Postdoc Position Data Science and Artificial Intelligence in Cardiac Electrophysiology

Postdoc Position Data Science and Artificial Intelligence in Cardiac Electrophysiology

You just finished your PhD trajectory and looking for the next step in your academic career? Your interests lie in the field of machine learning techniques, particularly artificial neural networks, and deep learning? And you would like to continue your research on clinically relevant topics? If yes, then Maastricht University has a new challenge for you!

• Our goal: the development of multimodal prediction models to detect and predict atrial fibrillation (AF) and other clinically relevant cardiac rhythm patterns, predict disease progression and treatment response, and support personalised AF management.
• Your colleagues: The Department of Physiology at Maastricht University is a key academic partner in AF-B-STEP, contributing expertise in AF burden quantification, AI-based rhythm analysis, and digital biomarkers. The department has a strong data science environment, with an additional team of three to four data scientists working across related cardiovascular research projects. As part of the Innovative Health Initiative (IHI) project AF-B-STEP (Quantifying Atrial Fibrillation Burden to inform Screening, Treatment, and hEalth Policy, (Use the "Apply for this Job" box below).),
  
  we aim to establish atrial fibrillation (AF) burden as a novel biomarker for precision medicine. AF-B-STEP brings together leading academic institutions, medical device manufacturers, pharmaceutical companies and wearable technology developers to integrate and analyse one of the world's largest collections of AF burden data, comprising more than 400,000 individuals and 200,000 patient-years of linked clinical outcome data.

For this project, the Department of Physiology at the Cardiovascular Research Institute Maastricht (CARIM) has a vacancy for a postdoctoral researcher in Data Science and Artificial Intelligence. In this position you will develop advanced computational methods for the analysis of large-scale multimodal cardiovascular data, including electrocardiograms, cardiac device recordings, wearable sensor data, clinical trial data, electronic health records and patient-reported outcomes.

Research activities will include AI-assisted signal analysis, transformer-based analysis of structured and unstructured clinical data, automated data harmonisation, clustering of AF burden phenotypes, and the development of multimodal prediction models to identify clinically relevant disease patterns, predict disease progression and treatment response, and support personalised AF management.

The postdoctoral researcher will develop, implement and validate state-of-the-­art machine learning methods, ranging from deep learning and transformer architectures to unsupervised learning and representation learning approaches. You will work in close collaboration with clinicians, AI researchers, statisticians, and industrial partners in a highly interdisciplinary consortium, translating large‑scale cardiovascular data into clinically applicable tools for precision medicine.

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

• You have completed a PhD in data science and/or artificial intelligence.
• You have gained knowledge of various machine learning techniques, particularly artificial neural networks and deep learning and would like to further develop this knowledge.
• In previous roles you have worked with the application of data science and artificial intelligence in the context of biomedical signals.
• You enjoy the process of conceiving and writing papers (in English) and have the ambition to produce high quality research outcomes.
• Familiarity with concepts from the field of computational cardiac electrophysiology and cardiac measurement modalities is considered an advantage.

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

We offer an interdisciplinary and collaborative postdoc project embedded into a highly international institute, which is one of the leading…