Machine Learning Models for Heart Attack Prediction

Abstract

This research investigates the application of machine learning models for heart attack prediction. It employs a multi-step approach, beginning with Exploratory Data Analysis (EDA), followed by correlation and cluster analyses to identify patterns in cardiovascular risk factors. A variety of machine learning algorithms, including Logistic Regression, Support Vector Machines (SVM), Random Forest, Gradient Boosting, and others, are compared for their predictive accuracies. The results show that Extreme Gradient Boosting (XGBoost) is the most effective model with 90.96% accuracy. The study highlights challenges such as model interpretability, generalization, and ethical considerations, aiming to enhance early detection and intervention strategies in cardiovascular health.