EUVIMEDEUVIMED entdecken
Randomisierte kontrollierte StudieOpen Access

Neural-Net Artificial Pancreas: A Randomized Crossover Trial of a First-in-Class Automated Insulin Delivery Algorithm

Boris Kovatchev iD, Alberto Castillo, Elliott Pryor, Laura L Kollar, Charlotte L Barnett, Mark D DeBoer, Sue A Brown

Diabetes Technology & Therapeutics · 2024-06 · 26 (6) · 375-382

DOI: 10.1089/dia.2023.0469 ↗

Kurz gefasst

Randomisierte kontrollierte Studie in der Zeitschrift Diabetes Technology & Therapeutics, online erschienen am 30.05.2024. Verfasst von Boris Kovatchev und 6 weiteren Autor:innen. Beteiligte Einrichtung: Center for Diabetes Technology, University of Virginia School of Medicine, Charlottesville, Virginia, USA. Hauptthemen laut MEDLINE: Cross-Over Studies, Diabetes Mellitus, Type 1, Insulin, Pancreas, Artificial. Die Arbeit wurde bisher 39-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIDDK NIH HHS, NCATS NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Automated insulin delivery (AID) is now integral to the clinical practice of type 1 diabetes (T1D). The objective of this pilot-feasibility study was to introduce a new regulatory and clinical paradigm—a Neural-Net Artificial Pancreas (NAP)—an encoding of an AID algorithm into a neural network that approximates its action and assess NAP versus the original AID algorithm.

Methods

The University of Virginia Model-Predictive Control (UMPC) algorithm was encoded into a neural network, creating its NAP approximation. Seventeen AID users with T1D were recruited and 15 participated in two consecutive 20-h hotel sessions, receiving in random order either NAP or UMPC. Their demographic characteristics were ages 22–68 years old, duration of diabetes 7–58 years, gender 10/5 female/male, White Non-Hispanic/Black 13/2, and baseline glycated hemoglobin 5.4%–8.1%.

Results

The time-in-range (TIR) difference between NAP and UMPC, adjusted for entry glucose level, was 1 percentage point, with absolute TIR values of 86% (NAP) and 87% (UMPC). The two algorithms achieved similar times

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Cross-Over StudiesDiabetes Mellitus, Type 1InsulinPancreas, ArtificialAlgorithmsInsulin Infusion SystemsNeural Networks, ComputerHypoglycemic AgentsBlood GlucoseHumansFemaleMaleMiddle AgedAdultAgedYoung AdultPilot ProjectsFeasibility Studies

Stichwörter der Autor:innen

Automated insulin delivery (AID)Hybrid closed-loop (HCL)Machine learningNeural networksType 1 diabetes

Substanzen

InsulinHypoglycemic AgentsBlood Glucose

Autor:innen und Institutionen

  • Center for Diabetes Technology, University of Virginia School of Medicine, Charlottesville, Virginia, USA.

ORCID-Profile: Boris Kovatchev

Förderung

  • NIDDK NIH HHS
  • NCATS NIH HHS

Zitieren

APA

Kovatchev, B., Castillo, A., Pryor, E., Kollar, L. L., Barnett, C. L., DeBoer, M. D., & Brown, S. A. (2024). Neural-Net Artificial Pancreas: A Randomized Crossover Trial of a First-in-Class Automated Insulin Delivery Algorithm. Diabetes Technology & Therapeutics, 26(6), 375-382. https://doi.org/10.1089/dia.2023.0469

Vancouver

Kovatchev B, Castillo A, Pryor E, Kollar LL, Barnett CL, DeBoer MD, et al. Neural-Net Artificial Pancreas: A Randomized Crossover Trial of a First-in-Class Automated Insulin Delivery Algorithm. Diabetes Technology & Therapeutics. 2024;26(6):375-382. doi:10.1089/dia.2023.0469

BibTeX
@article{Kovatchev2024,
  author = {Kovatchev, Boris and Castillo, Alberto and Pryor, Elliott and Kollar, Laura L and Barnett, Charlotte L and DeBoer, Mark D and Brown, Sue A},
  title = {Neural-Net Artificial Pancreas: A Randomized Crossover Trial of a First-in-Class Automated Insulin Delivery Algorithm},
  journal = {Diabetes Technology & Therapeutics},
  year = {2024},
  volume = {26},
  number = {6},
  pages = {375--382},
  doi = {10.1089/dia.2023.0469}
}
Kostenlos starten →