Deep Learning in the prediction of Angiography-proven Severe Coronary Stenosis in Patients with Apparently Normal Electrocardiograms

A bstract Patients with severe coronary artery stenosis may have apparently normal electrocardiograms (ECGs), making it difficult to detect the adverse health conditions during screening or physical examinations, resulting in them missing the optimal window of treatment. The goal of this study was to develop an artificial intelligence-based ECG model which can distinguish severe coronary stenosis (≥ 90%) from no or mild coronary stenosis (< 50%) in patients with apparently normal ECGs. Deep learning (DL) models trained from scratch with pre-trained parameters (transfer learning) were tested on ECG alone as well as on ECG along with clinical information (age, sex, hypertension, diabetes, dyslipidemia and smoking status). We also compared the performance of logistic regression for clinical information only and found that DL models trained from scratch with ECG alone can achieve a specificity of 0.746; however, they have low sensitivity, which is comparable to the performance of logistic regression with clinical data. Although adding clinical information to the ECG DL model trained from scratch can improve the sensitivity, it can reduce the specificity. Combining clinical information with the ECG transfer learning model provides the best performance, with a 0.847 AUC, 0.848 sensitivity, and 0.704 specificity.