MACHINE LEARNING-BASED INTELLIGENT APPROACH FOR PREDICTIVE ANALYTICS OF CARDIOVASCULAR DISEASE RISK ASSESSMENT

Abstract

Chronic cardiac diseases remain one of the leading causes of death across the globe, making early and accurate diagnosis critically important. Identifying these conditions in their early stages allows for timely treatment and can significantly reduce the risk of severe events such as heart attacks. This study focuses on using machine-learning techniques, applied to health examination data, to improve the prediction of chronic cardiac disease. Early detection of key risk factors—such as hypertension, smoking, high cholesterol levels, aging, male gender, and obesity—plays a vital role in preventing disease progression.

In this follow-up research, statistical analysis is combined with machine learning methods to better understand and predict disease patterns. A clustering heatmap is used to visually group patients based on the severity of their condition, offering an intuitive way to distinguish between early-stage and advanced-stage cases. Patients in the early stages tend to cluster together, while those in more advanced stages are identified as high-risk and may require closer monitoring due to the potential for rapid deterioration in heart function.

This integrated approach not only enhances predictive accuracy but also provides a practical tool for healthcare professionals. By offering clearer insights into disease progression, the proposed model can support physicians in making more informed and timely decisions when diagnosing and managing this complex and progressive condition.

Keywords: Chronic Cardiac, Heart Attach, Machine Learning, and Classifier