Heart Disease Prediction using Ensemble Model

Heart Disease is one of the prominent fatal diseases that have caused a colossal amount of deaths over decades. Machine learning an effective domain has been a key factor to solve various problems over a wide spread of areas. If the presence or the indication of such a fatal disease can be predicted in advance, it will be effortless for doctors to diagnose them. The ensemble stacked model which offers a way to combine Support Vector Machine (SVM) and Decision Tree(DT) models is part of the Machine learning domain that has been applied in our model to develop an intelligent system to predict the accuracy of the disease. The ensemble model of SVM and DT has achieved a higher percentage of efficiency among the various methods used for prediction. The proposed system presents a machine-learning approach for predicting heart disease, using a dataset of significant health factors such as age, sex, cholesterol, blood pressure, and sugar, from patients. The proposed system enables precise prediction of heart disease that enhances medical care and reduces the cost incurred for prediction. The dataset has been obtained from Kaggle.