Heart Disease Prediction Using ML (Logistic Regression, Random Forest, and XGBoost)

This research study focuses on the application of machine learning for early prediction of heart disease using patient health data. The study develops and compares three classification models: Logistic Regression, Random Forest, and XGBoost. The data is preprocessed and analyzed through exploratory data analysis and visualization, followed by model training and evaluation using accuracy, precision, recall, F1-score, and ROC-AUC. The study examines the strengths and limitations of the models, with particular attention to class imbalance and the importance of recall in medical prediction. It also discusses the potential use of machine learning for early risk assessment and outlines future improvements such as advanced feature engineering, synthetic sampling techniques, explainable AI, deep learning, and the integration of additional clinical data.