, Michel; Massicano, Felipe; Sasso, Ariane Morassi (2015). 534–538.
[ BibTeX ]
 
@inproceedings{patrao2015recruit, author = {Patrao, Diogo FC and Oleynik, Michel and Massicano, Felipe and Sasso, Ariane Morassi}, booktitle = {MedInfo}, keywords = {information-retrieval myown oncology clinical-trial ontology}, pages = {534–538}, title = {Recruit-An Ontology Based Information Retrieval System for Clinical Trials Recruitment.}, year = 2015 }
Implementation and Demonstration of the p-BioSPRE Metabiobank Platform. Dobkwicz, M.; Jüttner, T.; Freitas da Cruz, Harry; Heidtke, K.; Finkenwirth, T.; Kunze, S.; Hänold, S.; Nwankwo, I.; Forgó, N.; Schröder, C.; Graf, N. (2015).
[ BibTeX ]
 
@inproceedings{dobkwicz2015implementation, author = {Dobkwicz, M. and Jüttner, T. and Freitas da Cruz, Harry and Heidtke, K. and Finkenwirth, T. and Kunze, S. and Hänold, S. and Nwankwo, I. and Forgó, N. and Schröder, C. and Graf, N.}, booktitle = {Demo at the 15th World Congress on Health and Biomedical Informatics}, keywords = {myown}, title = {Implementation and Demonstration of the p-BioSPRE Metabiobank Platform}, year = 2015 }
A Federated In-Memory Database System For Life Sciences. Schapranow, Matthieu-P.; Perscheid, Cindy; Wachsmann, Alf; Siegert, Martin; Bock, Cornelius; Horschig, Friedrich; Liedke, Franz; Brauer, Janos; Plattner, Hasso (2015).
[ BibTeX ]
 
@inproceedings{Matthieu-P.2015a, author = {Schapranow, Matthieu-P. and Perscheid, Cindy and Wachsmann, Alf and Siegert, Martin and Bock, Cornelius and Horschig, Friedrich and Liedke, Franz and Brauer, Janos and Plattner, Hasso}, booktitle = {Proceedings of the 9th International Workshop on Business Intelligence for the Real Time Enterprise (BIRTE)}, keywords = {myown}, title = {A Federated In-Memory Database System For Life Sciences}, year = 2015 }

2014

In-Memory Technology Enables Interactive Drug Response Analysis. Schapranow, Matthieu-P.; Klinghammer, Konrad; Fähnrich, Cindy; Plattner, Hasso (2014).
[ BibTeX ]
 
@conference{Matthieu-P.2014a, author = {Schapranow, Matthieu-P. and Klinghammer, Konrad and Fähnrich, Cindy and Plattner, Hasso}, booktitle = {16th International Conference on e-Health Networking, Applications and Services (Healthcom 2014)}, keywords = {myown}, title = {In-Memory Technology Enables Interactive Drug Response Analysis}, year = 2014 }
An Optimized Research Process for Real-time Drug Response Analysis. Schapranow, Matthieu-P.; Klinghammer, Konrad; Fähnrich, Cindy; Plattner, Hasso (2014).
[ BibTeX ]
 
@conference{Matthieu-P.2014b, author = {Schapranow, Matthieu-P. and Klinghammer, Konrad and Fähnrich, Cindy and Plattner, Hasso}, booktitle = {The Third International Conference on Global Health Challenges}, keywords = {myown}, title = {An Optimized Research Process for Real-time Drug Response Analysis}, year = 2014 }
In-Memory Computing Enabling Real-time Genome Data Analysis. Haeger, Franziska; Schapranow, Matthieu-P.; Fähnrich, Cindy; Ziegler, Emanuel; Plattner, Hasso in International Journal on Advances in Life Sciences, Vol 6, Nr 1-2 (2014).
[ BibTeX ]
 
@article{Franziska2014a, author = {Haeger, Franziska and Schapranow, Matthieu-P. and Fähnrich, Cindy and Ziegler, Emanuel and Plattner, Hasso}, journal = {International Journal on Advances in Life Sciences, Vol 6, Nr 1-2}, keywords = {myown}, title = {In-Memory Computing Enabling Real-time Genome Data Analysis}, year = 2014 }
Applying In-Memory Technology for Automatic Template Filling in the Clinical Domain. Herbst, Konrad; Fähnrich, Cindy; Neves, Mariana; Schapranow, Matthieu-P. (2014).
[ BibTeX ]
 
