PhD Integrative machine learning for oncology and neurology

In current medical decision-making, clinical risk and prediction models play an increasingly important role in determining, accelerating and improving diagnosis, prognosis and/or intervention. The development of diagnostic or predictive models based on clinical, laboratory, genetic and/or imaging variables is now at the core of many clinical research questions. Although medical data is widely available today, these data still pose challenges for clinical models as they are often heterogeneous, multimodal (text, images, tables) and high-dimensional (lots of measurement data) with relatively small numbers of patients.

Would you like to know more about the different phases within the PhD trajectory? You can read more about this on this page.

You will develop new AI methods and foundation models to systematically integrate expert knowledge and external data of different modalities into clinical AI models to improve their performance. These new methods and models address the challenges of heterogeneity, multimodality and high-dimensionality when developing clinical risk models. The project entails methodological development, balanced with implementation and applications in the onco- and neurological field. You will have access to high-quality clinical data from our collaborators.

• You hold an MSc in AI, Mathematics, Bioinformatics, or a closely related discipline;
• You have a background in quantitative modeling enabling the development of new computational methods;  
• You have strong programming skills, preferably in R / Python;
• You are able to explain complex ideas to non-specialists;
• Knowledge of Generative AI, machine learning and deep learning techniques;  
• You have good communication skills (written/oral) in English, you are self-disciplined and can work in a multi-disciplinary environment;
• For Dutch nationals, a VOG (Verklaring Omtrent Gedrag) is mandatory.