Robin P. van de Water

🧠 AI in Health Researcher
🧑‍🎓 PhD in Machine Learning
🏛️ Hasso Plattner Institute
🏠 Berlin, Germany

Researcher and Engineer in AI and Machine Learning for Healthcare

Postdoc in Machine Learning

2026 Hasso Plattner Institute and Institute for Digital Health at Mount Sinai

This work is done in collaboration with the Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, in New York City. The aim is to use data of 12 million patients to train and benchmark foundation models on these patient sequences in a clinically useful manner for downstream application. We want to enable the use of foundation models for AI applications for individual specialties and to provide insights into the generalizability of these models across different healthcare systems. Moreover, we want to add modalities such as pathology and text to the these models to improve their performance and applicability.

PhD in Machine Learning

2021-2026 Hasso Plattner Institute and Charité University Hospital, Graded with Magna Cum Laude

Official title: Doctor rerum naturalium or Dr. rer. nat. (Doctor of Natural Sciences)

As a PhD candidate at the HPI, supervised by Prof. Dr. Christoph Lippert, I worked on a project to develop a predictive approach to detecting complications after surgeries in collaboration with one of the biggest university hospitals in Europe, the Charité. The challenge I faced is to combine multiple data sources and employ different AI/ML techniques to get a risk assessment for doctors to increase the healthspan of patients. These models are designed to support perioperative decision‑making and early‑warning workflows, with implications for ward staffing. Moreover, I have co-founded the Medical Event Data Standard (MEDS) project and started development of Mount Sinai EHR Foundation Models. The published dissertation, Benchmark to Bedside: Building Modular Multimodal Machine Learning Infrastructure for Healthcare at Scale, can be found here. The committee consisted of Padhraic Smyth, Mykola Pechenizkiy, Christoph Lippert, Lothar Wieler, Felix Naumann, and Bernard Renard. The defense slides are openly available here.

  • Supervision
    • Master Theses: Hendrik Schmidt, 2022-2023: Benchmarking Model-agnostic Multi-source Supervised Domain Adaptation for Clinical Prediction on ICU Data. Youssef Mecky: Comparative Analysis of Explainable AI Methods Across Domains for ICU Risk Prediction Models 2023-2024 (paper in progress), Daniela Zuluaga Lotero: Evaluation of Early Warning Systems for Postoperative Complications from Continuous Vital Sign Monitoring in Surgical Wards.
    • Master Project: Alisher Turubayev, Anna Shopova, Fabian Lange, Mahmut Kamalak, Paul Mattes, and Victoria Ayvasky, 2022-2023: Deep Learning Data Generation for Medical Prediction Systems.
    • Course: Statistics in Healthcare, 2022, 2023: Grading and Supervision of final presentation and report.
    • Working Students: Hired and supervised three working students to assist with data engineering and analysis tasks.
  • Talks
    • 2025, Humboldt University Berlin, invited by Ulf Leser.
    • 2025, Danish Pioneer Center for Artificial Intelligence, invited by Mads Nielsen.
    • 2025, NYU, Rajesh Ranganath Group.
    • 2025, Dagstuhl Seminar 2025: Scaling up Clinical ML: Modalities, External Validation, Health Systems. in: From Research to Certification with Data-Driven Medical Decision Support Systems (Dagstuhl Seminar 25052)
    • 2024, HPI Data Cluster Retreat.
    • 2024, University of Lausanne.
    • 2024, Talk at Deutsche Forschungsdatenportal für Gesundheit (FDPG), University of Tübingen, invited by Mila Hardt.
    • 2023, University of California Irvine (UCI), invited by the Department of Computer Science.
    • 2022, Invited talk at ETH Zürich Biomedical Informatics group about Yet another ICU Benchmark.
  • Open source software
  • Activities

Visiting Researcher, Machine Learning

2023 University of California, Irvine

Working with Stephan Mandt’s and Padhraic Smyth’s groups on applying state-of-the-art modelling to patient deterioration problems with clinical and wearable data.

  • Invited as visiting scholar in the framework of the HPI Research Center in Machine Learning and Data Science at UCI
  • Explored new modelling techniques for time series data with missingness and irregular sampling.
  • Visit to Stanford University to discuss collaboration with Nigam Shah’s lab.

