Research Article Comparison of dierent methods for determining diabetes

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