Effective heart disease prediction using hybrid machine learning technique

Abstract

Heart disease is one of the most significant causes of mortality in the world today. Prediction of cardiovascular.Disease is a critical challenge in the area of clinical dataanalysis In this project, we propose a novel method that aims at finding significant features by applying machine learning techniques (EML) resulting in improving the accuracy in the prediction of Heart disease.HRFLM (Hybrid Random Forest Linear Model) Technique proved to be quite accurate in the prediction of heart disease. by using entropy feature selection technique and removing unnecessary features, different classification techniques such that Gaussian Naïve Bayes, Support Vector Machine, Hybrid Random Forest with Linear Model, and Extension extreme Machine Learning Technique are used on heart disease dataset for better prediction. Different performance measurement factors such as accuracy precision, recall, sensitivity, specificity, and F1-score are considered to determine the performance of the classification techniques. Our project compares the performances of the classification algorithms in the prediction of heart disease. It tries to find out the best classifier for the detection of heart diseases.