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

Satoshi Higuchi; Roland Li; Edward P Gerstenfeld; L Bing Liem; Sung Il Im; Shadi Kalantarian; Minhaj Ansari; Sean Abreau; Joshua Barrios; Melvin M Scheinman; Geoffrey H Tison

doi:10.1016/j.hroo.2023.07.004

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

Heart Rhythm O2. 2023 Jul 13;4(8):491-499. doi: 10.1016/j.hroo.2023.07.004. eCollection 2023 Aug.

Authors

Affiliations

¹ Section of Cardiac Electrophysiology, Division of Cardiology, University of California, San Francisco, San Francisco, California.
² Division of Cardiology, Department of Medicine, University of California, San Francisco, San Francisco, California.
³ Division of Cardiology, San Francisco VA Medical Center, San Francisco, California.
⁴ Bakar Computational Health Sciences Institute, University of California, San Francisco, San Francisco, California.

Abstract

Background: It remains difficult to definitively distinguish supraventricular tachycardia (SVT) mechanisms using a 12-lead electrocardiogram (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 standard of SVT ablation and to compare CNN performance against experienced electrophysiologists among patients with atrioventricular nodal re-entrant tachycardia (AVNRT), atrioventricular reciprocating 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 under 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' specificity, 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 mechanisms from surface 12-lead ECGs with high overall performance, achieving similar performance to experienced electrophysiologists at fixed specificities.

Keywords: Artificial intelligence; Convolutional neural network; Electrocardiogram; Long RP tachycardia; Machine learning; Supraventricular tachycardia.