This work presents a Model Predictive Control (MPC) for the artificial pancreas, which is able to autonomously manage basal insulin injections in type 1 diabetic patients. Specifically, the MPC goal is to maintain the patients’ blood glucose level inside the safe range of 70-180 mg/dL, acting on the insulin amount and respecting all the imposed constraints, taking into consideration also the Insulin On Board (IOB), to avoid excess of insulin infusion. MPC uses a model to make predictions of the system behavior. In this work, due to the complexity of the diabetes disease that complicates the identification of a general physiological model, a data-driven learning method is employed instead. The Componentwise Hölder Kinky Inference (CHoKI) method is adopted, to have a customized controller for each patient. For the data collection phase and also to test the proposed controller, the virtual patients of the FDA-accepted UVA/Padova simulator are exploited. The MPC is also tested on simulations with variability of the insulin sensitivity and with physical activity sessions. The final results are satisfying since the proposed controller is conservative and reduces the time in hypoglycemia (which is more dangerous) if compared to the outcomes obtained without the IOB constraints.

(2025). CHoKI-based MPC for blood glucose regulation in Artificial Pancreas [journal article - articolo]. In IFAC JOURNAL OF SYSTEMS AND CONTROL. Retrieved from https://hdl.handle.net/10446/291546

CHoKI-based MPC for blood glucose regulation in Artificial Pancreas

Sonzogni, Beatrice;Previdi, Fabio;Ferramosca, Antonio
2025-01-01

Abstract

This work presents a Model Predictive Control (MPC) for the artificial pancreas, which is able to autonomously manage basal insulin injections in type 1 diabetic patients. Specifically, the MPC goal is to maintain the patients’ blood glucose level inside the safe range of 70-180 mg/dL, acting on the insulin amount and respecting all the imposed constraints, taking into consideration also the Insulin On Board (IOB), to avoid excess of insulin infusion. MPC uses a model to make predictions of the system behavior. In this work, due to the complexity of the diabetes disease that complicates the identification of a general physiological model, a data-driven learning method is employed instead. The Componentwise Hölder Kinky Inference (CHoKI) method is adopted, to have a customized controller for each patient. For the data collection phase and also to test the proposed controller, the virtual patients of the FDA-accepted UVA/Padova simulator are exploited. The MPC is also tested on simulations with variability of the insulin sensitivity and with physical activity sessions. The final results are satisfying since the proposed controller is conservative and reduces the time in hypoglycemia (which is more dangerous) if compared to the outcomes obtained without the IOB constraints.
antonio.ferramosca@unibg.it
articolo
2024
2025
Inglese
online
31
Art. n. 100294
1
13
Settore IINF-04/A - Automatica
Artificial Pancreas; MPC; Learning-based control
   ANTHEM - AdvaNced Technologies for Human-centrEd Medicine
   ANTHEM
   MUR - MINISTERO DELL'UNIVERSITA' E DELLA RICERCA - Segretariato generale Direzione generale della ricerca - Ufficio IV
Sonzogni, Beatrice; Manzano, José María; Polver, Marco; Previdi, Fabio; Ferramosca, Antonio
info:eu-repo/semantics/article
open
(2025). CHoKI-based MPC for blood glucose regulation in Artificial Pancreas [journal article - articolo]. In IFAC JOURNAL OF SYSTEMS AND CONTROL. Retrieved from https://hdl.handle.net/10446/291546
Non definito
5
1.1 Contributi in rivista - Journal contributions::1.1.01 Articoli/Saggi in rivista - Journal Articles/Essays
262
File allegato/i alla scheda:
File Dimensione del file Formato  
1. Bea - ChoKi_IFAC_JSC.pdf

accesso aperto

Versione: publisher's version - versione editoriale
Licenza: Creative commons
Dimensione del file 2.79 MB
Formato Adobe PDF
2.79 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

Aisberg ©2008 Servizi bibliotecari, Università degli studi di Bergamo | Terms of use/Condizioni di utilizzo

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10446/291546
Citazioni
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact