PhD in Epidemiology value-of-information from validating clinical prediction models and AI

Welcome to Maastricht University!

Join Maastricht University as a PhD student in Epidemiology, advancing interdisciplinary methods to ensure reliable AI in healthcare through innovative statistical and health‑economic approaches. You will develop value‑of‑information measures and software that help determine when an AI model is ready for use and when more research is needed.

• Our goal:
  Develop value‑of‑information methods to assess and improve the reliability of clinical prediction models and AI.
• Your colleagues: A VIDI project team with 2 PhD students and 1 postdoctoral researcher, supervised by Dr. Laure Wynants, working with clinicians, statisticians, epidemiologists, health economists and data scientists.

Clinical prediction models and Artificial intelligence (AI) can support diagnosis and prognosis, and support optimisation of patient care. Whether this is achievable depends on the reliability of an AI model. Testing of AI is often done on small numbers, and AI models are not equally useful in all locations and patient populations. Reliability can be measured with value‑of‑information measures that reflect the risks of uncertainty, expressed as the expected number of misdiagnoses.

This allows physicians and policymakers to decide for each AI model: is it ready for use, or is more research needed?

In this project, you will develop and refine these value‑of‑information measures. In this role, you will conduct interdisciplinary research at the intersection of statistics and health economics to assess and enhance the reliability of AI models in healthcare. To support the dissemination of your methods, you will contribute to user‑friendly statistical software, such as an R package, and develop guidance material for other researchers.

You will share your findings through academic publications, conference presentations, and engagements with stakeholders. Additionally, you will actively contribute to the institute’s academic environment by participating in seminars, workshops, and collaborative research.

Your daily worksite is the Department of Epidemiology at Maastricht University. Your day‑to‑day tasks and responsibilities are to:

• Develop new predictive performance and value‑of‑information metrics.
• Propose computational algorithms to estimate these metrics.
• Design and execute simulation studies to evaluate the above.
• Develop and test statistical software.
• Write user‑friendly guidance on how to apply novel methodology.
• Deepen subject‑matter knowledge through literature review and active engagement with current research developments.
• Work closely with academic advisors and collaborators to ensure research quality.
• Write up, publish and present findings, and assist with teaching duties.

Are you ready to set the course for the years ahead? Then we’d love to meet you.

We’re not looking for check boxes; we’re interested in who you are and what you bring. Do you recognise yourself in this?

• Strong analytical and interdisciplinary mindset – You enjoy bridging medical statistics and health economics, and thrive in a dynamic research environment.
• Academic foundation – You have a Master’s degree in Statistics, Health‑Economics, or equivalent.
• Relevant methods experience – You have knowledge of and/or experience with validation of prediction models (regression or supervised machine learning), health technology assessment, decision curve analysis, and/or value‑of‑information analysis.
• Programming skills – You can program in R, or you are proficient in another language and willing to learn R.
• Clear scientific communication – You master scientific English for speaking, reading, and writing. Knowledge of clinical epidemiology and/or Dutch is an asset.

At Maastricht University, you’ll work in an international, open, and engaged environment.

• Employment contract for 12 months with a scope of 1 FTE. Upon a positive evaluation, an extension of 3 years will follow.
• Good employment conditions. Salary based on experience ranging from € 3059,- to € 3881,- gross per month (38 hours per week). In addition to the…