Double Master in Data Science

2019-2021 EIT Digital Master School, TU Eindhoven & TU Berlin, with Honours

The EIT Digital Master programme is a selective double degree Master of Science focused on combining technical knowledge and innovation at two renowned European Technical Universities. I studied at Eindhoven University of Technology in the period of 2019-2020 and at the Technical University of Berlin during 2020-2021. This programme includes a minor in entrepreneurship and innovation and is supported by the European Institute of Innovation and Technology (which is part of the EU).

  • GPA – 8.5 [4.0/4.0] (Cum Laude) 151 ECTS
  • Thesis “A Semi-automated Training Data Generation Approach with the Human-in-the-Loop.” at the Database Systems and Information Management Group of TU Berlin
    • Under supervision of Prof. Volker Markl, Dr. Jorge-Arnulfo Quiané-Ruiz, Dr. Francesco Ventura & Dr. Zoi Kaoudi
    • Within the Agora Ecosystem and based on the DataFarm System.
    • Including two peer-reviewed publications at A* conferences (and best demonstration award).
  • Awarded the EIT Digital Excellence Scholarship
  • Participant of the Honors Academy at TU/e: Honours programme of 20 ECTS for Personal Leadership
  • Including courses: Advanced Algorithms, Cloud Computing, Discrete Event Systems, Speech Analysis, Scalable Data Science, Statistical Learning Theory, Advanced Statistics, Visualization, Data Mining, Data Engineering, Process Mining and Technology Entrepreneurship
  • With Innovation Space Project in interdisciplinary team for Signify (Philips Lighting), Cyclomedia and the TU/e Intelligent Lighting Institute
  • Selected for the Semi-Professional Race Rowing team at E.S.R Thêta

Bachelor of Computer Science

2016-2019 Utrecht University, with Honours

During my time at Utrecht University, I have developed skills for problem solving and reasoning. I have taken many different courses in Computer Science and other disciplines.

  • GPA – 8.28, [4.0/4.0] (Cum Laude) 218.5 ECTS
  • Descartes Honours Programme (30 ECTS): Focused on broad academic development through lectures from prominent figures in society and projects with students from other disciplines
  • Minor in Mathematics
  • Including courses: Data Analysis and Retrieval, Algorithms, Intelligent Systems, Computational Intelligence, Optimisation & Complexity, Concurrency, Graphics, Functional Programming and Data-structures
  • Bachelor software project in automated medical reporting with semantic interpretation
  • Co-author of the “The Care2Report System: Automated Medical Reporting as an Integrated Solution to Reduce Administrative Burden in Healthcare” paper, written with the department of Computer Science, presented at the HICSS-53 conference.

