Generally, the most complicated task in the healthcare field is the diagnosis of the disease itself. The diagnosis phase in disease detection is usually the most time-consuming task and is prone to most of the errors. Such complications can be effectively handled if the disease detection process is well automated by incorporating effective machine learning algorithms trained with some benchmark datasets. It should also be noted that huge amounts of data that are acquired from Heart Specialization Hospitals are being wasted every year. In this paper, various classification algorithms have been used to train the machine to diagnose heart disease. By a comparative study of various learning models, we have identified the appropriate learning model for the heart disease dataset. Initially, the work will begin with an overview of various machine learning algorithms followed by the algorithmic comparison.
Analysis of Supervised Machine Learning Algorithms for Heart Disease Prediction with Reduced Number of Attributes using Principal Component Analysis
