An Insulin Infusion Advisory System Based on Autotuning Nonlinear Model-Predictive Control
Система рекомендаций по инфузии инсулина на основе самонастраивающегося нелинейного управления с прогнозированием модели
2011-05-27
SCID: 54.1/ncytkpsq
Discuss with AI
continuous glucose monitoringfuzzy logic autotuninginsulin infusion advisory systemnonlinear model-predictive controltype 1 diabetes mellitus
Figures from the paper
Abstract (AI)
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 patient's 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.
Key Findings
1
An online fuzzy-logic algorithm adapts the NMPC control parameters to account for changing patient conditions.
2
Developed a personalized insulin infusion advisory system combining continuous glucose monitoring, insulin pumps, and nonlinear model-predictive control.
3
In silico evaluation with the UVA T1DM simulator showed robustness across varied meals, fasting, interpatient and intraday physiological variability, and meal-estimation errors.
4
The system uses a personalized glucose-insulin model comprising two compartmental models and a recurrent neural network to predict future glucose levels.
Research Object
personalized insulin infusion advisory system for type 1 diabetes mellitus patients
Research Subject
real-time estimation and adaptive control of appropriate insulin infusion rates under meal, fasting, patient-variability, intraday-variation, and meal-estimation-error conditions
Publication Details
Publication Date
2011-05-27
Journal
Publisher
ISSN
Cited by
80
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai5
Meal Simulation Model of the Glucose-Insulin System2007
In Silico Preclinical Trials: A Proof of Concept in Closed-Loop Control of Type 1 Diabetes2009
Model Predictive Control of Type 1 Diabetes: An in Silico Trial2007
GIM, Simulation Software of Meal Glucose—Insulin Model2007
Zone Model Predictive Control: A Strategy to Minimize Hyper- and Hypoglycemic Events2010