Comparative Analysis of different Heart Disease Prediction Models

In today generation, heart disease is most common disease among most of the people in the world. There are many types of heart disease, but CAD is most common and it can block or reduced the flow of blood to heart muscle that can cause a heart attack or stroke. To detect cardiac disease, doctors are advised you to take an EKG and exercise stress test which are very costly. As a result, people do not take a test. The main cause of cardiovascular disease is Diabetes, high blood pressure, smoking, high cholesterol etc. In this study, machine learning techniques are used to detect whether a patient has heart disease or not. The algorithms which are used in this study are Random Forest, Logistic Regression, Naïve Bayes, Decision Tree and K-Nearest Neighbors. After the experimentation, it was concluded that RF gave out the best accuracy, F1 score and precision score.