Heart Disease Prediction System using Ensemble Machine Learning Technique

The traditional approach to prediction of heart disease using a limited set of essential physical signs from repetitive inspections is inadequate. Also, manual inspection and analysis of large data sets is time-consuming and labor-intensive. Heart disease is a major global health issue marked by high rates of death. Traditional predictive methods often fall short, making machine learning solutions more effective. This paper applies algorithms such as LR, DT, KNN, SVM, RF, naïve bias, and bagging classifier to enhance diagnostic efficiency for heart disease. The accuracy of ensemble technique namely bagging classifier is 89%. The results show that an ensemble technique greatly improves predictive accuracy and enables early heart attack risk detection.