Atrial fibrillation (AF) is a common and serious cardiac arrhythmia that significantly increases morbidity and mortality in intensive care unit (ICU) patients. Early detection and accurate prediction of AF episodes are essential for timely intervention, but current monitoring approaches are often reactive and may miss subtle warning signs.

This project aims to develop advanced AI-driven tools for the early detection and prediction of atrial fibrillation in ICU patients. By integrating continuous physiological monitoring data with electronic health records, we seek to identify predictive patterns and novel biomarkers associated with AF onset. Our goal is to provide clinicians with real-time, objective decision support to improve patient outcomes, reduce ICU complications, and optimize resource allocation.

This project is a collaboration between the qurAI group and the ICU team at Amsterdam UMC