Cardiovascular Disease Risk Assessment Using Hybrid Machine Learning Model

Cardiovascular diseases (CVD) are the leading reasons of the death globally, posing significant health risks. Accurate risk assessment is crucial for early intervention and prevention. This paper is about exploring a machine learning (ML) based approach for the estimating CVD risk using many clinical parameters like age of the person, person's blood pressure (BP), cholesterol levels, smoking habits and ECG signals. The model then classifies individuals into low, moderate and high-risk groups providing risk prediction of about 10 years. Established ML models like naive bayes and random forest along with the feature selection techniques. Performance comparison shows that neural networks outperform the other models by achieving 97% accuracy. This model aims to assist doctors in early diagnosis, thereby improving patient outcomes and reducing the incidence of CVD.