EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

On-device reinforcement learning-based insulin dosing controller for fully automated insulin delivery

Jina Lee, Sung-Min Park

Frontiers in Digital Health · 13.11.2026 · 8

DOI: 10.3389/fdgth.2026.1967489 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Digital Health, online erschienen am 13.11.2026. Verfasst von Jina Lee und 1 weiteren Autor:innen. Die Arbeit nennt 76 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Automated insulin delivery (AID) systems integrate continuous glucose monitoring (CGM) with algorithm-driven insulin dosing to enable closed-loop glycemic management for people with type 1 diabetes (T1D). Recent advances in wearable glucose sensing and insulin delivery technologies have enabled increasingly compact AID systems; however, deploying advanced AI-based dosing algorithms directly on resource-constrained wearable devices remains technically challenging. Some AID architectures also rely on external devices, such as smartphones or dedicated controllers, introducing additional communication dependencies into the closed-loop operation.

Methods

This study presents an on-device insulin dosing controller based on the soft actor–critic (SAC) algorithm for resource-constrained AID systems. The proposed approach processes CGM data and makes insulin dosing decisions locally, without relying on external computing devices. To enable embedded deployment, a compressed SAC architecture with a lightweight encoder was developed using quantization-aware training and knowledge distillation, together with an online adaptation mechanism for individualized control. The controller was implemented on a resource-constrained microcontroller and evaluated in a hardware-in-the-loop framework using virtual patients from a T1D simulator.

Results

The proposed controller achieved an average time-in-range of 83% while maintaining real-time on-device execution with millijoule-level energy consumption per control step.

Discussion

These hardware-in-the-loop and in-silico results demonstrate the technical feasibility of real-time reinforcement learning-based insulin dosing and personalization on a resource-constrained embedded platform, while clinical efficacy and safety require further validation.

Förderung

  • National Research Foundation of Korea

Zitieren

APA

Lee, J., & Park, S. (2026). On-device reinforcement learning-based insulin dosing controller for fully automated insulin delivery. Frontiers in Digital Health, 8. https://doi.org/10.3389/fdgth.2026.1967489

Vancouver

Lee J, Park S. On-device reinforcement learning-based insulin dosing controller for fully automated insulin delivery. Frontiers in Digital Health. 2026;8. doi:10.3389/fdgth.2026.1967489

BibTeX
@article{Lee2026,
  author = {Lee, Jina and Park, Sung-Min},
  title = {On-device reinforcement learning-based insulin dosing controller for fully automated insulin delivery},
  journal = {Frontiers in Digital Health},
  year = {2026},
  volume = {8},
  doi = {10.3389/fdgth.2026.1967489}
}
Kostenlos starten →