An insulin infusion advisory system based on autotuning nonlinear model-predictive control

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

dc.contributor.author	Zarkogianni, K	en
dc.contributor.author	Vazeou, A	en
dc.contributor.author	Mougiakakou, SG	en
dc.contributor.author	Prountzou, A	en
dc.contributor.author	Nikita, KS	en
dc.date.accessioned	2014-03-01T01:35:12Z
dc.date.available	2014-03-01T01:35:12Z
dc.date.issued	2011	en
dc.identifier.issn	0018-9294	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/20981
dc.subject	Artificial pancreas (AP)	en
dc.subject	autotuning model-predictive control	en
dc.subject	personalized model	en
dc.subject	type I diabetes mellitus (T1DM)	en
dc.subject.classification	Engineering, Biomedical	en
dc.subject.other	Advisory systems	en
dc.subject.other	Artificial pancreas (AP)	en
dc.subject.other	Autotuning	en
dc.subject.other	Compartmental model	en
dc.subject.other	Control parameters	en
dc.subject.other	Glucose measurements	en
dc.subject.other	Glucose monitors	en
dc.subject.other	In-silico	en
dc.subject.other	Insulin infusion rate	en
dc.subject.other	Insulin infusions	en
dc.subject.other	Insulin pumps	en
dc.subject.other	On-line adaptation	en
dc.subject.other	personalized model	en
dc.subject.other	Physiological parameters	en
dc.subject.other	Real-time estimation	en
dc.subject.other	Simulation environment	en
dc.subject.other	Type 1 diabetes mellitus	en
dc.subject.other	Type I diabetes	en
dc.subject.other	Estimation	en
dc.subject.other	Forecasting	en
dc.subject.other	Fuzzy logic	en
dc.subject.other	Glucose	en
dc.subject.other	Insulin	en
dc.subject.other	Nonlinear systems	en
dc.subject.other	Parameter estimation	en
dc.subject.other	Physiological models	en
dc.subject.other	Physiology	en
dc.subject.other	Predictive control systems	en
dc.subject.other	Recurrent neural networks	en
dc.subject.other	Model predictive control	en
dc.subject.other	algorithm	en
dc.subject.other	article	en
dc.subject.other	artificial neural network	en
dc.subject.other	blood glucose monitoring	en
dc.subject.other	compartment model	en
dc.subject.other	food intake	en
dc.subject.other	fuzzy logic	en
dc.subject.other	glucose absorption	en
dc.subject.other	glucose blood level	en
dc.subject.other	glucose metabolism	en
dc.subject.other	insulin dependent diabetes mellitus	en
dc.subject.other	insulin infusion	en
dc.subject.other	insulin metabolism	en
dc.subject.other	insulin pump	en
dc.subject.other	intestine absorption	en
dc.subject.other	nonlinear system	en
dc.subject.other	prediction	en
dc.subject.other	Adult	en
dc.subject.other	Algorithms	en
dc.subject.other	Blood Glucose	en
dc.subject.other	Computer Simulation	en
dc.subject.other	Diabetes Mellitus, Type 1	en
dc.subject.other	Fuzzy Logic	en
dc.subject.other	Humans	en
dc.subject.other	Individualized Medicine	en
dc.subject.other	Insulin Infusion Systems	en
dc.subject.other	Models, Biological	en
dc.subject.other	Nonlinear Dynamics	en
dc.subject.other	Pancreas, Artificial	en
dc.subject.other	Signal Processing, Computer-Assisted	en
dc.title	An insulin infusion advisory system based on autotuning nonlinear model-predictive control	en
heal.type	journalArticle	en
heal.identifier.primary	10.1109/TBME.2011.2157823	en
heal.identifier.secondary	http://dx.doi.org/10.1109/TBME.2011.2157823	en
heal.identifier.secondary	5776665	en
heal.language	English	en
heal.publicationDate	2011	en
heal.abstract	This paper aims at the development and evaluation of a personalized insulin infusion advisory system (IIAS), able to provide real-time estimations of the appropriate insulin infusion rate for type 1 diabetes mellitus (T1DM) patients using continuous glucose monitors and insulin pumps. The system is based on a nonlinear model-predictive controller (NMPC) that uses a personalized glucose-insulin metabolism model, consisting of two compartmental models and a recurrent neural network. The model takes as input patients information regarding meal intake, glucose measurements, and insulin infusion rates, and provides glucose predictions. The predictions are fed to the NMPC, in order for the latter to estimate the optimum insulin infusion rates. An algorithm based on fuzzy logic has been developed for the on-line adaptation of the NMPC control parameters. The IIAS has been in silico evaluated using an appropriate simulation environment (UVa T1DM simulator). The IIAS was able to handle various meal profiles, fasting conditions, interpatient variability, intraday variation in physiological parameters, and errors in meal amount estimations. © 2011 IEEE.	en
heal.publisher	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC	en
heal.journalName	IEEE Transactions on Biomedical Engineering	en
dc.identifier.doi	10.1109/TBME.2011.2157823	en
dc.identifier.isi	ISI:000294127700005	en
dc.identifier.volume	58	en
dc.identifier.issue	9	en
dc.identifier.spage	2467	en
dc.identifier.epage	2477	en