EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Optimizing Adaptive Notifications in Mobile Health Interventions Systems: Reinforcement Learning from a Data-driven Behavioral Simulator

Shihan Wang, Chao Zhang, Ben Kröse, Herke van Hoof

Journal of Medical Systems · 2021-12 · 45 (12)

DOI: 10.1007/s10916-021-01773-0 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Medical Systems, online erschienen am 18.10.2021. Verfasst von Shihan Wang und 3 weiteren Autor:innen. Beteiligte Einrichtung: Informatics Institute, University of Amsterdam, Amsterdam, Netherlands. s.wang2@uu.nl. Hauptthemen laut MEDLINE: Telemedicine. Die Arbeit wurde bisher 39-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Stichting voor de Technische Wetenschappen, Nationaal Regieorgaan Praktijkgericht Onderzoek SIA.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Mobile health (mHealth) intervention systems can employ adaptive strategies to interact with users. Instead of designing such complex strategies manually, reinforcement learning (RL) can be used to adaptively optimize intervention strategies concerning the user’s context. In this paper, we focus on the issue of overwhelming interactions when learning a good adaptive strategy for the user in RL-based mHealth intervention agents. We present a data-driven approach integrating psychological insights and knowledge of historical data. It allows RL agents to optimize the strategy of delivering context-aware notifications from empirical data when counterfactual information (user responses when receiving notifications) is missing. Our approach also considers a constraint on the frequency of notifications, which reduces the interaction burden for users. We evaluated our approach in several simulation scenarios using real large-scale running data. The results indicate that our RL agent can deliver notifications in a manner that realizes a higher behavioral impact than context-blind strategies.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

TelemedicineAwarenessComputer SimulationHealth BehaviorHumans

Stichwörter der Autor:innen

Adaptive agentHuman simulatorJust-in-time adaptive interventionMobile health interventionReinforcement learning

Autor:innen und Institutionen

  • Informatics Institute, University of Amsterdam, Amsterdam, Netherlands. s.wang2@uu.nl.
  • Information and Computing Sciences, Utrecht University, Utrecht, Netherlands. s.wang2@uu.nl.
  • Department of Psychology, Utrecht University, Utrecht, Netherlands.
  • Human-Technology Interaction, Eindhoven University of Technology, Eindhoven, Netherlands.
  • Informatics Institute, University of Amsterdam, Amsterdam, Netherlands.
  • Digital Life, Amsterdam University of Applied Sciences, Amsterdam, Netherlands.

Förderung

  • Stichting voor de Technische Wetenschappen
  • Nationaal Regieorgaan Praktijkgericht Onderzoek SIA

Zitieren

APA

Wang, S., Zhang, C., Kröse, B., & van Hoof, H. (2021). Optimizing Adaptive Notifications in Mobile Health Interventions Systems: Reinforcement Learning from a Data-driven Behavioral Simulator. Journal of Medical Systems, 45(12). https://doi.org/10.1007/s10916-021-01773-0

Vancouver

Wang S, Zhang C, Kröse B, van Hoof H. Optimizing Adaptive Notifications in Mobile Health Interventions Systems: Reinforcement Learning from a Data-driven Behavioral Simulator. Journal of Medical Systems. 2021;45(12). doi:10.1007/s10916-021-01773-0

BibTeX
@article{Wang2021,
  author = {Wang, Shihan and Zhang, Chao and Kröse, Ben and van Hoof, Herke},
  title = {Optimizing Adaptive Notifications in Mobile Health Interventions Systems: Reinforcement Learning from a Data-driven Behavioral Simulator},
  journal = {Journal of Medical Systems},
  year = {2021},
  volume = {45},
  number = {12},
  doi = {10.1007/s10916-021-01773-0}
}
Kostenlos starten →