Improvising Heart Attack Prediction System using Feature Selection and Data Mining Methods

Main Article Content

B. Kavitha
R.Naveen Kumar

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.

 

Keywords: Data mining, weka, heart attack, j48, Naive bayes, logistic, classification, Regression, Self Organizing Map.

Downloads

Download data is not yet available.

Article Details

Section
Articles