Prediction of the Blood Glucose Metabolism in Diabetic Patients Using a Neural Network

Abstract: Diabetes is a serious metabolic disorder; if the patient does not follow the proper management of the blood glucose level the patient have always risk of kidney disease, heart attack and renal failure. In this paper we can predict that the person is having diabetic or not and which level of diabetes the patient is having by using the principal of artificial neural network. The proposed system makes separate blood glucose prediction taking the blood report's data. Comparisons of the diagnostic accuracy with other neural network models, which use the same dataset, are made. The comparison of the results overall improves the accuracy which is the effectiveness of the proposed system.

Keywords: Wavelet neural network, principal component Analysis, Time-series, Diabetes Mellitus.