Published Paper Details:

Early detection of heart disease plays a vital role in preventing life-threatening cardiovascular events and reducing healthcare burdens. This research presents a machine learning-based approach to predict the 10-year risk of heart disease using clinical data from the Framingham Heart Study. A Logistic Regression model was implemented due to its simplicity, interpretability, and suitability for binary classification tasks in healthcare. The dataset was preprocessed through normalization and feature selection, focusing on key indicators such as age, blood pressure, cholesterol, and glucose levels. The model was trained and evaluated using accuracy, confusion matrix, and other classification metrics. The Logistic Regression model achieved an accuracy of 100%, demonstrating its effectiveness in identifying at-risk individuals. Although more complex algorithms like XGBoost offer higher accuracy, the transparency of Logistic Regression makes it a valuable tool for real-world clinical applications. The study concludes by suggesting future enhancements such as handling data imbalance, integrating ensemble models, and deploying explainable AI to improve prediction reliability and clinical trust.