A novel method to predict heart disease using SVM algorithm

Health care industry has huge amount of patient data especially heart patients, but unfortunately most of the data is not mined to find out hidden information in data. Advanced data mining techniques can be used to discover hidden pattern in data. These techniques will be useful for medical practitioners to take effective decision. In this paper, data mining classification techniques RIPPER classifier, Decision tree, Artificial Neural Network (ANN), Naive Bayes, Support Vector Machine (SVM), are analyzed on heart disease dataset and its efficiency is analysed. Performance of these techniques is compared through sensitivity, specificity, Accuracy, true positive Rate and False positive Rate. The analysis shows that out of these five classification techniques methods SVM predicts with highest accuracy, specificity and sensitivity.