📄 Publications

  • Matthew McDermott, Ethan Steinberg, Jason Fries, Robin P. van de Water, Chao Pang, Patrick Rockenschaub, Pawel Renc, Jungwoo Oh, Kamilė Stankevičiūtė, Justin Xu, Tom Joseph Pollard, Nassim Oufattole, Michael Wornow, Teya Bergamaschi, Hyewon Jeong, Simon Lee, Vincent Jeanselme, Kiril Klein, Mikkel Odgaard, Maria Elkjær Montgomery, Arkadiusz Sitek, Mads Nielsen, Jeffrey Chiang, Noa Dagan, Isaac Kohane, Shalmali Joshi, Edward Choi, and Nigam Shah, MEDS: A Simple, Interoperable Data Standard and Ecosystem for Health AI Research, Accepted to NEJM AI, to appear in vol:3, iss:6 (2026).
  • Robin P. van de Water, Hendrik Schmidt, and Patrick Rockenschaub, ReciPies: A Lightweight Data Transformation Pipeline for Reproducible ML, Journal of Open Source Software (JOSS) (2026)
  • Matthias Kirchler, Matteo Ferro, Veronica Lorenzini, Robin P. van de Water, Christoph Lippert, and Andrea Ganna, Large Language Models Improve Transferability of Electronic Health Record-Based Predictions across Countries and Coding Systems, Published at NPJ Digital Medicine (2026)
  • Katharina Alefs, Susanne Ibing, Pia Francesca Rissom, Jan Carlo Schmid, Arkadiusz Kwasigroch, Robin van de Water, Bernhard Y. Renard, and Eugenia Alleva, Towards Foundation Model-Based Propensity Score Matching from Electronic Health Records, Machine Learning for Health Symposium 2025
  • Matthew B. A. McDermott, Justin Xu, Teya S. Bergamaschi, Hyewon Jeong, Simon A. Lee, Nassim Oufattole, Patrick Rockenschaub, Kamilė Stankevičiūtė, Ethan Steinberg, Jimeng Sun,Robin P. van de Water, Michael Wornow, John Wu, and Zhenbang Wu, MEDS: Building Models and Tools in a Reproducible Health AI Ecosystem, Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2, Toronto ON Canada: ACM, Aug. 2025
  • Robin P. van de Water, Scaling Up Clinical ML from Datasets to Entire Health Systems through the MEDS Ecosystem, SBHD 2025 International Conference on Systems Biology of Human Diseases, Berlin, June 2025
  • Max M. Maurer, Bjarne Pfitzner, Robin P. van de Water, Lara Faraj, Christoph Riepe, Daniela Zuluaga, Felix Krenzien, Nathanael Raschzok, Robert Siegel, Christian Schineis, Bert Arnrich, Katharina Beyer, Johann Pratschke, Igor M. Sauer, and Axel Winter, Privacy Preserving Federated Learning for 90-Day Mortality Prediction in Colorectal Surgery: A Multicenter Retrospective Development and Comparison Study, International Journal of Surgery (London, England), Aug. 2025
  • Axel Winter, Bjarne Pfitzner, Robin P. van de Water, Lara Faraj, Christoph Riepe, Wolf-Heinrich Hahn, Felix Krenzien, Christian Schineis, Thomas Malinka, and Wenzel Schöning, Overcoming the Data Barrier: Transfer Learning for 90-Day Mortality Prediction in General Surgery–a Retrospective Multicenter Development and Comparison Study, International Journal of Surgery, 2025
  • Bjarne Pfitzner, Max M. Maurer, Axel Winter, Christoph Riepe, Igor M. Sauer, Robin van de Water, Christian Denecke, Johann Pratschke, and Bert Arnrich, Differentially-Private Federated Learning with Non-IID Data For Surgical Risk Prediction, International Journal of Semantic Computing 19.3, 2025
  • Christoph Riepe, Robin van de Water, Axel Winter, Bjarne Pfitzner, Lara Faraj, Robert Ahlborn, Maximilian Schulze, Daniela Zuluaga, Christian Schineis, Katharina Beyer, Johann Pratschke, Bert Arnrich, Igor M Sauer, Max M Maurer, 90-Day mortality prediction in elective visceral surgery using machine learning: a retrospective multicenter development, validation and comparison study
  • M. B. A. McDermott et al. (MEDS-DEV Working Group), “MEDS Decentralized, Extensible Validation (MEDS-DEV) Benchmark: Establishing Reproducibility and Comparability in ML for Health,” ML4H Demo Track, Nov. 2024, Accessed: Dec. 24, 2024.
  • R. van de Water, H. Schmidt, P. Elbers, P. Thoral, B. Arnrich, and P. Rockenschaub, ‘Yet Another ICU Benchmark: A Flexible Multi-Center Framework for Clinical ML’. arXiv, Jun. 08, 2023. Available: http://arxiv.org/abs/2306.05109, accepted at the 12th International Conference on Learning Representations (ICLR) 2024.
  • A. Winter, R. van de Water, 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, Art. no. 17, Jan. 2024, doi: 10.3390/cancers16173000.
  • B. Arnrich, E. Choi, J.A. Fries, M.B.A. McDermott, J.Oh, T.J. Pollard, N. Shah, E. Steinberg, M. Wornow, R. van de Water, (MEDS working group, alpabethized authors) An ML-oriented Interface for Medical Record Datasets, https://github.com/Medical-Event-Data-Standard, accepted at Time Series for Health (TS4H) at ICLR 2024
  • R.van de Water, A. Winter, M. Maurer, F. Treykorn, I. Sauer, B Pfitzner, B. Arnrich, Combining Time Series Modalities to Create Endpoint-driven Patient Records, Accepted at Workshop for Data Centric ML at ICLR 2024
  • R.van de Water, A. Winter, M. Maurer, F. Treykorn, I. Sauer, B Pfitzner, B. Arnrich, Combining Hospital-grade Clinical Data and Wearable Vital Sign Monitoring to Predict Surgical Complications, Accepted at Workshop for Timeseries For Health (TS4H) at ICLR 2024
  • B. Pfitzner, M. M. Maurer, A. Winter, C. Riepe, I. M. Sauer, R. van de Water, Bert Arnrich, Differentially-Private Federated Learning with Non-IID Data For Surgical Risk Prediction, First IEEE International Conference on AI for Medicine, Health, and Care (2024)
  • A. Winter, R. van de Water et al., Advancing Preoperative Outcome Prediction: A Comparative Analysis of Machine Learning and ISEG Risk Score for Predicting 90-Day Mortality after Esophagectomy, 2023, accepted at the 141st Congress of the German Society of Surgery (2024)
  • O. Konak, R. van de Water et al., ‘HARE: Unifying the Human Activity Recognition Engineering Workflow’, accepted at MDPI Sensors 2023
  • 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’. arXiv, Jul. 06, 2023. doi: 10.48550/arXiv.2307.02906. accepted at iWOAR 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), 2022, pp. 3186–3189. (Best demo award 2022)
  • 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–’, presented at the Conference on Innovative Data Systems Research (CIDR), 2022.
  • L. Maas, M. Geurtsen, F. Nouwt, S. Schouten, R. van de Water, S. van Dulmen, F. Dalpiaz, K. van Deemter, S. Brinkkemper ‘The Care2Report system: automated medical reporting as an integrated solution to reduce administrative burden in healthcare’, in Information technology in healthcare: IT architectures and implementations in healthcare environments, Hawaii International Conference on System Sciences (HICSS), 2020.

