PhD in Machine Learning in Medicine

UniBE is ambitious.
With us, you deliver top performance and test your skills against the best. Chronic diseases often develop gradually over years, and their trajectories vary widely between individuals. Understanding this progression is key to early detection and timely intervention. Large multimodal health datasets combining medical imaging, wearable sensor data and clinical measurements now make it possible to study disease progression from multiple perspectives.

The goal of this project is to develop machine learning methods that learn from multimodal health data to characterise and model disease progression. Methodological focus areas the candidate may explore include:

• Multimodal representation learning across imaging, time series and tabular data
• Disease progression modelling from cross-sectional and sparse longitudinal data
• Causal machine learning to disentangle disease progression from treatment effects
• Learning with missing modalities and irregularly sampled signals
• Fairness and bias in multimodal models across demographic subgroups

We are looking for a curious and motivated PhD candidate with a keen interest in doing machine learning research in the healthcare space. You should hold a Master's degree in a quantitative discipline such as computer science, machine learning, statistics, biomedical or electrical engineering, or similar. You have solid knowledge of the foundations of machine learning, are willing to dig deep to understand a problem, and have strong analytical skills. You have practical experience implementing and evaluating machine learning models in Python. Experience processing biomedical data (imaging, wearable, tabular) is a plus. Strong research infrastructure and international network