EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Evidence-Driven Simulated Data in Reinforcement Learning Training for Personalized mHealth Interventions

Juan Carlos Caro, Giorgio Galgano, Melissa Muñoz, Jorge Díaz Ramírez, Jorge Maluenda

Applied Sciences · 02.04.2026 · 16 (7) · 3463

DOI: 10.3390/app16073463 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 02.04.2026. Verfasst von Juan Carlos Caro und 4 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Chilean National Agency for Research and Development ANID.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Physical inactivity is a major preventable cause of non-communicable disease and premature mortality. Mobile health interventions can promote physical activity, but their effectiveness depends on the ability to adapt to user’s context and motivation. Reinforcement learning (RL), particularly contextual bandits (CBs), offers a promising framework for such adaptive personalization. However, in practice, RL-based models face the cold start problem (CSP), due to the lack of initial training data. This study examines whether theory-driven simulated data can mitigate the CSP in training RL systems for personalized physical activity recommendations. A scoping review of 18 empirical studies on the Integrated Behavioral Change Model (IBC) provided population parameters for key constructs, used to simulate 2000 virtual users via multivariate modeling and structural equation calibration. A CB algorithm with an ε-greedy policy was trained with this dataset and compared with data from real world pilot using the Apptivate mHealth web-app (n = 588). Results showed close alignment between simulated and real behaviors. Our findings demonstrate that behaviorally informed synthetic data can effectively be used to train RL algorithms, offering an interpretable, sustainable, scalable, and privacy-safe solution to the CSP in personalized digital health interventions.

Förderung

  • Chilean National Agency for Research and Development ANID

Zitieren

APA

Caro, J. C., Galgano, G., Muñoz, M., Ramírez, J. D., & Maluenda, J. (2026). Evidence-Driven Simulated Data in Reinforcement Learning Training for Personalized mHealth Interventions. Applied Sciences, 16(7), 3463. https://doi.org/10.3390/app16073463

Vancouver

Caro JC, Galgano G, Muñoz M, Ramírez JD, Maluenda J. Evidence-Driven Simulated Data in Reinforcement Learning Training for Personalized mHealth Interventions. Applied Sciences. 2026;16(7):3463. doi:10.3390/app16073463

BibTeX
@article{Caro2026,
  author = {Caro, Juan Carlos and Galgano, Giorgio and Muñoz, Melissa and Ramírez, Jorge Díaz and Maluenda, Jorge},
  title = {Evidence-Driven Simulated Data in Reinforcement Learning Training for Personalized mHealth Interventions},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {7},
  pages = {3463},
  doi = {10.3390/app16073463}
}
Kostenlos starten →