Under review

  • Robin P. van de Water, Axel Winter, Daniela Zuluaga Lotero, Bjarne Pfitzner, Lara Faraj, Bert Arnrich, Patrick Rockenschaub, Wenzel Schoning, Thomas Malinka, Christian Denecke, Johann Pratschke, Igor M. Sauer, and Max M. Maurer, Continuous Multimodal AI with Wearable Vital Signs Predicts Postoperative Complications in the General Ward, Nov. 2025, doi: 10.1101/2025.11.25.25340950, medRxiv: 2025.11.25.25340950 under review at The Lancet Digital Health (2026)
  • Jan Carlo Schmid, Susanne Ibing, Stefan Kalabakov, Katharina Alefs, Robin P. van de Water, Arkadiusz Kwasigroch, Eugenia Alleva, Bert Arnrich, Bernhard Y. Renard, and Maia Kayal, Expert-Defined, Chart-Reviewed Features Outperform EHR Foundation Models for Predicting Crohn’s-like Disease of the Pouch, Under review at The American Journal of Gastroenterology (2025)

Preprints / In preparation

  • Robin P. van de Water, Christoph Riepe, Bjarne Pfitzner, Lara Faraj, Daniela Zuluaga, Christian Schineis, Katharina Beyer, Johann Pratschke, Igor Sauer, Axel Winter, and Max Maurer, Machine Learning for 30-Day Mortality Prediction for High-Risk General Emergency Surgery, In preparation (2025)
  • Alisher Turubayev, Anna Shopova, Fabian Lange, Mahmut Kamalak, Paul Mattes, Victoria Ayvasky, Bert Arnrich, Bjarne Pfitzner, and Robin P. van de Water, Closing Gaps: An Imputation Analysis of ICU Vital Signs, Oct. 2025, doi: 10.48550/arXiv.2510.24217, arXiv: 2510.24217 [cs]
  • Wouter van Amsterdam, Michael Kamp, Rajesh Ranganath, Robin P. van de Water, Florian Markowetz, Evangelia Christodoulou, Yamuna Krishnamurthy, Christoph Lippert, Jeff Clark, Julia E. Vogt, Raul Santos-Rodriguez, Thomas Gärtner, Gilbert Koch, and Brett Beaulieu-Jones, Missing Incentives, Missing Oversight: The Challenges of AI Monitoring in Clinical Practice, 2025

✨ Honours

Best Demonstration Paper Award at ICDE

Received “Best Demonstration” Award from IEEE International Conference on Data Engineering (ICDE) 2022. Elaboration of the jury: “The award committee members have chosen your demonstration unanimously both based on the relevance of the problem, the high potential of the proposed approach and the excellent presentation.” More information here, video here.