@conference{Konrad2014a, author = {Herbst, Konrad and Fähnrich, Cindy and Neves, Mariana and Schapranow, Matthieu-P.}, booktitle = {CLEF 2014 Evaluation Labs and Workshop, Online Working Notes}, keywords = {myown}, title = {Applying In-Memory Technology for Automatic Template Filling in the Clinical Domain}, year = 2014 }
High-Performance In-Memory Genome Data Analysis: How In-Memory Database Technology Accelerates Personalized Medicine Schapranow, Matthieu-P.; Plattner, Hasso (2014). 123. Springer.
[ BibTeX ]
 
@book{Matthieu-P.2014a, author = {Schapranow, Matthieu-P. and Plattner, Hasso}, keywords = {myown}, pages = 123, publisher = {Springer}, title = {High-Performance In-Memory Genome Data Analysis: How In-Memory Database Technology Accelerates Personalized Medicine}, year = 2014 }
Towards Integrating the Detection of Genetic Variants into an In-Memory Database. Fähnrich, Cindy; Schapranow, Matthieu-P.; Plattner, Hasso (2014).
[ BibTeX ]
 
@conference{Cindy2014a, author = {Fähnrich, Cindy and Schapranow, Matthieu-P. and Plattner, Hasso}, booktitle = {Proceedings of the International Conference on Big Data}, keywords = {myown}, title = {Towards Integrating the Detection of Genetic Variants into an In-Memory Database}, year = 2014 }

2013

Big Data soll Genom-Analysen schneller voranbringen. Schapranow, Matthieu-P.; Meinel, Christoph; Plattner, Hasso in Krankenhaus-IT Journal, p. 26 (2013).
[ BibTeX ]
 
@article{Matthieu-P.2013a, author = {Schapranow, Matthieu-P. and Meinel, Christoph and Plattner, Hasso}, journal = {Krankenhaus-IT Journal, p. 26}, keywords = {myown}, title = {Big Data soll Genom-Analysen schneller voranbringen}, year = 2013 }
In-Memory Technology Enables History-Based Access Control for RFID-Aided Supply Chains. Schapranow, Matthieu-P.; Plattner, Hasso in The Secure Information Society: Ethical, Legal and Political Challenges, pp. 187-213 (2013).
[ BibTeX ]
 
@inbook{Matthieu-P.2013a, author = {Schapranow, Matthieu-P. and Plattner, Hasso}, keywords = {myown}, series = {The Secure Information Society: Ethical, Legal and Political Challenges, pp. 187-213}, title = {In-Memory Technology Enables History-Based Access Control for RFID-Aided Supply Chains}, year = 2013 }
Applied In-Memory Technology to High Throughput Genome Data Processing. Schapranow, Matthieu-P.; Meinel, Christoph; Plattner, Hasso (2013). 35–42.
[ BibTeX ]
 
@inproceedings{2013_Meinel_CATAI, address = {Canary Islands, Spain}, author = {Schapranow, Matthieu-P. and Meinel, Christoph and Plattner, Hasso}, booktitle = {Proceedings of XXI Winter Course of the CATAI (CATAI 2013)}, keywords = {myown}, month = 3, pages = {35-42}, title = {Applied In-Memory Technology to High Throughput Genome Data Processing}, year = 2013 }
HIG – An In-memory Database Platform Enabling Real-time Analyses of Genome Data. Schapranow, Matthieu-P.; Plattner, Hasso (2013). 691–696.
[ BibTeX ]
 
@conference{Matthieu-P.2013a, author = {Schapranow, Matthieu-P. and Plattner, Hasso}, booktitle = {Proceedings of the International Conference on Big Data}, keywords = {myown}, pages = {691-696}, title = {HIG – An In-memory Database Platform Enabling Real-time Analyses of Genome Data}, year = 2013 }
Mobile Real-time Analysis of Patient Data for Advanced Decision Support in Personalized Medicine. Schapranow, Matthieu-P.; Plattner, Hasso; Tosun, Cafer; Regenbrecht, Christian (2013).
[ BibTeX ]
 
