Comparing individualization strategies of Model Predictive Control for Artificial Pancreas

Сравнение стратегий индивидуализации управления с прогнозирующей моделью для искусственной поджелудочной железы
Francesco Prendin, Simone Del Favero, Alessandro Chiuso, Lorenzo Cester
2025-01-01

Artificial PancreasModel Predictive ControlType 1 DiabetesUVa/Padova T1D Simulatorglucose-insulin dynamics
Personalization is a key in developing technologies for Type 1 Diabetes (T1D) management, given the large inter- and intra-variability in patients response. This holds in the design of Artificial Pancreas (AP) systems as well. Model Predictive Control (MPC) is one of the most adopted control strategies for this purpose. Leveraging a model of glucose-insulin dynamics, MPC proactively adjusts insulin infusion based on the predicted impact of this action on glucose concentration level. Personalization strategies in MPC could be based on the use of individual-specific models and/or rely on the customization of the cost function. A comparison of these approaches seems to be missing in literature. Therefore, this work investigates three levels of individualization (of cost only, model only, and both cost and model) for a MPC-based AP system. Their comparison is performed using the UVa/Padova T1D Simulator (v.S2014). The latter two strategies are found to significantly outperform the former, provided that the adopted individualized model is compliant with basic physiological requirements.
1
Both model-only and combined model-and-cost personalization are effective when the individualized model satisfies basic physiological requirements.
2
Evaluations using the UVa/Padova T1D Simulator (v.S2014) show that model-based individualization strategies significantly outperform cost-only individualization.
3
The findings highlight individualized glucose-insulin dynamics models as more important than cost-function customization alone for MPC-based T1D management.
4
The study compares three MPC personalization strategies for artificial pancreas systems: individualized cost function, individualized model, and simultaneous model-and-cost individualization.

MPC-based artificial pancreas systems for Type 1 Diabetes management

The effects of individualizing the MPC cost function, the glucose–insulin dynamics model, or both on blood-glucose control performance

Publication Details
Publication Date
2025-01-01
Journal
Publisher
ISSN
Cited by
0
Access Type
Author Information
Authors
Francesco Prendin
Simone Del Favero
Alessandro Chiuso
Lorenzo Cester
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%