PREDICTIVE MODELING OF CARDIOVASCULAR DISEASE USING MACHINE LEARNING APPROACH

Abstract

The primary causes of death worldwide are Chronic Cardiac diseases. Accurately diagnose and predicting chronic cardiac disease is important to the proper treatment of cardiac patients before a heart attack occurs. The goal of accurate disease prediction will be achieved using a ML algorithm with health examination data. Early prediction of the risk factors of cardiac disease is critical for preventing heart disease. In our research, this is a follow-up study the statistical analysis will be used to assess the prediction of CCD as many high-risk factors (hypertension, smoking, high blood cholesterol, increasing age, male gender, being overweight) are involved. The heat-map cluster and machine learning algorithm provide interactive visualization for the classification of patients with different CCD stages. Early stages of cardiac patients are grouped into one cluster and advanced staged cardiac patients could be at high risk for the expeditious decline of heart function and should be closely monitored. The clustering heatmap provided a new predictive model for health care management for patients at high risk of rapid CCD progression. This model could help physicians make an accurate diagnosis of this progressive and complex disease.