@conference{Matthieu-P.2013a, author = {Schapranow, Matthieu-P. and Plattner, Hasso and Tosun, Cafer and Regenbrecht, Christian}, booktitle = {The 5th International Conference on eHealth, Telemedicine, and Social Medicine, pp. 129-136}, keywords = {myown}, title = {Mobile Real-time Analysis of Patient Data for Advanced Decision Support in Personalized Medicine}, year = 2013 }
High-Performance In-Memory Genome Project: A Platform for Integrated Real-Time Genome Data Analysis. Haeger, Franziska; Plattner, Hasso; Schapranow, Matthieu-P. (2013). 5–10.
[ BibTeX ]
 
@conference{Franziska2013a, author = {Haeger, Franziska and Plattner, Hasso and Schapranow, Matthieu-P.}, booktitle = {Proceedings of the 2nd International Conference on Global Health Challenges}, keywords = {myown}, pages = {5-10}, title = {High-Performance In-Memory Genome Project: A Platform for Integrated Real-Time Genome Data Analysis}, year = 2013 }
Applied In-Memory Technology for High-Throughput Genome Data Processing and Real-time Analysis. Schapranow, Matthieu-P.; Plattner, Hasso; Meinel, Christoph (2013).
[ BibTeX ]
 
@conference{Matthieu-P.2013a, author = {Schapranow, Matthieu-P. and Plattner, Hasso and Meinel, Christoph}, booktitle = {System on Chip (!SoC) Devices in Telemedicine from !LABoC to High Resolution Images, pp. 35-42}, keywords = {myown}, title = {Applied In-Memory Technology for High-Throughput Genome Data Processing and Real-time Analysis}, year = 2013 }
Krebsdatenbank auf Tablet und Smartphone. Schapranow, Matthieu-P. in Best Practice Wireless in der Hauptstadtregion Berlin-Brandenburg, pp. 48-49 (2013).
[ BibTeX ]
 
@inbook{Matthieu-P.2013b, author = {Schapranow, Matthieu-P.}, keywords = {myown}, series = {Best Practice Wireless in der Hauptstadtregion Berlin-Brandenburg, pp. 48-49}, title = {Krebsdatenbank auf Tablet und Smartphone}, year = 2013 }
Real-time Security Extensions for EPCglobal Networks: Case Study for the Pharmaceutical Industry Schapranow, Matthieu-P. (2013). In-Memory Data Management Research, Springer.
[ BibTeX ]
 
@book{Matthieu-P.2013a, author = {Schapranow, Matthieu-P.}, keywords = {myown}, publisher = {In-Memory Data Management Research, Springer}, title = {Real-time Security Extensions for EPCglobal Networks: Case Study for the Pharmaceutical Industry}, year = 2013 }

2012

Datenbanktechnologie beflügelt personalisierte Medizin. Schapranow, Matthieu-P.; Meinel, Christoph; Plattner, Hasso in Laborwelt Nr. 4/2012, 13. Jahrgang (2012).
[ BibTeX ]
 
@article{Matthieu-P.2012a, author = {Schapranow, Matthieu-P. and Meinel, Christoph and Plattner, Hasso}, journal = {Laborwelt Nr. 4/2012, 13. Jahrgang}, keywords = {myown}, title = {Datenbanktechnologie beflügelt personalisierte Medizin}, year = 2012 }
Blitzschnelle Datenanalysen für die personalisierte Medizin der Zukunft – Interdisziplinäre Impulse aus Potsdam und Berlin. Plattner, Hasso; Meinel, Christoph; Schapranow, Matthieu-P. in Themenbroschüre 2012 Gesundheitsstandort Berlin-Brandenburg (2012).
[ BibTeX ]
 
