PO-655-07 AUTOMATIC DETECTION OF CONGENITAL LONG QT SYNDROME ON ECG WITH DEEP NEURAL NETWORKS

Abstract

Congenital long QT syndrome (LQTS) is a channelopathy associated with syncope, polymorphic VT, and rarely sudden arrhythmic death. While often detected by QT prolongation on the resting ECG, 50% of patients have a normal or borderline QT interval, necessitating further investigation (i.e. exercise treadmill and genetic testing). A deep neural network may accurately identify latent LQTS using the resting ECG.