Personalized Glucose Management With AI: Pilot Study Using a Multiarmed Bandit Approach
JMIR Formative Research · 19.03.2026 · 10 · e70826-e70826
DOI: 10.2196/70826 ↗Kurz gefasst
Fachartikel in der Zeitschrift JMIR Formative Research, online erschienen am 19.03.2026. Verfasst von Shinji Hotta und 4 weiteren Autor:innen. Beteiligte Einrichtung: Fujitsu Limited, 4-1-1 Kamikodanaka, Nakahara-ku, Kawasaki, Kanagawa, 211-8588, Japan, 81 44 777 1111. Hauptthemen laut MEDLINE: Blood Glucose, Precision Medicine, Artificial Intelligence, Glycemic Control. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Background
Personalized behavioral recommendations through mobile apps have proven effective in preventing serious chronic diseases such as diabetes. Recent studies have primarily focused on optimizing personalized recommendations using reinforcement learning. However, the main problem with these approaches is that they focus on behavioral changes and overlook clinical outcomes.
Objective
This study aimed to propose a method for online planning of dietary and exercise recommendations to optimize postprandial glucose levels through behavioral changes directly.
Methods
The proposed method is a multiarmed bandit based on a two-stage reward prediction model, where an action is a combination of the total carbohydrate intake and postprandial walking duration, and the reward is the reduction in postprandial glucose levels. We implemented the prediction of the reward for each action based on the predicted behavioral responses to an action, and subsequently, the postprandial glycemic response.
Results
In a simulation experiment, we demonstrated that the proposed online algorithm can significantly improve postprandial glucose levels with personalized recommendations, compared to the randomized policy. Furthermore, we conducted a small real-world experiment with a simplified proposed method involving a single update of the recommendation policy into a personalized one. For 6 participants, compared to the randomized policy, we observed a 23% improvement, on average, in actual glucose responses along with the behavioral adherence to the recommendations concerning carbohydrate intake and postprandial walking.
Conclusions
The preliminary effectiveness of the proposed method was demonstrated from both the simulation experiment and the small real-world experiment. However, further longitudinal real-world experiments in patients with diabetes are needed to validate and generalize the findings.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Fujitsu Limited, 4-1-1 Kamikodanaka, Nakahara-ku, Kawasaki, Kanagawa, 211-8588, Japan, 81 44 777 1111.
- Department of Computer Science, Aalto University, Espoo, Uusimaa, Finland.
- Development and Strategy Unit, Helsinki University Hospital, University of Helsinki, Helsinki, Uusimaa, Finland.
- Department of Computer Science, University of Helsinki, Helsinki, Uusimaa, Finland.
- Department of Obstetrics and Gynecology, Helsinki University Hospital, University of Helsinki, Helsinki, Uusimaa, Finland.
ORCID-Profile: Shinji Hotta, Mikko Kytö, Saila Koivusalo, Seppo Heinonen, Pekka Marttinen
Zitieren
APA
Hotta, S., Kytö, M., Koivusalo, S., Heinonen, S., & Marttinen, P. (2026). Personalized Glucose Management With AI: Pilot Study Using a Multiarmed Bandit Approach. JMIR Formative Research, 10, e70826-e70826. https://doi.org/10.2196/70826
Vancouver
Hotta S, Kytö M, Koivusalo S, Heinonen S, Marttinen P. Personalized Glucose Management With AI: Pilot Study Using a Multiarmed Bandit Approach. JMIR Formative Research. 2026;10:e70826-e70826. doi:10.2196/70826
BibTeX
@article{Hotta2026,
author = {Hotta, Shinji and Kytö, Mikko and Koivusalo, Saila and Heinonen, Seppo and Marttinen, Pekka},
title = {Personalized Glucose Management With AI: Pilot Study Using a Multiarmed Bandit Approach},
journal = {JMIR Formative Research},
year = {2026},
volume = {10},
pages = {e70826--e70826},
doi = {10.2196/70826}
}
EUVIMED