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