A Web based Cardiovascular Risk Prediction and Preventive Health Advisory System

Abstract

Heart diseases are among the most common causes of death in the world, which underlines the necessity of early risk evaluation and preventive care. This paper is a proposal of an intelligent Heart Risk Prediction System that applies machine learning methods to predict cardiovascular disease risk with high accuracy. The system combines the structured data preprocessing, feature selection, and training the ensemble model based on the implementation of random forest and XGBoost algorithms to analyses clinical and lifestyle-related features. Recursive Feature Elimination is used to filter the most useful features and enhance the efficiency of the model. The suggested ensemble model is effective in capturing complicated association among risk factors and gives coherent prediction results. Through experimental analysis, the ensemble approach results in a recall of 95.2 a precision of 95.8, and an F1-score of 95.5 which surpasses single machine learning models with an accuracy of 96.4. In addition, Explainable AI (XAI) techniques such as feature importance analysis and SHAP-based interpretation are used to explain the contribution of clinical attributes toward prediction outcomes, improving model transparency and trustworthiness. The scalability and applicability in the real-world situation of healthcare is guaranteed by the modular architecture and secure data management. The findings suggest that the suggested framework can help healthcare workers to recognize patients at risk and allow timely intervention to lessen the consequences of heart diseases.