An insulin infusion advisory system for type 1 diabetes patients based on non-linear model predictive control methods

Zarkogianni, K; Mougiakakou, SG; Prountzou, A; Vazeou, A; Bartsocas, CS; Nikita, KS

dc.contributor.author	Zarkogianni, K	en
dc.contributor.author	Mougiakakou, SG	en
dc.contributor.author	Prountzou, A	en
dc.contributor.author	Vazeou, A	en
dc.contributor.author	Bartsocas, CS	en
dc.contributor.author	Nikita, KS	en
dc.date.accessioned	2014-03-01T02:44:26Z
dc.date.available	2014-03-01T02:44:26Z
dc.date.issued	2007	en
dc.identifier.issn	05891019	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/31828
dc.subject	compartmental model	en
dc.subject	Control Strategy	en
dc.subject	Hybrid Model	en
dc.subject	Kinetics	en
dc.subject	Mathematical Model	en
dc.subject	Non-linear Model	en
dc.subject	Predictive Control	en
dc.subject	Time Delay	en
dc.subject	type 1 diabetes	en
dc.subject	Continuous Subcutaneous Insulin Infusion	en
dc.subject	Neural Network	en
dc.subject	Real Time Recurrent Learning	en
dc.subject.other	Blood	en
dc.subject.other	Insulin	en
dc.subject.other	Mathematical models	en
dc.subject.other	Medical problems	en
dc.subject.other	Nonlinear analysis	en
dc.subject.other	Real time control	en
dc.subject.other	Glucose predictions	en
dc.subject.other	Multiple meal disturbances	en
dc.subject.other	Real Time Recurrent Learning (RTRL)	en
dc.subject.other	Patient monitoring	en
dc.title	An insulin infusion advisory system for type 1 diabetes patients based on non-linear model predictive control methods	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/IEMBS.2007.4353708	en
heal.identifier.secondary	http://dx.doi.org/10.1109/IEMBS.2007.4353708	en
heal.identifier.secondary	4353708	en
heal.publicationDate	2007	en
heal.abstract	In this paper, an Insulin Infusion Advisory System (IIAS) for Type 1 diabetes patients, which use insulin pumps for the Continuous Subcutaneous Insulin Infusion (CSII) is presented. The purpose of the system is to estimate the appropriate insulin infusion rates. The system is based on a Non-Linear Model Predictive Controller (NMPC) which uses a hybrid model. The model comprises a Compartmental Model (CM), which simulates the absorption of the glucose to the blood due to meal intakes, and a Neural Network (NN), which simulates the glucose-insulin kinetics. The NN is a Recurrent NN (RNN) trained with the Real Time Recurrent Learning (RTRL) algorithm. The output of the model consists of short term glucose predictions and provides input to the NMPC, in order for the latter to estimate the optimum insulin infusion rates. For the development and the evaluation of the IIAS, data generated from a Mathematical Model (MM) of a Type 1 diabetes patient have been used. The proposed control strategy is evaluated at multiple meal disturbances, various noise levels and additional time delays. The results indicate that the implemented HAS is capable of handling multiple meals, which correspond to realistic meal profiles, large noise levels and time delays. © 2007 IEEE.	en
heal.journalName	Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings	en
dc.identifier.doi	10.1109/IEMBS.2007.4353708	en
dc.identifier.volume	2007	en
dc.identifier.spage	5971	en
dc.identifier.epage	5974	en