Motivated by the rising mortality of Heart Disease, Breast Cancer and Diabetes patients every year worldwide and the handiness of enormous amount of patient’s data that could be used to mine useful knowledge, researchers have been using machine learning methods to assist medical professionals in the prediction of heart disease, breast cancer and diabetes. The techniques offer a framework to study the problem of inference that is of getting the knowledge, decision making, doing predictions or developing models from a data set. To predict different diseases like diabetes, breast cancer and heart disease etc., data mining techniques were applied. In this study, classification techniques were applied to extract knowledge from the heart disease, diabetes and breast cancer data sets. The performance measures of these classification algorithms, namely, Naïve Bayes, Back Propagation, Support Vector Machines (SVM), K-Nearest Neighbor and C4.5 were examined by considering the various parameters like accuracy, specificity, sensitivity, precision, error rate, ROC area and time. For evaluating these measures Confusion matrix values were used and stratified 10-fold cross-validation method was applied.

Machine Learning, Diseases, Support Vector Machines, Decision Making, Datasets