@article{Hasso2012a, author = {Plattner, Hasso and Meinel, Christoph and Schapranow, Matthieu-P.}, journal = {Themenbroschüre 2012 Gesundheitsstandort Berlin-Brandenburg}, keywords = {myown}, title = {Blitzschnelle Datenanalysen für die personalisierte Medizin der Zukunft – Interdisziplinäre Impulse aus Potsdam und Berlin}, year = 2012 }
Secure RFID-Enablement in Modern Companies: A Case Study of the Pharmaceutical Industry. Müller, Jürgen; Schapranow, Matthieu-P.; Zeier, Alexander; Plattner, Hasso in Handbook of Research on Industrial Informatics and Manufacturing Intelligence: Innovations and Solutions, pp. 507-539, IGI Global (2012).
[ BibTeX ] [ DOI ]
 
@inbook{Jürgen2012a, author = {Müller, Jürgen and Schapranow, Matthieu-P. and Zeier, Alexander and Plattner, Hasso}, keywords = {myown}, series = {Handbook of Research on Industrial Informatics and Manufacturing Intelligence: Innovations and Solutions, pp. 507-539, IGI Global}, title = {Secure RFID-Enablement in Modern Companies: A Case Study of the Pharmaceutical Industry}, year = 2012 }

2011

Discovery Services in the EPC Network. Schapranow, Matthieu-P.; Zeier, Alexander; Plattner, Hasso; Müller, Jürgen; Lorenz, Martin in Designing and Deploying RFID Applications, pp. 109-130, INTECH Press (2011).
[ BibTeX ]
 
@inbook{Matthieu-P.2011a, author = {Schapranow, Matthieu-P. and Zeier, Alexander and Plattner, Hasso and Müller, Jürgen and Lorenz, Martin}, keywords = {myown}, series = {Designing and Deploying RFID Applications, pp. 109-130, INTECH Press}, title = {Discovery Services in the EPC Network}, year = 2011 }
What are Authentic Pharmaceuticals Worth?. Schapranow, Matthieu-P.; Müller, Jürgen; Zeier, Alexander; Plattner, Hasso in Designing and Deploying RFID Applications, pp. 204-220, INTECH Press (2011).
[ BibTeX ]
 
@inbook{Matthieu-P.2011b, author = {Schapranow, Matthieu-P. and Müller, Jürgen and Zeier, Alexander and Plattner, Hasso}, keywords = {myown}, series = {Designing and Deploying RFID Applications, pp. 204-220, INTECH Press}, title = {What are Authentic Pharmaceuticals Worth?}, year = 2011 }
A Formal Model for Enabling RFID in Pharmaceutical Supply Chains. Schapranow, Matthieu-P.; Zeier, Alexander; Plattner, Hasso (2011).
[ BibTeX ] [ DOI ]
 
@conference{Matthieu-P.2011a, author = {Schapranow, Matthieu-P. and Zeier, Alexander and Plattner, Hasso}, booktitle = {44th Hawaii International Conference on System Sciences (HICSS)}, keywords = {myown}, publisher = {IEEE}, title = {A Formal Model for Enabling RFID in Pharmaceutical Supply Chains}, year = 2011 }
Security Extensions for Improving Data Security of Event Repositories in EPCglobal Networks. Schapranow, Matthieu-P.; Zeier, Alexander; Plattner, Hasso (2011).
[ BibTeX ]
 
@conference{Matthieu-P.2011b, author = {Schapranow, Matthieu-P. and Zeier, Alexander and Plattner, Hasso}, booktitle = {The 9th International Conference on Embedded and Ubiquitous Computing pp. 213-220}, keywords = {myown}, title = {Security Extensions for Improving Data Security of Event Repositories in EPCglobal Networks}, year = 2011 }
License-based Access Control in EPCglobal Networks. Schapranow, Matthieu-P.; Lorenz, Martin; Zeier, Alexander; Plattner, Hasso (2011).
[ BibTeX ]
 
@conference{Matthieu-P.2011a, author = {Schapranow, Matthieu-P. and Lorenz, Martin and Zeier, Alexander and Plattner, Hasso}, booktitle = {The 7th European Workshop on RFID Systems and Technologies, pp. 1-7}, keywords = {myown}, title = {License-based Access Control in EPCglobal Networks}, year = 2011 }
Securing EPCglobal Object Name Service -- Privacy Enhancements for Anti-counterfeiting. Schapranow, Matthieu-P.; Zeier, Alexander; Leupold, Felix; Schubotz, Tobias (2011).
[ BibTeX ]
 
