Heart Disease Prediction Using GridSearchCV and Random Forest

Abstract

INTRODUCTION: This study explores machine learning algorithms (SVM, Adaboost, Logistic Regression, Naive Bayes, and Random Forest) for heart disease prediction, utilizing comprehensive cardiovascular and clinical data. Our research enables early detection, aiding timely interventions and preventive measures. Hyperparameter tuning via GridSearchCV enhances model accuracy, reducing heart disease's burdens. Methodology includes preprocessing, feature engineering, model training, and cross-validation. Results favor Random Forest for heart disease prediction, promising clinical applications. This work advances predictive healthcare analytics, highlighting machine learning's pivotal role. Our findings have implications for healthcare and policy, advocating efficient predictive models for early heart disease management. Advanced analytics can save lives, cut costs, and elevate care quality. OBJECTIVES: Evaluate the models to enable early detection, timely interventions, and preventive measures. METHODS: Utilize GridSearchCV for hyperparameter tuning to enhance model accuracy. Employ preprocessing, feature engineering, model training, and cross-validation methodologies. Evaluate the performance of SVM, Adaboost, Logistic Regression, Naive Bayes, and Random Forest algorithms. RESULTS: The study reveals Random Forest as the favored algorithm for heart disease prediction, showing promise for clinical applications. Advanced analytics and hyperparameter tuning contribute to improved model accuracy, reducing the burden of heart disease. CONCLUSION: The research underscores machine learning's pivotal role in predictive healthcare analytics, advocating efficient models for early heart disease management.