Prediction and diagnosis of diabetes mellitus — A machine learning approach

Abstract

Diabetes is a disease caused due of the expanded level of sugar fixation in the blood. Various computerized information systems were outlined utilizing diverse classifiers for anticipating and diagnosing diabetes. Selecting legitimate classifiers clearly expands the exactness and proficiency of the system. Here a decision support system is proposed that uses AdaBoost algorithm with Decision Stump as base classifier for classification. Additionally Support Vector Machine, Naive Bayes and Decision Tree are also implemented as base classifiers for AdaBoost algorithm for accuracy verification. The accuracy obtained for AdaBoost algorithm with decision stump as base classifier is 80.72% which is greater compared to that of Support Vector Machine, Naive Bayes and Decision Tree.