@conference{Matthieu-P.2011a, author = {Schapranow, Matthieu-P. and Zeier, Alexander and Leupold, Felix and Schubotz, Tobias}, booktitle = {2nd International Conference on Intelligent Systems, Modeling and Simulation, pp. 332-337}, keywords = {myown}, title = {Securing EPCglobal Object Name Service – Privacy Enhancements for Anti-counterfeiting}, year = 2011 }
A Distributed EPC Discovery Service based on Peer-to-peer Technology. Lorenz, Martin; Müller, Jürgen; Schapranow, Matthieu-P.; Zeier, Alexander (2011). 1–7.
[ BibTeX ]
 
@conference{Martin2011a, author = {Lorenz, Martin and Müller, Jürgen and Schapranow, Matthieu-P. and Zeier, Alexander}, booktitle = {Proceedings of the RFID SysTech 2011, 7th European Workshop on Smart Objects: Systems, Technologies and Applications, Dresden}, keywords = {myown}, pages = {1 - 7}, publisher = {VDE}, title = {A Distributed EPC Discovery Service based on Peer-to-peer Technology}, year = 2011 }
Costs of Authentic Pharmaceuticals: Research on Qualitative and Quantitative Aspects of Enabling Anti-counterfeiting in RFID-aided Supply Chains. Zeier, Alexander; Plattner, Hasso; Schapranow, Matthieu-P.; Müller, Jürgen in Personal and Ubiquitous Computing, Volume 16, Issue 3 (2011). 271–289.
[ BibTeX ] [ DOI ]
 
@article{Alexander2011a, author = {Zeier, Alexander and Plattner, Hasso and Schapranow, Matthieu-P. and Müller, Jürgen}, journal = {Personal and Ubiquitous Computing, Volume 16, Issue 3}, keywords = {myown}, pages = {271-289}, publisher = {Springer}, title = {Costs of Authentic Pharmaceuticals: Research on Qualitative and Quantitative Aspects of Enabling Anti-counterfeiting in RFID-aided Supply Chains}, year = 2011 }
Simulation of RFID-aided Supply Chains: Case Study of the Pharmaceutical Supply Chain. Schapranow, Matthieu-P.; Fähnrich, Cindy; Zeier, Alexander; Plattner, Hasso (2011).
[ BibTeX ]
 
@conference{Matthieu-P.2011a, author = {Schapranow, Matthieu-P. and Fähnrich, Cindy and Zeier, Alexander and Plattner, Hasso}, booktitle = {Third International Conference on Computational Intelligence, Modelling and Simulation, pp. 340-345}, keywords = {myown}, title = {Simulation of RFID-aided Supply Chains: Case Study of the Pharmaceutical Supply Chain}, year = 2011 }

2010

Real-Time Billing in Smart Grid Infrastructures. Schapranow, Matthieu-P.; Kühne, Ralph; Zeier, Alexander (2010).
[ BibTeX ]
 
@conference{Matthieu-P.2010a, author = {Schapranow, Matthieu-P. and Kühne, Ralph and Zeier, Alexander}, booktitle = {Power and Energy Student Summit 2010 - Integration of Renewable Energies into the Grid}, keywords = {myown}, title = {Real-Time Billing in Smart Grid Infrastructures}, year = 2010 }
Best Practices for Rigorous Evaluation of RFID Software Components. Müller, Jürgen; Schapranow, Matthieu-P.; Pöpke, Conrad; Urbat, Michaela; Zeier, Alexander; Plattner, Hasso (2010).
[ BibTeX ]
 
@conference{Jürgen2010a, author = {Müller, Jürgen and Schapranow, Matthieu-P. and Pöpke, Conrad and Urbat, Michaela and Zeier, Alexander and Plattner, Hasso}, booktitle = {Proceedings of the 6th European Workshop on RFID Systems and Technologies (RFID !SysTech'10), Ciudad Real, Spain}, keywords = {myown}, title = {Best Practices for Rigorous Evaluation of RFID Software Components}, year = 2010 }
RFID Event Data Processing -- An Architecture for Storing and Searching. Schapranow, Matthieu-P.; Müller, Jürgen; Zeier, Alexander; Plattner, Hasso (2010).
[ BibTeX ]
 
