Exploring Machine Learning Algorithms for Myocardial Infarction Diagnosis

Cardiovascular diseases, including Myocardial Infarction, remain a leading cause of global morbidity and mortality [1]. Myocardial Infarction is a medical condition characterized by abnormal heart function resulting from factors such as arterial and venous blockages [2]. Machine Learning has emerged as a highly effective approach for developing predictive models in various healthcare sectors. In this study, we investigate the application of Machine Learning algorithms for Myocardial Infarction detection using the MIT-BIH dataset. We conduct a thorough performance evaluation of four distinct algorithms including K-Nearest Neighbors, Decision Trees, Random Forest, and Support Vector Classifier. Notably, Random Forest emerges as the top performing algorithm, achieving an accuracy rate of 97.68%. This study not only demonstrates the effectiveness of ensemble learning in enhancing Myocardial Infarction detection accuracy but also highlights the potential of computational techniques in cardiac health diagnostics.