An Overview of Data Mining Classification Methods in Aortic Stenosis Prediction
T. Revathi1, P. Sumathi2
1T. Revathi, Research Scholar, Manonmaniam Sundaranar University, Tirunelveli, India.
2Dr. P. Sumathi, Asst. Prof, Department of Computer Science, Govt. Arts College, Coimbatore, India.
Manuscript received on July 22, 2014. | Revised Manuscript received on August 10, 2014. | Manuscript published on August 30, 2014. | PP: 173-175  | Volume-3 Issue-6, August 2014.  | Retrieval Number:  F3376083614/2013©BEIESP

Open Access | Ethics and Policies | Cite
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (

Abstract: There is a huge amount of data in medical science industry. But most of this data is not mined to find out the hidden information. To discover those hidden information, advanced data mining techniques are used. Models developed from these techniques are seemed to be very useful for medical practitioners to take effective decision. In this research paper data mining classification techniques Decision Tree and Support Vector Machine (SVM) are analyzed on Aortic Stenosis disease dataset. Performance of these techniques is compared by sensitivity, specificity, accuracy, error rate, True Positive Rate and False Positive Rate. As per our results error rates for Decision Tree and SVM are 0.2755 and 0.1488 respectively. Accuracy of Decision Tree and SVM are 79.05% and 85.12% respectively. Our analysis shows that among these two classification models SVM predicts Aortic Stenosis disease with least error rate and highest accuracy.
Keywords: Heart disease, Aortic Stenosis, Data Mining techniques, Decision tree and support vector machine.