Home|Journals|Articles by Year

Directory for Medical Articles
 

Research Article

JCDR. 2021; 12(3): 379-391


HEART DISEASE PREDICTION USING VARIOUS MACHINES LEARNING APPROACH

Arif Ullah, Canan Batur Şahin, Ozlem Batur Dinler, Mubashir Hayat Khan, Hanane Aznaoui.


Abstract

In health sector computer aided diagnosis (CAD) system is rapidly growing area because medical diagnostic systems make huge change as compare to traditional system. Now a day huge availability of medical data and it need proper system to extract them in to useful knowledge. Machine learning has been exposed to be operative in supporting in making decision and predication from the large quantity of data produce by the healthcare sector. Classification is a prevailing machine leaning approach which are commonly used for predication some classification algorithm predict accurate result according to the marks whereas some others exhibit a limited accuracy. So in this paper investigates some of classification approaches and also combining multiple classifiers for single approaches are used. A reasonable analytical of these technique was done to conclude how the cooperative techniques can be applied for improving prediction accuracy in heart disease. Five main classifiers used to construct heart disease prediction base on the experimental results demonstrate that support vector machine, naive bayes, logistic regression, decision tree and memory-based learner provide reliable and accurate result.

Key words: Classifiers, Machine learning technique, prediction, Healthcare sector






Full-text options


Share this Article



Online Article Submission
• ejmanager.com







eJManager.com
Review(er)s Central
About BiblioMed
License Information
Terms & Conditions
Privacy Policy
Contact Us

The articles in Bibliomed are open access articles licensed under the terms of the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License (https://creativecommons.org/licenses/by-nc-sa/4.0/) which permits unrestricted, non-commercial use, distribution and reproduction in any medium, provided the work is properly cited.