Enhanced Ensemble Classifiers for Heart Disease Prediction

In developing countries, people suffer from heart disease (HD), and it is the leading cause of Lifestyle Disease. Obesity, increased pulmonary heart pressure, hypertension, and dyslipidemia are all symptoms of heart disease. Early detection of heart disease minimizes mortality risk and treatment expenses. In the traditional method, heart disease is predicted and analyzed through Data Mining techniques such as genetic, fuzzy, and optimization models. The main limitation of the existing clinical decision support system (CDSS) is its low HD prediction accuracy. This proposed model developed CDSS for HD prediction using enhanced ensemble classifiers, which help physicians in diagnosing heart disease at an earlier stage, with higher accuracy and reduce treatment costs. The advantage of this suggested system is building many ensemble models and then selecting the best-performing model among them based on efficiency, which is a prominent technique for predicting the heart disease.