Machine Learning Methods for Heart Disease Prediction
Rashmi G.O1, Ashwin Kumar .U.M2
1Rashmi G.O, Department of Computer Science and Information Technology, REVA University, Bangalore (Karnataka), India.
2Ashwinkumar U.M, Department of Computer Science and Information Technology, REVA University, Bangalore (Karnataka), India.
Manuscript received on 05 June 2019 | Revised Manuscript received on 14 June 2019 | Manuscript Published on 29 June 2019 | PP: 220-223 | Volume-8 Issue-5S, May 2019 | Retrieval Number: E10450585S19/19©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Machine learning is utilized to empower a program to analyze information, understand correlations and make utilization of bits of knowledge to take care of issues or potentially enhance information and for prediction. The American Heart Association Statistics 2016 Report shows that coronary illness is the main source of death for people, responsible for 1 in every 4 deaths. Machine learning algorithms play a very important role in medical area. We use machine learning to understand, predict, and prevent cardiovascular disease using numeric data. The end goal is to produce an approved machine learning application in healthcare. In an effort to refine the search for a useful and accurate method with the dataset, the results of several algorithms will be compared. The front-runners will be analyzed and used to develop a unique, higher-accuracy method. Machine learning methods inclusive of Logistic Regression, Naïve Bayes, Decision tree(CART). We use ensemble learning for better accuracy which includes algorithms like Random Forest, XGBoost, Extra trees classifier. Also, our work adds to the present literature by giving a far reaching review of machine learning algorithms on sickness prediction tasks. Our goal is to perform predictive analysis with these machine learning algorithms on heart diseases using ensembles like bagging, boosting, stacking. Machine Learning algorithms used and conclude which techniques are effective and efficient. A huge medical datasets are accessible in different data repositories which used in the real world application.
Keywords: Machine Learning, Cardiovascular Disease, Decision Tree(CART), Ensemble Learning.
Scope of the Article: Machine Learning