We are happy to announce that four conference papers were accepted for publication in July!
Data Augmentation of Kinematic Time-Series from Rehabilitation Exercises using GANs
Accepted at the IEEE International Conference on Omni-layer Intelligent systems (COINS)
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.
Perioperative Risk Assessment in Pancreatic Surgery Using Machine Learning
Accepted at the 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)
Authors: Bjarne Pfitzner, Jonas Chromik, Rachel Brabender, Eric Fischer, Alexander Kromer, Axel Winter, Simon Moosburner, Igor Sauer, Thomas Malinka, Johann Pratschke, Bert Arnrich, Max Magnus Maurer
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 Charit´e Mitte j Campus Virchow-Klinikum, Charit´e – Universit¨atsmedizin 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.
Impact of Custom Features of Do-it-yourself Artificial Pancreas Systems (DIYAPS) on Glycemic Outcomes of People with Type 1 Diabetes
Accepted at the 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)
One of the benefits of Do-it-yourself Artificial Pancreas Systems (DIYAPS) over commercially available systems is the high degree of customization possible through various features developed by the community. This paper investigates the impact of thirteen commonly used custom features on the glycemic outcomes of users with type 1 diabetes. Significant differences were observed in the group using the Automated Microbolus, Autotune (automatic), and the Superbolus feature. As many of the features aim to improve not only glycemic outcomes but also reduce the burden of managing diabetes on the user, future studies should investigate the impact of these features on the quality of life of their users. This paper expands the existing knowledge on the DIYAPS for people with type 1 diabetes which have been gaining popularity among the patient population in recent years.
Optimal Deployment in Emergency Medicine with Genetic Algorithm Exemplified by Lifeguard Assignments
Accepted at the 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)
In emergency medicine, workforce planning needs to satisfy a number of constraints. There are hard constraints regarding qualifications and soft constraints regarding the wishes of the personnel. One instance of such a planning problem is the assignment of lifeguards at the coasts of the North Sea and the Baltic Sea in Germany. These lifeguards are volunteers and thus accounting for wishes is crucial while qualification constraints must be satisfied nevertheless. This paper presents a genetic algorithm that solves this problem with sub-second runtime. We compare this genetic algorithm to a brute force solution creating optimal solutions at the expense of larger runtime complexity. The genetic approach outperforms the brute force approach in terms of runtime when there are more than 3 places of deployment while consistently producing optimal solutions within less than 10 generations.
