Analysis of Anomaly Detection of Diabetes Using Decision Tree Classifier and an Innovative Back Propagation Algorithm using Fit as a Parameter

Aim: The work aims to evaluate the accuracy and precision in the analysis of Anomaly detection of diabetes using Decision tree and Backpropagation classification algorithm. Materials and Methods: Back Propagation Classification is applied on a Pima Indian diabetes dataset that consist of 769 records. A machine learning techniques for earlier prediction of diabetes disease which compares Decision tree and Back Propagation Classification algorithms has been proposed and developed. The sample size was measured as 27 per group using Glower. Sample size was calculated using clincalc analysis, with alpha and beta values 0.07 and 0.5, 95% confidence, pretest power 80% and enrolment ratio 1. The accuracy and precision of the classifiers was evaluated and recorded. Results: The accuracy was maximum in predicting diabetes usingBack propagation (77.29%) with minimum mean error when compared with Decision tree classifier (70.09%). There is a significant difference of 0.05 between the classifiers. Conclusion: The study proves that Back Propagation exhibits better accuracy than Decision tree classifier in predicting diabetes.