Bio
Wouter van Amsterdam is an assistant professor at the University Medical Center Utrecht, working on methods and applications of machine learning and causal inference for health care. His focus is the intersection of machine learning and causal inference. This intersection goes two ways: machine learning can improve typical causal inference tasks such as estimating individual treatment effects and doing prediction-under-intervention. On the other hand, causal inference provides a formal way to understanding and improving prediction model generalization and robustness. Wouter holds degrees in Physics (BSc), Medicine (MD), epidemiology (MSc) and a PhD on machine learning for healthcare.
Master students with a background in statistics or machine learning who want to work with me are welcome to contact me. Students enrolled at Utrecht University or UMC Utrecht can find open master projects on konjoin
Education
University Medical Center Utrecht / Utrecht University
2010 | BSc. Physics
2017 | M.D.
2021 | MSc. Epidemiology (med. statistics track)
2022 | PhD. machine learning for healthcare | co-advised by Rajesh Ranganath from NYU
Experience
UMC Utrecht| Assistant Professor | 2023 - now
Babylon Health | Senior Research Scientist | 2021 - 2023
Selected papers
When accurate prediction models yield harmful self-fulfilling prophecies (arXiv:2312.01210).
van Amsterdam, W. A. C., van Geloven, N., Krijthe, J. H., Ranganath, R., & Ciná, G. (2024). ML4H 2023 findings-track
pdf
Individual treatment effect estimation in the presence of unobserved confounding using proxies: A cohort study in stage III non-small cell lung cancer. van Amsterdam, W. A. C., Verhoeff, J. J. C., Harlianto, N. I., Bartholomeus, G. A., Puli, A. M., de Jong, P. A., Leiner, T., van Lindert, A. S. R., Eijkemans, M. J. C., & Ranganath, R. (2022). Scientific Reports
pdf
Conditional average treatment effect estimation with marginally constrained models.
van Amsterdam, W. A. C., & Ranganath, R. (2023). Journal of Causal Inference
pdf
Decision making in cancer: Causal questions require causal answers.
van Amsterdam, W. A. C., de Jong, P. A., Suijkerbuijk, K. P. M., Verhoeff, J. J. C., Leiner, T., & Ranganath, R. (2022). ArXiv pre-print
pdf
Eliminating biasing signals in lung cancer images for prognosis predictions with deep learning.
van Amsterdam, W. A. C., Verhoeff, J. J. C., de Jong, P. A., Leiner, T., & Eijkemans, M. J. C. (2019). Npj Digital Medicine
pdf
More papers at google scholar
Talks
Date | Title | Subtitle |
---|---|---|
May 7, 2024 | An intro to causal inference and its uses in radiotherapy | ESTRO - Understanding dose-effects: Can we go beyond association - symposium |
Apr 18, 2024 | AI and its (mis)uses in medical research and practice | Infection and Immunity spring meeting |
Mar 12, 2024 | Wouter’s twitter X-peri(ments/ences) | Data Science and Biostatistics department lunch talk |
Aug 10, 2023 | The value of observational causal inference for medical decision making | MLHC causality pre-conference workshop |
Jun 24, 2023 | My risk model is super accurate so it will be useful for treatment decision making, right? Wrong! | CHIL 2023 - lightning talk |
Teaching
- 2024 Introduction to Causal Inference and Causal Data Science summer school
- 2023 Big Data summer school
Posts
Activities
- board member BMS-ANed (Dutch biometrics society, board member)
- coordinator of UMC Utrecht AI methods lab
- ambassador for Applied Data Science of Utrecht University
- co-coordinator of Causal Data Science Special Interest Group of Utrecht University
Contact
wamster3 at umcutrecht dot nl