International Journal of Science, Engineering and TechnologyAuthors: Ms. Voliviya Veronica Sam. N
Abstract: The increasing incidence of cardiovascular disease (CVD) highlights the need for accurate and early risk prediction methods. Traditional approaches often fail to capture complex relationships among multiple health factors, leading to lower prediction efficiency. This paper proposes a machine learning–based framework for early prediction of cardiovascular disease risk using patient health and lifestyle data. The system incorporates data preprocessing, feature selection using Recursive Feature Elimination (RFE), and class balancing using SMOTE to improve model performance. The optimized dataset is trained using the XGBoost classifier, which effectively handles nonlinear relationships and enhances prediction accuracy. Experimental results demonstrate that the proposed model achieves high accuracy with improved precision, recall, and F1-score. The system provides a reliable and efficient solution for early detection of cardiovascular disease, supporting timely medical intervention and preventive healthcare strategies.
DOI:
