I specialize in using predictive modelling methods to derive insights from clinical data, thereby prolonging the life of patients. I am currently working on the CASSANDRA project aimed at developing a predictive approach to detecting complications after surgeries in collaboration with Berlin’s biggest hospital, the Charité. The challenge I face is to combine multiple data sources and employ different AI/ML techniques to get a risk assessment for doctors to increase the survival rate. More information can be found on my personal website.

Work Experience

• 2021: Research Assistant and developer at the German Research Institute for Artificial Intelligence (DFKI), Berlin

• 2019: Teaching Assistant at Utrecht University, Utrecht

Education

• 2019 - 2021: Computer Science and Data Science (M.Sc./M.Eng.) dual degree at Eindhoven University of Technology and Technische Universität Berlin

• 2016- 2019: Computer Science (B.Sc.) at Utrecht University

• Clinical Machine Learning
• Time Series Analysis and Prediction
• Clinical Data Processing and Data Engineering
• Use of Machine Learning for Complication Prediction

Project

CASSANDRA - Clinical ASSist AND aleRt Algorithms in visceral surgery

• Master thesis of Hendrik Schmidt: Domain Adaptation for Machine Learning on Multi-Modal ICU Data
• Master Project: Deep Learning Data Generation for Medical Prediction Systems WiSe 2022/2023

A. Winter et al., ‘Enhancing Preoperative Outcome Prediction: A Comparative Retrospective Case–Control Study on Machine Learning versus the International Esodata Study Group Risk Model for Predicting 90-Day Mortality in Oncologic Esophagectomy’, Cancers, vol. 16, no. 17, p. 3000, 2024.

R. van de Water et al., ‘Combining hospital-grade clinical data and wearable vital sign monitoring to predict surgical complications’, in ICLR 2024 workshop on learning from time series for health, 2024. [Online]. Available: https://openreview.net/forum?id=EzNGSRPGa7

R. van de Water et al., ‘Combining time series modalities to create endpoint-driven patient records’, in ICLR 2024 workshop on data-centric machine learning research (DMLR): Harnessing momentum for science, 2024. [Online]. Available: https://openreview.net/forum?id=0NZOSSBZCi

B. Pfitzner et al., ‘Differentially-Private Federated Learning with Non-IID Data for Surgical Risk Prediction’, in 2024 IEEE First International Conference on Artificial Intelligence for Medicine, Health and Care (AIMHC), IEEE, 2024, pp. 120–129. Accessed: Oct. 23, 2024. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/10504325/

MEDS Working Group, ‘Medical Event Data Standard (MEDS): Facilitating Machine Learning for Health’, 2024, Accessed: Oct. 23, 2024. [Online]. Available: https://openreview.net/forum?id=IsHy2ebjIG

R. van de Water, H. N. A. Schmidt, P. Elbers, P. Thoral, B. Arnrich, and P. Rockenschaub, ‘Yet Another ICU Benchmark: A Flexible Multi-Center Framework for Clinical ML’, presented at the The Twelfth International Conference on Learning Representations, Oct. 2023. Accessed: Apr. 12, 2024. [Online]. Available: https://openreview.net/forum?id=ox2ATRM90I

O. Konak, A. Wischmann, R. Van De Water, and B. Arnrich, ‘A Real-time Human Pose Estimation Approach for Optimal Sensor Placement in Sensor-based Human Activity Recognition’, in Proceedings of the 8th international Workshop on Sensor-Based Activity Recognition and Artificial Intelligence, Lübeck Germany: ACM, Sep. 2023, pp. 1–6. doi: 10.1145/3615834.3615848.

O. Konak et al., ‘HARE: Unifying the Human Activity Recognition Engineering Workflow’, Sensors, vol. 23, no. 23, p. 9571, 2023.

R. Van De Water, F. Ventura, Z. Kaoudi, J.-A. Quiané-Ruiz, and V. Markl, ‘Farming Your ML-based Query Optimizer’s Food’, in 2022 IEEE 38th International Conference on Data Engineering (ICDE), IEEE, 2022, pp. 3186–3189. Accessed: Oct. 23, 2024. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/9835175/

R. Van De Water, F. Ventura, Z. Kaoudi, J. Quiane-Ruiz, and V. Markl, ‘Farm Your ML-based Query Optimizer’s Food!–Human-Guided Training Data Generation–’, in CIDR, 2022. Accessed: Oct. 23, 2024. [Online]. Available: https://www.cidrdb.org/cidr2022/papers/a37-water.pdf

L. Maas et al., ‘The Care2Report System: Automated Medical Reporting as an Integrated Solution to Reduce Administrative Burden in Healthcare.’, in HICSS, 2020, pp. 1–10. Accessed: Oct. 23, 2024. [Online]. Available: https://core.ac.uk/download/pdf/286030500.pdf