EP News: Basic and Translational

Hannun et  al (Nat Med 2019;25:65, PMID 30617320) developed a deep neural network (DNN) to classify 12 rhythm classes, ranging from supraventricular to ventricular tachycardia, using 91,232 single-lead electrocardiograms (ECGs) from 53,549 patients who used a single-lead ambulatory ECG monitoring device. The DNN was then validated against an independent test data set by a consensus committee of board-certified practicing cardiologists. The authors reported that the DNN achieved an average area under the receiver operating characteristic curve of 0.97.
Source: Heart Rhythm - Category: Cardiology Authors: Tags: EP News Source Type: research