Heart Disease Risk Prediction Using Machine Learning

Heart disease remains one of the leading causes of mortality worldwide, accounting for approximately 17.9 million deaths annually. Traditional diagnostic methods are often costly, time-consuming, and inaccessible for routine screening. This paper proposes a Heart Disease Risk Prediction system built on a weighted soft voting ensemble of Logistic Regression (LR) and Random Forest (RF). The model is trained on a 4,000-record clinical dataset with 13 features. The system provides probability-based outputs suitable for graded clinical risk assessment.