ANN Techniques and Their Applications in Accurate Blood Glucose Level Prediction of Type II Diabetes

Abstract

Diabetes is a chronic disease wherein the body doesn’t produce enough or any insulin, doesn’t properly utilize the insulin that is produced, or shows a combination of both. When any of these occur the body is unable to get sugar from the blood into the cells which lead to rise in blood sugar levels. Diabetes is characterized by increase in blood glucose level either because of insufficient insulin discharge (type I diabetes) or impeded insulin action (type II diabetes). It is a vital health problem which can cause physical disability and even death in some cases.

Diabetes has affected over 246 million people worldwide as indicated by the World Health Organization (WHO) report, and this number is predicted to ascend to more than 592 million in 2035. In India, the type of diabetes differs considerably from the western world i.e. Type I diabetes is considerably rarer, while more than 90% of the people are diagnosed with Type II diabetes. Due to the high occurrence of Type II diabetes in recent years, the forecast and early prediction of the disease have become more important.

An artificial neural network (ANN) is a network of artificial neurons, similar to the ones found in human brain which is used for solving artificial intelligence problems such as image identification, pattern recognition, classification, prediction, data compression and optimization. A number of ANN techniques have been applied for prediction and classification of diabetes. After reviewing various literature papers, this study is aimed to identify the technique among different artificial neural network techniques that can be used to predict accurate blood sugar level of Type II diabetes.