Abstract
Acute myocardial ischemia (AMI) is one of the leading causes of cardiovascular deaths around the globe. Yet, clinical early detection and patient risk stratification of AMI remain an unmet need, in part due to poor performance of traditional electrocardiogram (ECG) interpretation. Machine learning (ML) techniques have shown promise in analysis of ECGs, even detecting cardiac diseases not identifiable via traditional analysis. However, there has been limited usage of ML tools in the case of AMI due to a lack of high-quality training data, especially detailed ECG recordings throughout the evolution of ischemic events. In this study, we applied ML to predict the ischemic tissue volume directly from body surface ECGs in an AMI animal model. The developed ML networks performed favorably, with an average R(2) value of 0.932 suggesting a robust prediction. The study also provides insights on how to create and utilize ML tools to enhance clinical risk stratification of patients experiencing AMI.