%0 Journal Article
%T Artificial intelligence-enabled electrocardiogram to distinguish atrioventricular re-entrant tachycardia from atrioventricular nodal re-entrant tachycardia.
%A Sau A
%A Ibrahim S
%A Kramer DB
%A Waks JW
%A Qureshi N
%A Koa-Wing M
%A Keene D
%A Malcolme-Lawes L
%A Lefroy DC
%A Linton NWF
%A Lim PB
%A Varnava A
%A Whinnett ZI
%A Kanagaratnam P
%A Mandic D
%A Peters NS
%A Ng FS
%J Cardiovasc Digit Health J
%V 4
%N 2
%D 2023 Apr
%M 37101944
暂无%R 10.1016/j.cvdhj.2023.01.004
%X <B>UNASSIGNED: </B>Accurately determining arrhythmia mechanism from a 12-lead electrocardiogram (ECG) of supraventricular tachycardia can be challenging. We hypothesized a convolutional neural network (CNN) can be trained to classify atrioventricular re-entrant tachycardia (AVRT) vs atrioventricular nodal re-entrant tachycardia (AVNRT) from the 12-lead ECG, when using findings from the invasive electrophysiology (EP) study as the gold standard.<BR><B>UNASSIGNED: </B>We trained a CNN on data from 124 patients undergoing EP studies with a final diagnosis of AVRT or AVNRT. A total of 4962 5-second 12-lead ECG segments were used for training. Each case was labeled AVRT or AVNRT based on the findings of the EP study. The model performance was evaluated against a hold-out test set of 31 patients and compared to an existing manual algorithm.<BR><B>UNASSIGNED: </B>The model had an accuracy of 77.4% in distinguishing between AVRT and AVNRT. The area under the receiver operating characteristic curve was 0.80. In comparison, the existing manual algorithm achieved an accuracy of 67.7% on the same test set. Saliency mapping demonstrated the network used the expected sections of the ECGs for diagnoses; these were the QRS complexes that may contain retrograde P waves.<BR><B>UNASSIGNED: </B>We describe the first neural network trained to differentiate AVRT from AVNRT. Accurate diagnosis of arrhythmia mechanism from a 12-lead ECG could aid preprocedural counseling, consent, and procedure planning. The current accuracy from our neural network is modest but may be improved with a larger training dataset.