@conference{Matthieu-P.2010a, author = {Schapranow, Matthieu-P. and Müller, Jürgen and Zeier, Alexander and Plattner, Hasso}, booktitle = {Proceedings of the 4th International Workshop on RFID Technology - Concepts, Applications, Challenges, Funchal, Madeira, Portugal}, keywords = {myown}, title = {RFID Event Data Processing – An Architecture for Storing and Searching}, year = 2010 }
A Dynamic Mutual RFID Authentication Model Preventing Unauthorized Third Party Access. Schapranow, Matthieu-P.; Zeier, Alexander; Plattner, Hasso (2010).
[ BibTeX ]
 
@conference{Matthieu-P.2010a, author = {Schapranow, Matthieu-P. and Zeier, Alexander and Plattner, Hasso}, booktitle = {The 4th International Conference on Network and System Security, , pp. 371-376}, keywords = {myown}, title = {A Dynamic Mutual RFID Authentication Model Preventing Unauthorized Third Party Access}, year = 2010 }
CoMoSeR: Cost Model for Security-Enhanced RFID-Aided Supply Chains. Schapranow, Matthieu-P.; Nagora, Mike; Zeier, Alexander (2010).
[ BibTeX ]
 
@conference{Matthieu-P.2010c, author = {Schapranow, Matthieu-P. and Nagora, Mike and Zeier, Alexander}, booktitle = {The 18th International Conference on Software, Telecommunication and Computer Networks, pp. 11-16}, keywords = {myown}, title = {CoMoSeR: Cost Model for Security-Enhanced RFID-Aided Supply Chains}, year = 2010 }
Assessment of Communication Protocols in the EPC Network: Replacing Textual SOAP and XML with Binary Google Protocol Buffers Encoding. Schapranow, Matthieu-P.; Geller, Felix; Lorenz, Martin; Müller, Jürgen; Kowark, Thomas; Zeier, Alexander (2010).
[ BibTeX ]
 
@conference{Matthieu-P.2010a, author = {Schapranow, Matthieu-P. and Geller, Felix and Lorenz, Martin and Müller, Jürgen and Kowark, Thomas and Zeier, Alexander}, booktitle = {17th IEEE International Conference on Industrial Engineering and Engineering Management (IE&EM), Xiamen, China}, keywords = {myown}, title = {Assessment of Communication Protocols in the EPC Network: Replacing Textual SOAP and XML with Binary Google Protocol Buffers Encoding}, year = 2010 }
Enabling Real-Time Charging for Smart Grid Infrastructures using In-Memory Databases. Schapranow, Matthieu-P.; Kühne, Ralph; Zeier, Alexander (2010).
[ BibTeX ]
 
@conference{Matthieu-P.2010b, author = {Schapranow, Matthieu-P. and Kühne, Ralph and Zeier, Alexander}, booktitle = {1st IEEE LCN Workshop on Smart Grid Networking Infrastructure}, keywords = {myown}, title = {Enabling Real-Time Charging for Smart Grid Infrastructures using In-Memory Databases}, year = 2010 }

2009

Security Aspects in Vulnerable RFID-Aided Supply Chains. Schapranow, Matthieu-P.; Müller, Jürgen; Zeier, Alexander; Plattner, Hasso (2009).
[ BibTeX ]
 
@conference{Matthieu-P.2009a, author = {Schapranow, Matthieu-P. and Müller, Jürgen and Zeier, Alexander and Plattner, Hasso}, booktitle = {Proceedings of the 5th European Workshop on RFID Systems and Technologies, Bremen}, keywords = {myown}, title = {Security Aspects in Vulnerable RFID-Aided Supply Chains}, year = 2009 }
A Software as a Service RFID Middleware for Small and Medium-sized Enterprises. Müller, Jürgen; Faust, Martin; Schwalb, David; Schapranow, Matthieu-P.; Zeier, Alexander; Plattner, Hasso (2009).
[ BibTeX ]
 
