Development and Validation of the AI-HeartAge Model in Framingham and UK Biobank
Arterial pressure waveform shape conveys information regarding interactions between the left ventricle and aorta that could provide an estimate of biological heart age and cardiovascular disease risk. Artificial intelligence heart age (AI-HA) was estimated by averaging results from two convolutional neural networks trained to predict mitral annulus tissue Doppler e’ and s’ peak velocities using an uncalibrated arterial tonometry or photoplethysmography waveform as input. In Cox models that adjusted for PREVENT risk factors, AI-HA was associated with incident heart failure during 10 years of follow up in Framingham Heart Study and UK Biobank participants. AI-HA is a novel and accessible measure of accelerated heart aging and heart failure risk in community-based samples.