Prediction of diabetes Type-II Using a two-class neural network

Abstract

Diabetes is one of the most frightful diseases that is creating a terror in peoples mind all over the globe and all of them are putting tremendous efforts to search for various methods to prevent this disease at the budding stage by predicting the symptoms of diabetes. In this paper, our main aim is to predict the onset of diabetes amongst women aged at least 21 years using Two-class Neural Network and tabulate and compare our results with others results. This approach has been tested with the Pima Indians Diabetes Data Set downloaded from the UCI Machine Learning data repository. The performance of our predictive model has been measured and compared in terms of accuracy and recall. Endocrinologists, dietitians, ophthalmologists and podiatrists can use this model to predict how likely a patient is to suffer from diabetes.