Comparative Study of Existing Techniques for Heart Diseases Prediction using Data Mining Approach.

Abstract

The field of medical sciences heavily rely on the computer based automated means for proper and accurate and timely diagnosis.  This resulted in the maintenance of huge amount of patient related data on daily basis. The stored data can be used as a source of predicting the chance of future diseases that makes the data mining techniques to play a central role for the extraction of knowledge and prediction.  Heart disease predation is one of the growing areas for such prediction. Varieties of data mining techniques for the prediction of heart diseases have been proposed with the varying level of success and accuracy. The current study explores preliminaries behind the techniques and presents a classification of various techniques based on their accuracy and the number of parameters under investigation.  The main focus of this study will be to carry out the survey of existing data mining techniques used to predict heart diseases, to present the accuracy of each technique/techniques along with number of attributes under consideration and data mining tool/technique used.