Detection Of Heart Disease Using Machine Learning Techniques
International Journal of Scientific & Technology Research, 9(8), 285-288. Retrieved from http://www.ijstr.org/paper-references.php?ref=IJSTR-0820-40747
4 Pages Posted: 17 Sep 2020 Last revised: 24 Sep 2020
Date Written: August 1, 2020
Abstract
We live in a 'information age,' a popular saying says. Data of terabytes are generated daily. Data mining is the method that turns data processing into information. The health industry creates huge volumes of data every day. But most of it is not used effectively. Efficient methods to obtain information from such repositories are not widespread for clinical disease diagnosis or other purposes. This paper aims at comparing specific approaches for forecasting cardiac diseases using data mining techniques, examining the numerous variations of mining algorithms employed, and assessing the techniques are efficient and successful. In fact, several potential paths have been discussed on prediction systems. Naïve Bayes, SMO, Random Forest, Decision table is one such method of data mining that can be used to diagnose patients with cardiac diseases. This paper analyzes few parameters and predicts heart disease, suggesting a prediction system based entirely on data mining approaches.
Keywords: Algorithms, Dataset, Heart disease, Machine learning, Naïve Bayes, Weka
Suggested Citation: Suggested Citation