Digital twin integrating clinical, morphological and hemodynamic data to identify stroke risk factors.

Abstract

Stroke remains a leading global cause of mortality, with ischemic stroke as the most common subtype. Atrial fibrillation (AF) increases ischemic stroke risk due to thrombus formation in the left atrium (LA), particularly in the left atrial appendage (LAA). Traditional risk assessments, like the CHA₂DS₂-VASc score, focus on clinical factors but often overlook LA morphology and hemodynamics. Existing studies either use mechanistic models with limited cases or rely solely on clinical data, missing hemodynamic insights. This study integrates statistical and mechanistic models within a Digital Twin framework, using unsupervised Multiple Kernel Learning on 130 AF patients. Combining LA morphology, hemodynamics, and clinical data improved patient stratification, identifying three phenogroups. The highest-risk group exhibited larger atrial dimensions, complex LAA structures, and elevated B-type natriuretic peptide levels. This study underscores the potential of Digital Twin models in assessing thrombus risk, emphasizing the need for further research to refine stroke prediction models.