THE PREDICTION OF HEART DISEASE USING MACHINE LEARNING ALGORITHMS

Abstract

Heart disease threatens the lives of around one individual per minute, establishing it as the foremost cause of mortality in the contemporary era. A wide range of individuals over the globe has encountered the intricacies associated with cardiovascular illness. Various factors, such as hypertension, elevated levels of cholesterol, and an irregular pulse rhythm hinder the early identification of a cardiovascular disease. In cardiology, similar to other branches of Medicine, timely and precise identification of cardiac diseases is of utmost importance. Anticipating the onset of heart failure at the appropriate moment can provide challenges, particularly for cardiologists and surgeons. Fortunately, categorisation and forecasting models can assist the medical business and provide real applications for medical data. Regarding this, Machine Learning (ML) algorithms and techniques have benefited from the automated analysis of several medical datasets and complex data to aid the medical community in diagnosing heart-related diseases. Predicting if the patient has early-stage cardiac disease is the primary goal of this paper. A prior study that worked on the Erbil Heart Disease dataset has proved that Naïve Bayes (NB) got an accuracy of 65%, which is the worst classifier, while Decision Tree (DT) obtained the highest accuracy of 98%. In this article, a comparison study has been applied using the same dataset (i.e., Erbil Heart Disease dataset) between multiple ML algorithms, for instance, LR (Logistic Regression), KNN (K-Nearest Neighbours), SVM (Support Vector Machine), DT (Decision Tree), MLP (Multi-Layer Perceptron), NB (Naïve Bayes) and RF (Random Forest). Surprisingly, we obtained an accuracy of 98% after applying LR, MLP, and RF, which was the best outcome. Furthermore, the accuracy obtained by the NB classifier differed incredibly from the one received in the prior work.