Abstract

Info

Title:: Insulin evaluation and prediction model based on back-propagation neural network

Author(s):: ZHONG Tingting1; ZHANG Di1; CHEN Zhencheng2; ZOU Chunlin3; ZHU Jianming2; ZHAO Feijun2; LIANG Yongbo2; 1. School of Electronic Engineering and Automation, Guilin University of Electronic Technology, Guilin 541004, China; 2. School of Life and Environmental Sciences, Guilin University of Electronic Technology, Guilin 541004, China; 3. Transforming Medical Research Center, Guangxi Medical University, Nanning 530021, China

Keywords:: ; Keywords: diabetes mellitus; insulin; cynomolgus monkey; oral glucose tolerance test; back-propagation neural network

Abstract:: Abstract: In the research and treatment of diabetes mellitus, abnormal blood glucose will not only seriously affect the physiological functions, but also damage the tissues. Therefore, the research of insulin evaluation and prediction model is of great clinical significance for maintaining blood glucose balance. In order to understand the effects of insulin on blood glucose regulation, the related data of blood glucose-insulin metabolism system were obtained by oral glucose tolerance test in cynomolgus monkey. After screening and preprocessing the obtained data, insulin function evaluation indexes were selected as the characteristic parameters. According to the level of glucose tolerance of cynomolgus monkey, an insulin prediction model based on back-propagation neural network was established, and the predicted values of insulin evaluation indexes had a good correlation with the true values. In the proposed model, blood glucose level and physiological parameters are used to evaluate insulin secretion, thus assessing and predicting the role of insulin in the blood sugar regulation process, which provides certain reference information for glucose tolerance assessment and assists in the diagnosis of diabetes mellitus.