Finalist at the Bionnale Speed Lecture Award

I was a finalist at the Bionnale 2022 Speed Lecture Award. Here I presented my doctoral research topic with the topic: “Dr. Droid and the Curious Case of Complication Prevention”. The presentation focused on communicating the possibilities and challenges of predicting post-surgery complications using hetereogeneous patient data. The presentation was recorded and can be viewed here

Honors Academy Master

Selected for the Honors Academy Master: a program consisting of 20 ECTS where you orient yourself in your professional career and choose your own program of professional development.

EIT Digital Excellence Scholarship

Awarded the highest scholarship for the selective Dual Degree MSc in Data Science (with minor in entrepreneurship) at the TU Eindhoven and TU Berlin.

💼 Experience

Guest Scientist at the Icahn School of Medicine at Mount Sinai

2024-now
Using retrospective data of 12 million patients to train and benchmark foundation models for clinical prediction tasks in collaboration with the Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, in New York City.

Guest Scientist at Charité University Hospital, Berlin

2021-now
Several collaborations and publications with the Charité University Hospital, Berlin’s biggest hospital.

Research Assistant at the Hasso Plattner Institute Digital Health Center

2021-now
Responsible for supervising Master Theses, Master Projects and grading of individual students. Performing Scientific Data Analysis and Data Engineering for the Charité Academic Hospital.

Research Assistant at German Institute of Artificial Intelligence (DFKI)

2021
Worked on the Agora project, an open platform bringing together data, algorithms, models and computational resources.

Ambassador of the EIT Digital Master School

2020-2021
Representative of my Master School where I organise events, answer questions from prospective students and represent the master school in several capacities.

Education assistant for the Science Faculty of Utrecht University

2018-2019
Reviewed and graded code, diagrams and documentation. I developed teaching and organisational skills.

  • Managed a class of 60 students and assisted with their practical assignments
  • Supervised finals with 300 participants

Organisation committee study excursion

2018-2019
Organised an educational exchange to Sofia of the Descartes Honours Programme

  • Organised educational activities for 35 students and 3 supervisors
  • Developed parts of the programme curriculum and managed university funds

🧑‍💻Projects

  • 💊​MEDS: An ecosystem for high-capacity Health AI
  • 🧪Yet Another ICU Benchmark: A framework for benchmarking EHR tasks accross (open-access) datasets
  • 🥧ReciPys: A simple, declarative framework for defining preprocessing pipelines for ML-based data management systems
  • 🧑‍🌾GUIDatafarm: A human-in-the-loop ML-based query optimizer data generator
  • 📃Care2Report An automated ontology-matching based reporting tool

🔧 Skills

Technologies

Python (a.o Pytorch, Tensorflow, Keras, Pandas), Embedding models, LLM integrations, C#, R, Spark, Haskell, Prolog, SQL, Java, SAS, Tableau, Matlab, AWS, Google Cloud, Flink, JavaScript, Unity, OWL, HTML&CSS, Figma

Theoretic

Machine learning, Statistics, Linear algebra, Statistical learning, Software

Soft skills

SCRUM, Scientific & Creative writing, Scientific presenting, Entrepreneurial pitching, Design Thinking, Chairing meetings, Leading teams

🎲 Miscellaneous Education

  • UX Design Certificate, 2020-2021, TechLabs Digital Shaper Program
  • Big Data Analytics Summer School, 2020, KTH Royal Institute of Technology
  • Education Assistant Training, 2018, Faculty of Social Sciences, Utrecht University
  • Academic Writing Training, 2018, Skills Lab, Utrecht University

💬 Languages

  • Dutch - Native
  • English - Fluently - Cambridge University (2016) CPE CEFR C2 level
  • German - Professional - TU Berlin (2021) CEFR C1 level

🛝 Interests

  • 🚣Rowing
  • 🖼️Galleries and art history
  • 🏃‍♂️(Marathon) Running (M PR 2:59:16, HM PR: 1:20:54)

  • 🎸Playing guitar and drums