Heart Attack Prediction by using Machine Learning Techniques
Sangya Ware1, Shanu k Rakesh2, Bharat Choudhary3

1Sangya ware*, M. Tech scholar, CSE Department, Chouksey Engineering College, Lalkhadan Bilaspur (C.G.).
2Shanu K Rakesh, Assistant Professor, CSE Department, Choukesy Engineering College, Lalkhadan Bilaspur (C.G.).
3Bharat Choudhary, Assistant Professor, CSE Department, Chouksey Engineering College, Lalkhadan Bilaspur(C.G.).
Manuscript received on January 02, 2020. | Revised Manuscript received on January 15, 2020. | Manuscript published on January 30, 2020. | PP: 1577-1580 | Volume-8 Issue-5, January 2020. | Retrieval Number: D9439118419/2020©BEIESP | DOI: 10.35940/ijrte.D9439.018520

Open Access | Ethics and Policies | Cite | Mendeley
© 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: Heart disease is most common now a days and it is a very serious problem. Machine learning provides a best way for predicting heart disease. The aim of this paper is to develop simple, light weight approach for detecting heart disease by machine learning techniques. Machine learning can be implemented in heart disease prediction. In this paper different machine learning techniques have been used and it compares the result using various performance metrics. This study aims to perform comparative analysis of heart disease detection using publicly available dataset collected from UCI machine learning repository. There are various datasets available such as Switzerland dataset, Hungarian dataset and Cleveland dataset. Here Cleveland dataset is used which is having 303 records of patients along with 14 attributes are used for this study and testing. These datasets are preprocessed by removing all the noisy and missing data from the dataset. And then the preprocessed dataset are used for analysis. In this study six different machine learning techniques were used for comparison based on various performance metrics. The analysis shows that out of six techniques SVM gives the best result with 89.34%. A GUI is developed for the prediction of heart disease.
Keywords: SVM, Machine Learning, Datasets, Heart Disease Prediction, Analysis.
Scope of the Article: Machine Learning.