AN HYPERTUNING BASED APPROCH TOWARDS ENHANCEMENT IN ACCURACY OF HEART DESEASE PREDICTION USING MACHINE LEARNING

Abstract

Heart disease remains a leading cause of mortality worldwide, necessitated effective predictive models to enable early intervention and prevention. This research paper presents a comprehensive methodology for predicting heart disease using various machine learning algorithms. The study begins with data preprocessing to address issues such as missing values, feature scaling, and handling categorical variables. We then evaluate multiple machine learning models, including Logistic Regression, Random Forest, Support Vector Machines (SVM), and Gradient Boosting, using metrics such as accuracy, precision, recall, and F1 score. Hyperparameter tuning is conducted to optimize model performance. Our findings indicate that preprocessing significantly enhances predictive accuracy, and among the models tested, Random Forest and Logistic Regression demonstrate superior performance. This research offers valuable insights into the application of machine learning in medical data analysis and underscores the importance of pre processing in developing robust predictive models for heart disease.