Diabetes mellitus forecast using artificial neural network (ANN)

The diabetes mellitus forecasting using ANN is presented in this paper. The result of this study will provide solutions to the medical staff in determining whether someone is the diabetes sufferer or not which is much easier rather than currently doing a blood test. The back-propagation algorithm has been chosen for learning and testing of 768 data whereby 268 of them are diagnosed with diabetes. Inputs to the network are number of times pregnant, plasma glucose concentration, blood pressure, triceps skin fold thickness, serum insulin, body mass index, diabetes pedigree function and age. The network with eight inputs and four inputs are then tested and results obtained are compared in terms of error. The outcome of this study is whether someone is the diabetes sufferer or not. Accurate results have been obtained which proves the effectiveness of the proposed ANN.