Neural network based glucose - Insulin metabolism models for children with type 1 diabetes

Mougiakakou, SG; Prountzou, A; Iliopoulou, D; Nikita, KS; Vazeou, A; Bartsocas, CS

dc.contributor.author	Mougiakakou, SG	en
dc.contributor.author	Prountzou, A	en
dc.contributor.author	Iliopoulou, D	en
dc.contributor.author	Nikita, KS	en
dc.contributor.author	Vazeou, A	en
dc.contributor.author	Bartsocas, CS	en
dc.date.accessioned	2014-03-01T02:44:07Z
dc.date.available	2014-03-01T02:44:07Z
dc.date.issued	2006	en
dc.identifier.issn	05891019	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/31688
dc.subject	Adaptive Learning Rate	en
dc.subject	Artificial Neural Network	en
dc.subject	Back Propagation Algorithm	en
dc.subject	compartmental model	en
dc.subject	Food Intake	en
dc.subject	type 1 diabetes	en
dc.subject	Continuous Glucose Monitoring System	en
dc.subject	Feed Forward	en
dc.subject	Neural Network	en
dc.subject	Real Time Recurrent Learning	en
dc.subject.other	Computer simulation	en
dc.subject.other	Insulin	en
dc.subject.other	Learning aids for handicapped persons	en
dc.subject.other	Metabolism	en
dc.subject.other	Neural networks	en
dc.subject.other	Physiological models	en
dc.subject.other	Real time systems	en
dc.subject.other	Compartmental Models (CM)	en
dc.subject.other	Plasma insulin concentration	en
dc.subject.other	Real Time Recurrent Learning (RTRL)	en
dc.subject.other	Glucose	en
dc.title	Neural network based glucose - Insulin metabolism models for children with type 1 diabetes	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/IEMBS.2006.260640	en
heal.identifier.secondary	http://dx.doi.org/10.1109/IEMBS.2006.260640	en
heal.identifier.secondary	4030424	en
heal.publicationDate	2006	en
heal.abstract	In this paper two models for the simulation of glucose-insulin metabolism of children with Type 1 diabetes are presented. The models are based on the combined use of Compartmental Models (CMs) and artificial Neural Networks (NNs). Data from children with Type 1 diabetes, stored in a database, have been used as input to the models. The data are taken from four children with Type 1 diabetes and contain information about glucose levels taken from continuous glucose monitoring system, insulin intake and food intake, along with corresponding time. The influences of taken insulin on plasma insulin concentration, as well as the effect of food intake on glucose input into the blood from the gut, are estimated from the CMs. The outputs of CMs, along with previous glucose measurements, are fed to a NN, which provides short-term prediction of glucose values. For comparative reasons two different NN architectures have been tested: a Feed-Forward NN (FFNN) trained with the back-propagation algorithm with adaptive learning rate and momentum, and a Recurrent NN (RNN), trained with the Real Time Recurrent Learning (RTRL) algorithm. The results indicate that the best prediction performance can be achieved by the use of RNN. © 2006 IEEE.	en
heal.journalName	Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings	en
dc.identifier.doi	10.1109/IEMBS.2006.260640	en
dc.identifier.volume	1	en
dc.identifier.spage	3545	en
dc.identifier.epage	3548	en