AI-Enhanced Electrocardiography Analysis as a Promising Tool for Predicting Obstructive Coronary Artery Disease in Patients with Stable Angina

Abstract

The clinical feasibility of artificial intelligence (AI)-based electrocardiography (ECG) analysis for predicting obstructive coronary artery disease (CAD) has not been sufficiently validated in patients with stable angina, especially in large sample sizes. A deep learning framework for quantitative ECG (QCG) analysis was trained and internally tested to derive risk scores (0–100) for obstructive CAD (QCGObstCAD) and extensive CAD (QCGExtCAD) using 50,756 ECG images from 21,866 patients who underwent coronary artery evaluation for chest pain (invasive coronary or computed tomography angiography). External validation was performed in 4,517 patients with stable angina who underwent coronary imaging to identify obstructive CAD. QCGObstCAD and QCGExtCAD scores were significantly increased in the presence of obstructive and extensive CAD (all p < 0.001), and with increasing degrees of stenosis and disease burden, respectively (all ptrend < 0.001). In internal and external tests, QCGObstCAD exhibited good predictive ability for obstructive CAD (area under the curve [AUC], 0.781 and 0.731, respectively) and severe obstructive CAD (AUC, 0.780 and 0.786, respectively), and QCGExtCAD exhibited good predictive ability for extensive CAD (AUC, 0.689 and 0.784). In the external test, QCGObstCAD and QCGExtCAD scores demonstrated independent and incremental predictive value for obstructive and extensive CAD, respectively, over that with conventional clinical risk factors. QCG scores demonstrated significant associations with lesion characteristics, such as the fractional flow reserve, coronary calcification score, and total plaque volume. AI-based QCG analysis for predicting obstructive CAD in patients with stable angina, including those with severe stenosis and multivessel disease, is feasible.