Heart Disease Prediction using Supervised Learning Algorithms - A Comparative Study
Abstract - Heart diseases or cardiovascular diseases are diseases that are related to the heart which is an essential organ for the human body. The treatment for heart diseases are also very expensive for the general public to afford. Hence, it becomes really critical to detect and treat it at the right time to avoid further complications. The proposed work mainly concentrates on comparing various supervised machine learning algorithms for prediction of pulmonary diseases based on accuracy. The various algorithms considered in this paper are Support Vector Machine (SVM), KNN Classification, Logistic Regression, Random Forest Algorithm, Multiple Linear Regression and Naive Bayes. From the various studies it is found that the Random Forest Classifier produced the highest accuracy of 92% which would be beneficial to the medical industry in predicting heart diseases on time and saves lives of many people.
Keywords - Accuracy prediction, SVM, Logistic Regression, Random Forest, Naive Bayes classification, Multiple Linear Regression, KNN