Improving Cardiovascular Disease Prediction through Comparative Analysis of Machine Learning Models

Abstract

Cardiovascular diseases, including myocardial infarction, present significant challenges in modern healthcare, necessitating accurate prediction models for early intervention. This study explores the efficacy of machine learning algorithms in predicting myocardial infarction, leveraging a dataset comprising various clinical attributes sourced from patients with heart failure. Six machine learning models, including Logistic Regression, Support Vector Machine, XGBoost, LightGBM, Decision Tree, and Bagging, are evaluated based on key performance metrics such as accuracy, precision, recall, F1 Score, and AUC. The results reveal XGBoost as the top performer, achieving an accuracy of 94.80% and an AUC of 90.0%. LightGBM closely follows with an accuracy of 92.50% and an AUC of 92.00%. Logistic Regression emerges as a reliable option with an accuracy of 85.0%. The study underscores the potential of machine learning in enhancing myocardial infarction prediction, offering valuable insights for clinical decision-making and healthcare intervention strategies.