Improvising Heart Attack Prediction System using Feature Selection and Data Mining Methods
Main Article Content
Abstract
Medical diagnosis refers to the process of attempting to determine the identity of a possible disease. The identity of heart disease from
various factors or symptoms is a multi-layered issue which is not free from false presumptions often accompanied by unpredictable effects. In
this paper, we have proposed an efficient approach for the extraction of significant attributes from the heart disease warehouses for heart attack
using forward selection method and have performed the classification of heart attack using data mining techniques. The data used in this paper is
collected from UCI Machine Learning Repository Heart Disease dataset. The dataset consist of 303 records which have 14 attributes and after
applying Correlation–based Feature Selection methods the original attributes was reduced to 6 potential attributes. We have investigated five
data mining techniques such as J48, Naïve bayes, Logistic Regression, Classification via regression and Self-Organizing Map. The results shows
that classification via regression have much better performance than other four methods and it is also observed that using feature selection
method the performance of Logistic and Self Organizing Map has a notable improvement in their classification. It is observed that the
classification accuracy increases better after dimensionality reduction.
Â
Keywords: Data mining, weka, heart attack, j48, Naive bayes, logistic, classification, Regression, Self Organizing Map.
Downloads
Article Details
COPYRIGHT
Submission of a manuscript implies: that the work described has not been published before, that it is not under consideration for publication elsewhere; that if and when the manuscript is accepted for publication, the authors agree to automatic transfer of the copyright to the publisher.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work
- The journal allows the author(s) to retain publishing rights without restrictions.
- The journal allows the author(s) to hold the copyright without restrictions.