Intelligent Closed-Loop Insulin Delivery Systems for ICU Patients
Интеллектуальные системы замкнутого управления доставкой инсулина для пациентов отделений интенсивной терапии
2013-06-18
SCID: 54.1/y3g6hgxc
Discuss with AI
closed-loop insulin deliverycontrol-variability grid analysisintensive care unit patientsmodel predictive controlparticle swarm optimization
Figures from the paper
Abstract (AI)
Good glycemic control through insulin administration among intensive care unit (ICU) patients can reduce mortality significantly; however, it remains a big challenge because of scarcity of individualized models for ICU patients. To deal with this challenge, a new combination of particle swarm optimization (PSO) and model predictive control (MPC) has been proposed to identify the model online as well as to optimally design the input, i.e., the insulin delivery rate automatically. According to the population distribution, ten typical linear dynamic models were selected such that any patient's model could be approximated by a linear combination of these ten typical models. PSO was used to update the weight coefficients while MPC was used to design the insulin delivery rate based on the combination model identified by using PSO. The proposed strategy was compared with the Yale protocol on 30 virtual subjects. According to the control-variability grid analysis, the percentage values in A + B zone were, respectively, 100% under the proposed strategy and while 51% under the Yale protocol, which demonstrates the superior performance of the proposed strategy. As a good candidate for the full closed-loop insulin delivery method, this new combination can control the glucose level by bringing it to a safe range promptly thereby reducing the risk of death.
Key Findings
1
A combined particle swarm optimization and model predictive control strategy identifies ICU patient glucose-insulin dynamics online and automatically designs insulin delivery rates.
2
Model predictive control determines insulin delivery using the online-identified combination model, enabling individualized closed-loop glucose regulation.
3
On 30 virtual subjects, the proposed strategy placed 100% of outcomes in zones A+B of the control-variability grid, compared with 51% for the Yale protocol.
4
Ten typical linear dynamic models represent individual ICU patients through patient-specific linear combinations, with particle swarm optimization updating the model weights.
5
The strategy promptly brought glucose levels into a safe range and was identified as a candidate full closed-loop insulin delivery approach for reducing mortality risk.
Research Object
closed-loop insulin delivery systems for intensive care unit patients
Research Subject
automatic blood-glucose regulation and insulin delivery-rate optimization under individualized patient-model uncertainty
Publication Details
Publication Date
2013-06-18
Journal
Publisher
ISSN
Cited by
15
Access Type
Author Information
Download PDF
Subscribe to digest