MACHINE LEARNING–DRIVEN RISK ASSESSMENT OF HEART DISEASE THROUGH CLINICAL AND BIOLOGICAL PARAMETERS

Abstract

Heart disease remains one of the leading causes of mortality worldwide, emphasizing the importance of accurate and early risk prediction for improved clinical intervention. This study proposes a machine learning–based framework for predicting heart disease risk using structured clinical attributes and cardiovascular-related biological indicators associated with disease progression. The methodology integrates data preprocessing, feature scaling, and supervised classification techniques within a unified and reproducible pipeline to enhance predictive performance. Multiple machine learning models are evaluated using standard performance metrics, including accuracy, precision, recall, and F1-score, to assess their effectiveness in identifying high-risk individuals. Comparative analysis demonstrates that ensemble-based learning methods provide the most balanced and robust performance, supported by confusion matrix interpretation. The findings suggest that the proposed framework effectively captures complex relationships among patient characteristics and disease-associated indicators while maintaining stable generalization capability. By utilizing routinely available clinical parameters and supporting precision-oriented risk assessment, the approach offers an interpretable and scalable decision-support system that may assist clinicians in early identification, preventive management, and improved cardiovascular healthcare outcomes.