@conference{Jürgen2009a, author = {Müller, Jürgen and Faust, Martin and Schwalb, David and Schapranow, Matthieu-P. and Zeier, Alexander and Plattner, Hasso}, booktitle = {Proceedings of the 5th European Workshop on RFID Systems and Technologies (RFID !SysTech'09), Bremen, Germany}, keywords = {myown}, title = {A Software as a Service RFID Middleware for Small and Medium-sized Enterprises}, year = 2009 }
Data Loading & Caching Strategies in Service-Oriented Enterprise Applications. Schapranow, Matthieu-P.; Krüger, Jens; Borovskiy, Vadym; Zeier, Alexander; Plattner, Hasso (2009).
[ BibTeX ]
 
@conference{Matthieu-P.2009b, author = {Schapranow, Matthieu-P. and Krüger, Jens and Borovskiy, Vadym and Zeier, Alexander and Plattner, Hasso}, booktitle = {Proceedings of IEEE Congress on Services (SERVICES 2009), Los Angeles, CA, USA}, keywords = {myown}, title = {Data Loading & Caching Strategies in Service-Oriented Enterprise Applications}, year = 2009 }
Ensuring Service Backwards Compatibility with Generic Web Services. Borovskiy, Vadym; Müller, Jürgen; Schapranow, Matthieu-P.; Zeier, Alexander (2009).
[ BibTeX ]
 
@conference{Vadym2009a, author = {Borovskiy, Vadym and Müller, Jürgen and Schapranow, Matthieu-P. and Zeier, Alexander}, booktitle = {Proceedings of ICSE 2009, PESOS Workshop, Vancouver, Canada}, keywords = {myown}, title = {Ensuring Service Backwards Compatibility with Generic Web Services}, year = 2009 }
Integration of RFID Technology is a Key Enabler for Demand-Driven Supply Network. Schapranow, Matthieu-P.; Müller, Jürgen; Krüger, Jens; Hofmann, Paul; Zeier, Alexander in The IUP Journal of Supply Chain Management, Volume 6, Nos. 3 & 4, pp. 57-74 (2009).
[ BibTeX ]
 
@article{Matthieu-P.2009a, author = {Schapranow, Matthieu-P. and Müller, Jürgen and Krüger, Jens and Hofmann, Paul and Zeier, Alexander}, journal = {The IUP Journal of Supply Chain Management, Volume 6, Nos. 3 & 4, pp. 57-74}, keywords = {myown}, title = {Integration of RFID Technology is a Key Enabler for Demand-Driven Supply Network}, year = 2009 }
noFilis CrossTalk 2.0 as Device Management Solution, Experiences while Integrating RFID Hardware into SAP Auto-ID Infrastructure. Zeier, Alexander; Schapranow, Matthieu-P.; Krüger, Jens; Uflacker, Matthias; Müller, Jürgen (2009).
[ BibTeX ]
 
@conference{Alexander2009a, author = {Zeier, Alexander and Schapranow, Matthieu-P. and Krüger, Jens and Uflacker, Matthias and Müller, Jürgen}, booktitle = {Proceedings of the 16th International Conference on Industrial Engineering and Engineering Management (IE&EM), Beijing, China}, keywords = {myown}, title = {noFilis CrossTalk 2.0 as Device Management Solution, Experiences while Integrating RFID Hardware into SAP Auto-ID Infrastructure}, year = 2009 }
Binary Search Tree Visualization Algorithm. Schapranow, Matthieu-P.; Zeier, Alexander; Borovskiy, Vadym; Müller, Jürgen (2009).
[ BibTeX ]
 
@conference{Matthieu-P.2009a, author = {Schapranow, Matthieu-P. and Zeier, Alexander and Borovskiy, Vadym and Müller, Jürgen}, booktitle = {16th International Conference on Industrial Engineering and Engineering Management (IE&EM), Beijing, China}, keywords = {myown}, title = {Binary Search Tree Visualization Algorithm}, year = 2009 }
RFID Middleware as a Service - Enabling Small and Medium-sized Enterprises to Participate in the EPC Network. Müller, Jürgen; Schapranow, Matthieu-P.; Helmich, Marco; Enderlein, Sebastian; Zeier, Alexander (2009).
[ BibTeX ]
 
