Heart Disease Prediction Using Machine Learning Techniques

Abstract

Heart-related diseases or cardiovascular diseases are the primary purposes behind a large number of deaths on the planet in the course of the most recent couple of decades. It has risen as the most terrifying ailment around the world. Actually, in India, these issues are progressively awful; according to the Journal of the American College of Cardiology in India, the demise rate because of cardiovascular maladies increments around 34% in the middle of 1990–2016. Presently, we are in a time of data age where a huge quantity and variety of information is stored in different enterprises like retail, producing, medical clinic, and online networking. We can gather the information and break down the information to foresee the components and reasons for heart diseases so that safety measures can be taken to decrease the demise rate. There exists various types of information investigation instrument and procedure which requires an ideal informational collection; at that point, we can apply distinctive sort of machine learning strategies to anticipate whether the patient can be influenced by heart diseases or not by utilizing the recently gathered datasets. In this paper, we will exhibit how to utilize various kinds of machine learning models like K-nearest neighbor, decision tree classifier, and random forest classifier, and furthermore make a presentation correlation among these models so that we can get accurate precision about a patient having heart disease (Chen et al. in 2011 Computing in Cardiology IEEE, 557–560, 2011, [1]), (Kishore et al. Heart attack prediction using deep learning, [2]).