Detection and Prediction of Diabetes Mellitus Using Back-Propagation Neural Network

Diabetes mellitus is one of the chronic disease as recent estimation in 2015 shows 415 million people suffering from diabetes worldwide and estimated to have deaths of 1.5 to 5 million each year. It is very important to forecast tool which can be used to determine whether someone has diabetes or not. There are some methods which produce accurate prediction and Artificial neural network using Back propagation neural network is one of them. This neural network having an input layer with 8 parameters, one hidden layer with 10 neurons and one output layer is implemented to produce good results. The GUI is developed to make tool user friendly so that patients can get accurate test results even from assistants in the absence of a doctor. This project will help even doctors get records of the patient within seconds so t h a t it will save time for further treatment of patients. This paper summarizes the implementation and development of the software tool built in MATLAB which will predict whether someone is diabetic or not. The performance of the BPNN used for predicting diabetes is 81 percent, which shows improvement in previous work. This is a better method than finger stick which is very painful if carried out more number of times.