Effective Study of Machine Learning Algorithms for Heart Disease Prediction

Abstract

Heart disease has been a major public health concern in recent years, excessive alcohol consumption, cigarette, and a sedentary lifestyle are the primary factors, and it is the leading cause of mortality among patients. Medically, heart disease is known for being difficult to forecast, detect, and diagnose. To treat heart diseases, hospitals and other clinics are giving costly therapies and treatments. According to a recent WHO research, heart disease is on the rise. In 2019, 17.9 million people die as a result of this. It becomes more difficult to diagnose as the population grows. As a result, detecting cardiac disease early on will benefit people all across the world, allowing them to receive necessary therapy before it becomes critical. Thanks to recent technical breakthroughs, machine learning has shown to be effective in making decisions and predictions from a big set of data provided by the healthcare sector. In this paper, some of the supervised machine learning techniques used in this prediction of heart disease which are Support Vector Machines (SVMs), Gradient Boosting Classifier (GB), Decision tree (DT), Random forest (RF), Logistic Regression (LR) on the “UCI Machine learning repository for Statlog (Heart) Data Set” Furthermore, the findings of these algorithms are reported, and a proposal is made to employ the algorithm with the highest accuracy for predicting Heart Disease on a web application. This application will be used as a decision support system by medical practitioners in their clinics as well as people at home.

Ähnliche Arbeiten