Diabetes Detection Using Artificial Neural Networks 26 Back-Propagation Algorithm

This is a project aimed at predicting the chances of diabetes in a person that whether or not is heshe prone to it. We have used certain parameters namely number of pregnancies glucose BP skin fold insulin body mass index pedigree and age. The database of 768 patients with these parameters each was taken from National Institute of Diabetes and Digestive and Kidney Diseases. Using neural network feed forward prediction model in conjunction with back propagation algorithm and given training data set we predicted whether a subject was likely to have diabetes.