Comparing Machine Learning Approaches for Predicting CFD-Derived Stroke Risk Indicators in Atrial Fibrillation Patients
Paolo Melidoro, Riccardo Cavarra, Samia Mostafa, Gregory Y.H. Lip, Magdalena Kliś, Steven Edwin Williams, Oleg V. Aslanidi, Adelaide de Vecchi
This paper develops a computational fluid dynamics model of the left atrium in atrial fibrillation patients and uses machine learning to predict stroke risk indicators, finding that deep learning models achieve high accuracy.
bioRxiv · Jun 8, 2026 · PreprintBioengineering