EUVIMEDEUVIMED entdecken
Crossref

Design and Simulation of an AI ‐Powered Artificial Pancreas System With Personalized Glucose Sensing and Insulin Delivery

G Kalyani iD, T Pratap iD, Sateesh Jasti iD

Artificial Organs · 13.11.2026

DOI: 10.1111/aor.70278 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Artificial Organs, online erschienen am 13.11.2026. Verfasst von G Kalyani und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Information Technology, Siddhartha Academy of Higher Education (Deemed to be University), Vijayawada, India. Die Arbeit nennt 28 Literaturangaben. Gefördert von: Anusandhan National Research Foundation (ANRF), Govt. of India.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Achieving tight glycemic control in Type 1 diabetes is challenged by non‐linear metabolic dynamics and insulin‐stacking risk. Artificial intelligence models offer improved personalization, but their opacity raises safety concerns, particularly for basal insulin dosing, which is often treated as static in existing decision‐support systems.

Methods

We propose a hybrid closed‐loop system combining a data‐driven LightGBM regressor for basal dose prediction, trained on the T1D‐UOM dataset, with a physiologically grounded, rule‐based safety layer at the edge. Basal insulin is predicted from cyclical time encoding and glucose rate‐of‐change; bolus dosing follows carbohydrate intake and correction requirements. A time‐bounded insulin‐on‐board model, an uncertainty‐adaptive post‐bolus damping factor, and a predictive low‐glucose‐suspend rule reproducing the Tandem Basal‐IQ protocol together suspend or reduce delivery when residual insulin is high or hypoglycemia is projected. The system was evaluated in silico over 60 continuous days under shadow‐mode replay and closed‐loop reduced‐order simulation, including an ablation with bolus delivery suppressed.

Results

Under chronological, within‐subject validation, the offline basal estimator achieved and U; under strict leave‐one‐subject‐out validation on the same real cohort, performance did not generalize to unseen subjects (, U). The hybrid controller maintained Time‐in‐Range at 62.8% within the reduced‐order closed‐loop simulation, with no violations of the insulin‐on‐board suspension or damping rules; suppressing bolus delivery in an ablation within this simulation dropped Time‐in‐Range to 26.1%, indicating that, within the reduced‐order model, bolus delivery is a determinant of simulated glycemic outcome.

Conclusions

The proposed architecture demonstrates a safety‐audited template for combining machine‐learning basal prediction with clinically grounded dosing rules. Validation on real outcome data and physical hardware is identified as the next steps toward clinical translation.

Schlagwörter

Stichwörter der Autor:innen

LightGBMType 1 diabetesartificial intelligenceartificial pancreasclosed‐loop control systeminsulin dose prediction

Autor:innen und Institutionen

  • Department of Information Technology, Siddhartha Academy of Higher Education (Deemed to be University), Vijayawada, India.
  • Department of Electronics and Communication Engineering, Siddhartha Academy of Higher Education (Deemed to be University), Vijayawada, India.

ORCID-Profile: G Kalyani, T Pratap, Sateesh Jasti

Förderung

  • Anusandhan National Research Foundation (ANRF), Govt. of India

Zitieren

APA

Kalyani, G., Pratap, T., & Jasti, S. (2026). Design and Simulation of an AI ‐Powered Artificial Pancreas System With Personalized Glucose Sensing and Insulin Delivery. Artificial Organs. https://doi.org/10.1111/aor.70278

Vancouver

Kalyani G, Pratap T, Jasti S. Design and Simulation of an AI ‐Powered Artificial Pancreas System With Personalized Glucose Sensing and Insulin Delivery. Artificial Organs. 2026. doi:10.1111/aor.70278

BibTeX
@article{Kalyani2026,
  author = {Kalyani, G and Pratap, T and Jasti, Sateesh},
  title = {Design and Simulation of an AI ‐Powered Artificial Pancreas System With Personalized Glucose Sensing and Insulin Delivery},
  journal = {Artificial Organs},
  year = {2026},
  doi = {10.1111/aor.70278}
}
Kostenlos starten →