Forecasting Heart Disease Risk Through Lifestyle Analysis Using Machine Learning

Abstract

Cardiac disease remains a leading cause of death worldwide, and lifestyle components such as diet, physical exercise, consumption of fruit and vegetables or oily and fried foods, smoking, alcohol consumption, stress levels and sleeping habits have considerable roles to play in the development and initiation of cardiac disease. Detection of people at risk at an early stage will enable treatment to be initiated on time and may also stem the tide against the healthcare system. It is proposing a machine learning model using clustering to forecast heart disease risk from health and lifestyle related traits. Data preprocessing tasks, including missing value handling, encoding of categorical variables, and feature selection, were conducted to ensure data quality and model accuracy. Unsupervised learning using the K-Means clustering algorithm was carried out for the division of individuals into distinct risk clusters. Model performance was verified using internal validation metrics such as silhouette score and Davies–Bouldin index for effective clustering. From the results, it can be seen that the proposed method can effectively cluster the subjects into low, moderate, and high-risk groups, providing valuable information for targeted preventive intervention. The results show the prospects of machine learning in the development of predictive healthcare, especially in resource-poor settings. Future work includes expanding the dataset, incorporating additional lifestyle parameters, and deploying the model within a real-time decision-support system for clinicians.