A Review of Heart Disease Classification Base on Machine Learning Algorithms

Abstract

Heart disease is currently the leading cause of death. This problem is acute in developing countries. Predicting heart disease helps patients avoid it in its early stages and can also help medical practitioners find out the main causes. Machine learning has proven over time to play an important role in decision making and forecasting through massive data sets created by the healthcare sector. This review provides an overview of heart disease prediction using applied machine learning algorithms such as Naïve Bayes, Random Forest, Decision Tree (DT), Support Vector Machine (SVM), Logistic Regression, and K-Nearest Neighbour (KNN). And these differences in the techniques are a reflection of many strategies for predicting heart disease. We present a synopsis of classification techniques that are primarily used in the predicted of heart disease. Additionally, we review several previous studies that conducted over the past four years, that used machine learning algorithms to predict cardiovascular.