Characterization of Advanced Decision-Support Tools (DSTs) for Prediction of Major Adverse Cardiovascular Events (MACE) for Patients with Chest Angina

Cardiovascular disease (CVD), identified by the Centers for Disease Control and Prevention (CDC) as the leading cause of death in the United States, claimed over 700,000 lives and cost the U.S. over $250 billion from 2019 to 2020 (Heart Disease Facts, 2024). As a result, measures have been implemented to enhance diagnostic imaging, spread awareness of preventive methods, and correct issues in treatment. One of the major early symptoms of cardiovascular disease of many categories is angina, commonly called chest pain, a common umbrella term characterized by a limited oxygen-rich blood flow to the heart (What Is Angina? | NHLBI, NIH, 2023). To better predict the likelihood of a cardiovascular event occurring in a patient reporting consistent angina, several machine learning algorithms are currently being utilized as decision-support (Nestelberger et al., 2019). This review will compare various models, assess their capabilities, and analyze their statistical achievements, providing a summary of the current literature and shedding light on potential future directions.