An Efficient Heart Disease Prediction System based on Supervised Machine Learning Methods

Abstract

Heart illness is the most frequent disease that can lead to grave situations in a human life. Every year more number of people gets affected by heart disease around the world. Prediction and finding of heart disease has always been a critical and difficult task for the medical field. To overcome the issues, Machine Learning (ML) methods played a vital role to predict and detect heart disease very accurately and quickly. In this paper, an innovative approach is proposed to predict heart disease using different ML methods. The proposed method consists of three stages. First to preprocess the heart disease Dataset, which consists of checking the missing values, data scaling and calculate the correlation between the predictors. In the second stage apply the supervised classification methods such as Logistic Regression (LR), KNN, Random Forest (RF) and AdaBoost to train the model. classification metrics are used to evaluate the model and choose the best classifier for heart disease prediction. Also comparison can be done using the metrics of each classifier. As a result of the experiment, it is concluded that the RF classifier has attained more accuracy of 95.08% , ROC-AUC score of 0.95.