Predicting Atrial Fibrillation After Stroke by Combining Polygenic Risk Scores and Clinical Features

Patients diagnosed with ischemic stroke at the Massachusetts General Hospital between 2003 and 2017 were included. Clinical AF risk was estimated using the Recalibrated Cohorts for Heart and Aging Research in Genomic Epidemiology Atrial Fibrillation model, and genetic risk was estimated using a contemporary AF PRS from 1 093 050 variants. Patients were divided into clinical and genetic risk tertiles. Cox proportional hazards models at different follow-up windows were fit, and C indices and percentile-based net reclassification index were used to determine the improvement of clinical risk models with the addition of AF PRS.