Identification of supraventricular tachycardia mechanisms with surface electrocardiograms using a convolutional neural network

BACKGROUND It remains difficult to definitively distinguish sup-raventricular tachycardia (SVT) mechanisms using a 12-lead electro-cardiogram (ECG) alone. Machine learning may identify visually imperceptible changes on 12-lead ECGs and may improve ability to determine SVT mechanisms.OBJECTIVE We sought to develop a convolutional neural network (CNN) that identifies the SVT mechanism according to the gold stan-dard of SVT ablation and to compare CNN performance against expe-rienced electrophysiologists among patients with atrioventricular nodal re-entrant tachycardia (AVNRT), atrioventricular recipro-cating tachycardia (AVRT), and atrial tachycardia (AT).METHODS All patients with 12-lead surface ECG during sinus rhythm and SVT and had successful SVT ablation from 2013 to 2020 were included. A CNN was trained using data from 1505 surface ECGs that were split into 1287 training and 218 test ECG datasets. We compared the CNN performance against independent adjudication by 2 experienced cardiac electrophysiologists on the test dataset.RESULTS Our dataset comprised 1505 ECGs (368 AVNRT, 304 AVRT, 95 AT, and 738 sinus rhythm) from 725 patients. The CNN areas un-der the receiver-operating characteristic curve for AVNRT, AVRT, and AT were 0.909, 0.867, and 0.817, respectively. When fixing the specificity of the CNN to the electrophysiologist adjudicators' spec-ificity, the CNN identified all SVT classes with higher sensitivity: (1) AVNRT (91.7% vs 65.9%), (2) AVRT (78.4% vs 63.6%), and (3) AT (61.5% vs 50.0%).CONCLUSION A CNN can be trained to differentiate SVT mecha-nisms from surface 12-lead ECGs with high overall performance, achieving similar performance to experienced electrophysiologists at fixed specificities.