An Efficient Classification Analysis for Multivariate Coronary Artery Disease Data Patterns Using Distinguished Classifier Techniques

Abstract

Medical care industry has huge amount of data, which includes hidden information. Advanced data mining techniques can be used to develop classification models from these techniques for effective decision making. A system for efficient and automated medical diagnosis would increase medical care and reduce costs. This paper intends to provide a survey of current techniques of knowledge discovery in databases using data mining techniques that are very much needed for current study in medical research predominantly in Heart Disease diagnosis. The data mining classification techniques such as K means, SOM, decision Tree Techniques are explored with the algorithm for coronary Artery disease dataset (CAD) taken from University California Irvine (UCI). Performance of these techniques are compared through standard metrics. Number of experiment has been conducted to evaluate the performance of predictive data mining technique on the same dataset. The output shows that Decision Tree outperforms compared to other classifiers.