Diagnostic performance of machine learning on 12-lead electrocardiogram for predicting multi-vessel coronary vasospastic angina

Abstract

Abstract Background Multi-vessel coronary vasospastic angina (multi-VSA) is life-threatening disease. However, 12-leads electrocardiogram (ECG) in no chest symptom period was considered to have no predictive value for the multi-VSA. We tried to predict multi-VSA by machine learning (ML) on parameters of the 12-lead electrocardiogram. Purpose To predict multi-VSA by machine learning on ECG parameters in no chest pain period. Methods We recruited 227 consecutive sinus-rhythm patients (63.6±12.9years, 136men) who underwent acetylcholine-provocation test in coronary angiography (CAG). Multi-VSA was defined as spasm in at least 2 major branches which was provoked by ACh. ECG was recorded before CAG in no chest pain period. ML was performed on table data of ECG parameters (ex. ST level ant J point, R wave amplitude, and/or J wave in each lead) using several ensemble learning methods. Results 79 patients (35%) showed multi-VSA, and the breakdown of the multi-VSA was as follows: double vessel 44, triple vessel 35, including LAD 73, LCx 47, RCA73. Univariate logistic regression analysis extracted 23 significant but weak predictors, the highest area under receiver operating characteristics curve (AUROC) was 0.673 of Q wave amplitude in lead aVL. Conversely, ML demonstrated high diagnostic performance (AUROC of extra trees classifier: 0.817). Shapley additive explanation method in the extra trees showed male, QTc, J wave in lead II, and low amplitude of Q wave in lead I/aVL played essential roles to build the ML model. Conclusion Several parameters of 12-lead ECG in multi-VSA patients contains potential features of VSA, and their aggregation and ensemble learning can predict VSA with high diagnostic performance.