Comparison of different methods for determining diabetes

Authors: MEHMET RECEP BOZKURT, NİLÜFER YURTAY, ZİYNET YILMAZ, CENGİZ SERTKAYA

Abstract: In this study, the Pima Indian Diabetes dataset was categorized with 8 different classifiers. The data were taken from the University of California Irvine Machine Learning Repository's web site. As a classifier, 6 different neural networks [probabilistic neural network (PNN), learning vector quantization, feedforward networks, cascade-forward networks, distributed time delay networks (DTDN), and time delay networks], the artificial immune system, and the Gini algorithm from decision trees were used. The classifier's performance ratios were studied separately as accuracy, sensitivity, and specificity and the success rates of all of the classifiers are presented. Among these 8 classifiers, the best accuracy and specificity values were achieved with the DTDN and the best sensitivity value was achieved with the PNN.

Keywords: Diabetes diagnosis, artificial neural networks, decision tree, artificial immune system, classification, Pima Indian

Full Text: PDF