ECG trained Artificial Intelligence for the Detection of patients with Inducible Myocardial Ischemia

Background Myocardial ischemia is associated with adverse prognosis. Identifying high-risk individuals who require a stress test is challenging, and practical screening tool to detect these patients, especially in asymptomatic individuals, is lacking. We aimed to develop an artificial intelligence (AI) model based on resting 12-lead electrocardiogram to detect patients with inducible myocardial ischemia. Methods An AI model was developed using 12,074 resting 12-lead ECGs from 11,700 patients, and tested on 1,342 patients at two hospitals. Patients with inducible ischemia were defined as those who received revascularization for silent ischemia, stable angina, or unstable angina between 2004 and 2020 (n=6,070). No ischemia group included patients with 0% stenosis in all epicardial coronary arteries and coronary artery calcium score of ≤100 in coronary computed tomography angiography (n=7,346). The primary outcome was the model performance categorizing patients with inducible myocardial ischemia. We further validated the model through multiple reference and external validation datasets encompassing 35,898 patients. Results The model showed an area under the receiver operating characteristic curve (AUROC) of 0.90 (95% CI 0.88─0.92), and area under the precision-recall curve (AUPRC) of 0.87 (95% CI 0.84─0.89). The model performance was robust regardless of age, sex, comorbidities, clinical diagnosis, or culprit vessels. Consistent results were demonstrated in an age- and sex-matched dataset (n=7,414; AUROC 0.85, 95% CI 0.83─0.87 and AUPRC 0.84, 95% CI 0.82─0.87), as well as in reference and external cohorts. Conclusions Electrocardiogram-trained AI demonstrated favorable performance in detecting inducible myocardial ischemia. It may enable screening and risk stratification of high-risk patients.