Development and Internal Validation of an AI-Driven Model for 5-Year Cardiovascular Disease Risk Prediction in the Canadian Longitudinal Study on Aging

Three deep learning models were developed for 5-year CVD risk prediction using ECG signals, retinal images, and a multimodal combination, each incorporating age, sex, and hypertension status. The ECG-based model achieved AUROC 0.815, benchmarked against Framingham Risk Score, Pooled Cohort Equations, and XGBoost using traditional risk factors. Analyzed 23,142 participants from the Canadian Longitudinal Study on Aging.