@conference{Jürgen2009a, author = {Müller, Jürgen and Schapranow, Matthieu-P. and Helmich, Marco and Enderlein, Sebastian and Zeier, Alexander}, booktitle = {16th International Conference on Industrial Engineering and Engineering Management (IE&EM), Beijing, China}, keywords = {myown}, title = {RFID Middleware as a Service - Enabling Small and Medium-sized Enterprises to Participate in the EPC Network}, year = 2009 }
Low-Cost Mutual RFID Authentication Model Using Predefined Password Lists. Schapranow, Matthieu-P.; Müller, Jürgen; Enderlein, Sebastian; Helmich, Marco; Zeier, Alexander (2009).
[ BibTeX ]
 
@conference{Matthieu-P.2009a, author = {Schapranow, Matthieu-P. and Müller, Jürgen and Enderlein, Sebastian and Helmich, Marco and Zeier, Alexander}, booktitle = {The 16th International Conference on Industrial Engineering and Engineering Management, pp. 889-893}, keywords = {myown}, title = {Low-Cost Mutual RFID Authentication Model Using Predefined Password Lists}, year = 2009 }

2008

Smart Enterprise Widgets: Little Helpers with a Big Impact. Schapranow, Matthieu-P.; Krüger, Jens; Müller, Jürgen in SAP INFO (online) (2008).
[ BibTeX ]
 
@article{Matthieu-P.2008a, author = {Schapranow, Matthieu-P. and Krüger, Jens and Müller, Jürgen}, journal = {SAP INFO (online)}, keywords = {myown}, title = {Smart Enterprise Widgets: Little Helpers with a Big Impact}, year = 2008 }
Shared Table Access Pattern Analysis for Multi-Tenant Applications. Krüger, Jens; Grund, Martin; Schaffner, Jan; Schapranow, Matthieu-P.; Bog, Anja (2008).
[ BibTeX ]
 
@conference{Jens2008a, author = {Krüger, Jens and Grund, Martin and Schaffner, Jan and Schapranow, Matthieu-P. and Bog, Anja}, booktitle = {IEEE Symposium on Advanced Management of Information for Globalized Enterprises (AMIGE'08), Tianjin, China}, keywords = {myown}, title = {Shared Table Access Pattern Analysis for Multi-Tenant Applications}, year = 2008 }
Operational Reporting Using Navigational SQL. Grund, Martin; Schaffner, Jan; Schapranow, Matthieu-P.; Bog, Anja; Krüger, Jens (2008).
[ BibTeX ]
 
@conference{Martin2008a, author = {Grund, Martin and Schaffner, Jan and Schapranow, Matthieu-P. and Bog, Anja and Krüger, Jens}, booktitle = {IEEE Symposium on Advanced Management of Information for Globalized Enterprises (AMIGE'08), Tianjin, China}, keywords = {myown}, title = {Operational Reporting Using Navigational SQL}, year = 2008 }
HPI Students Learn with SAP Enterprise Services. Schapranow, Matthieu-P.; Krüger, Jens in SAP INFO (online) (2008).
[ BibTeX ]
 
@article{Matthieu-P.2008b, author = {Schapranow, Matthieu-P. and Krüger, Jens}, journal = {SAP INFO (online)}, keywords = {myown}, title = {HPI Students Learn with SAP Enterprise Services}, year = 2008 }
Combining Advantages - Unified Data Stores in Global Enterprises. Schapranow, Matthieu-P.; Grund, Martin; Krüger, Jens; Schaffner, Jan; Bog, Anja (2008).
[ BibTeX ]
 
@conference{Matthieu-P.2008a, author = {Schapranow, Matthieu-P. and Grund, Martin and Krüger, Jens and Schaffner, Jan and Bog, Anja}, booktitle = {IEEE Symposium on Advanced Management of Information for Globalized Enterprises (AMIGE'08), Tianjin, China}, keywords = {myown}, title = {Combining Advantages - Unified Data Stores in Global Enterprises}, year = 2008 }