Hybrid Machine Learning Algorithms for Optimal Diagnosis of Heart Disease with Feature Analysis

Abstract

Timely prediction of heart disease and its cause is the most challenging issue in medical science. This paper uses various machine learning algorithms such as Logistic Regression, Support Vector Machine, Decision Tree, Random Forest, Naive Bayes, K-Nearest Neighbourhood, and K-fold cross-validation are used to predict heart diseases. The system uses a K-fold cross-validation technique to enhance the accuracies of algorithms. The UCI Kaggle Cleveland heart disease datasets is used to analyse the performance of the models. It is found in the experiment that the training accuracy of K-Nearest Neighbour is 88.52%, and Recall is 93.30%. The Random Forest produced the highest and most comparable Receiver Operating Characteristics Curve accuracy. Moreover, the experimental results of the recommended techniques are compared with previous heart disease prediction studies, and it is found that among the suggested technique, the performance of K-Nearest Neighbour is best. The fundamental goal of this study is to design a novel and distinctive model-creation approach for resolving practical issues.