Development and Validation of Artificial Intelligence Prediction of Epicardial Coronary Artery Spasm in Patients Without Obstructive Coronary Artery Disease

Background: Epicardial coronary artery spasm (CAS) is a frequent and important cause of myocardial ischemia. We aimed to develop and validate a noninvasive, artificial intelligence (AI)-driven risk score using routine clinical data to predict CAS in patients without obstructive coronary artery disease (CAD). Methods: Between September 2008 and March 2025, this retrospective study analyzed a derivation cohort of 1,050 patients and an external validation cohort of 600 patients who underwent intracoronary methylergonovine provocation testing. A Random Forest (RF) model was developed using 15 clinical variables and simplified to a 9-variable model. Additionally, a convolutional neural network-long short-term memory (CNN-LSTM) deep learning model was implemented to predict CAS from raw digital electrocardiogram data (2,611 electrocardiogram records). Results: The final 9-variable RF model, including predictors such as diastolic/systolic blood pressure, age, BSA, hemoglobin, smoking, heart rate, sex, and estimated glomerular filtration rate, demonstrated strong discriminatory power. The area under the curve was 85.8% (95% confidence interval [CI]: 85.8–89.9%) in the derivation cohort and 84.1% in the validation cohort (95% CI: 80.6–87.7%). A dose-response relationship was confirmed, with CAS prevalence increasing from 42.1% (0–1 risk factors) to 82.4% (≥5 risk factors). The electrocardiogram-based CNN-LSTM deep learning model achieved high sensitivity (91.4%) but limited specificity (11.9%), indicating strong detection capability for CAS. Conclusions: A 9-variable RF model provides a practical and accurate tool for early identification and risk stratification of CAS. The electrocardiogram deep learning model complements the RF model to improve clinical decisions and resource allocation in diagnosing CAS.