Prediction of the Onset of Diabetes Using Artificial Neural Network and Pima Indians Diabetes Dataset
Kamlesh Lakhwani, Sandeep Bhargava, Kamal Kant Hiran, Mahesh Bundele, Devendra Somwanshi
Abstract
When a human body unable to respond to the insulin properly and/or unable to produce the required amount of insulin to regulate glucose, it means that the human body is suffering from Diabetes. Diabetes increases the risk of developing another disease like heart disease, kidney disease, and damage to blood vessels, nerve damage, and blindness. The diagnosis of diabetes using proper analysis of diabetes data is a significant problem. In this paper, an automatic diagnosis system is introduced and analyzed. For this purpose, a Three-Layered Artificial Neural Network (ANN) and Pima Indians Diabetes dataset are used. In this ANN based prediction model, a logistic-activation-function for activation of neurons, and the Quasi Newton method is used as the algorithm for the training. As a result cumulative gain plot and as a measure of the quality of this model the maximum gain score is used.