Learning from Historical data to make better decisions in the future
I work on the intersection of machine learning (for flexible data analysis) and causal inference (to learn to make better decisions).

I am an assistant professor at the University Medical Center Utrecht, working on methods and applications of machine learning and causal inference for health care. I have degrees in Physics (BSc), Medicine (MD), epidemiology (MSc) and a PhD on machine learning for healthcare, advised by Rajesh Ranganath from NYU and Joost Verhoeff, Tim Leiner and Pim de Jong from the UMC Utrecht.

Positions

UMC Utrecht| Assistant Professor | 2023 - now
Babylon Health | Senior Research Scientist | 2021 - 2023

CV (pdf)

News

Together with Maarten van Smeden, I’m recruiting a PhD student. For more information and to apply, see the UMC Utrecht website

I’m a guest editor for a special issue in BMC diagnostic and prognostic research titled “Validation and transparency for AI-based diagnosis and prognosis in healthcare”, together with Maarten van Smeden and Anne de Hond. Submission is open until Jan 31st 2025.

Selected papers

A causal viewpoint on prediction model performance under changes in case-mix: Discrimination and calibration respond differently for prognosis and diagnosis predictions.
van Amsterdam, W. A. C. (2024). arXiv preprint
url pdf

Causal Inference in Oncology: Why, What, How and When.
van Amsterdam, W. A. C., Elias, S., & Ranganath, R. (2024). Clinical Oncology.
url pdf

Prognostic models for decision support need to report their targeted treatments and the expected changes in treatment decisions.
van Amsterdam, W. A. C. and Cinà, Giovanni and Didelez, Vanessa and Keogh, Ruth H. and Peek, Niels and Sperrin, Matthew and Vickers, Andrew J. and van Geloven, Nan and Shalit, Uri (2024). BMJ Rapid-response
url

From algorithms to action: improving patient care requires causality.
van Amsterdam, W. A. C., de Jong, P. A., Verhoeff, J. J. C., Leiner, T., & Ranganath, R. (2024). BMC Medical Informatics and Decision Making
url pdf

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
url 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
url pdf

Conditional average treatment effect estimation with marginally constrained models.
van Amsterdam, W. A. C., & Ranganath, R. (2023). Journal of Causal Inference
url 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
url pdf

More papers on google scholar

Talks

Date Title Subtitle
Sep 26, 2024 An introduction to AI for biostatisticians BMS-Aned seminar
Jul 8, 2024 Medical imaging and AI for decision support Medical Imaging AI lab meeting
May 30, 2024 Uses and pitfalls with AI for decision support - harmful self-fulfilling prophecies WEON masterclass 2024 - AI-based prediction models in healthcare: from development to implementation
May 16, 2024 Causality and prediction: developing and validating models for decision making Causal Data Science Special Interest Group - Utrecht
May 15, 2024 Decision support based on AI in medical imaging AI in medical imaging (AIBIA) parallel session
No matching items

Teaching

Posts

No matching items

Students

  • Su Li (Methodology and Statistics) - MSc. student
  • Florian Metwaly (Methodology and Statistics) - MSc. student

Former

  • Samil Kilinc (Applied Data Science, 2024)
  • Kiara Peek (Applied Data Science, 2024)
  • Myra van Laar (Biomedical Sciences)
  • Gijs Bartholomeus (Medicine)
  • Netanja Harlianto (Medicine)

Activities

Contact

wamster3 at umcutrecht dot nl