Abstract WP133: Improvement of Deep Learning Models for Ischemic Stroke Prediction by Integrating Atrial Phenotypic and Genotypic Data Using Repeated Random Sampling Validation

Introduction: Better methods to predict ischemic stroke (IS) would improve stroke prevention. The role of atrial abnormalities other than atrial fibrillation (AF) in causing strokes is uncertain. We developed unimodal and multimodal deep learning models that include atrial traits to improve understanding of their contribution to stroke risk and to develop more accurate ways to predict stroke. Methods: We studied 24,570 people from the UK Biobank for whom cardiac MRI data and EKG data are available; of these, 100 had IS. We built multimodal multi-layer perceptron with late fusion (MMLP-LF) models to predict IS by integrating 5 data modalities: 1) MRI and EKG atrial traits, 2) lead genetic variants (P