Deep learning detects heart failure with preserved ejection fraction using a baseline electrocardiogram

This study included two patient cohorts. In the derivation cohort, we included n 1884 patients who presented with exertional dyspnea or equivalent and preserved ejection fraction ( 50%) and clinical suspicion for coronary artery disease. The ECGs were divided in segments, yielding a total of 77.558 samples. We trained a convolutional neural network (CNN) to classify HFpEF and control patients according to ESC criteria. An external group of 203 volunteers in a prospective heart failure screening program served as validation cohort of the CNN.