EUVIMEDObjevte EUVIMED
Randomisierte kontrollierte StudieOpen access

Effectiveness of a Digital Health Intervention Leveraging Reinforcement Learning: Results From the Diabetes and Mental Health Adaptive Notification Tracking and Evaluation (DIAMANTE) Randomized Clinical Trial

Adrian Aguilera iD, Marvyn Arévalo Avalos iD, Jing Xu iD, Bibhas Chakraborty iD, Caroline Figueroa iD, Faviola Garcia iD, Karina Rosales iD, Rosa Hernandez-Ramos iD, Chris Karr iD, Joseph Williams iD, Lisa Ochoa-Frongia iD, Urmimala Sarkar iD and 2 more

Journal of Medical Internet Research · 2024-10-08 · 26 · e60834

DOI: 10.2196/60834 ↗

At a glance

Randomisierte kontrollierte Studie in Journal of Medical Internet Research, published on 2024-10-08. Written by Adrian Aguilera and 13 co-authors. Institution: School of Social Welfare, University of California Berkeley, Berkeley, CA, United States. Major MEDLINE topics: Text Messaging. Cited 38 times so far (Crossref); 25 references. The full text is freely available in PubMed Central. Funded by: NIDDK NIH HHS, AHRQ HHS.

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

Background

Digital and mobile health interventions using personalization via reinforcement learning algorithms have the potential to reach large number of people to support physical activity and help manage diabetes and depression in daily life.

Objective

The Diabetes and Mental Health Adaptive Notification and Tracking Evaluation (DIAMANTE) study tested whether a digital physical activity intervention using personalized text messaging via reinforcement learning algorithms could increase step counts in a diverse, multilingual sample of people with diabetes and depression symptoms.

Methods

From January 2020 to June 2022, participants were recruited from 4 San Francisco, California–based public primary care clinics and through web-based platforms to participate in the 24-week randomized controlled trial. Eligibility criteria included English or Spanish language preference and a documented diagnosis of diabetes and elevated depression symptoms. The trial had 3 arms: a Control group receiving a weekly mood monitoring message, a Random messaging group receiving randomly selected feedback and motivational text messages daily, and an Adaptive messaging group receiving text messages selected by a reinforcement learning algorithm daily. Randomization was performed with a 1:1:1 allocation. The primary outcome, changes in daily step counts, was passively collected via a mobile app. The primary analysis assessed changes in daily step count using a linear mixed-effects model. An a priori subanalysis compared the primary step count outcome within recruitment samples.

Results

In total, 168 participants were analyzed, including those with 24% (40/168) Spanish language preference and 37.5% (63/168) from clinic-based recruitment. The results of the linear mixed-effects model indicated that participants in the Adaptive arm cumulatively gained an average of 3.6 steps each day (95% CI 2.45-4.78; P

Subjects

MeSH terms (MEDLINE)

Text MessagingHumansFemaleMaleMiddle AgedReinforcement, PsychologyAdultDiabetes MellitusTelemedicineDepressionAgedExerciseSan FranciscoMental HealthDigital Health

Author keywords

SMSdepressiondiabetesdigital healthexercisemachine learningmobile phonephysical activityreinforcement learningstepstext messageswalking

Authors and institutions

  • School of Social Welfare, University of California Berkeley, Berkeley, CA, United States.
  • Department of Psychiatry and Behavioral Sciences, University of California-San Francisco, San Francisco, CA, United States.
  • Centre for Quantitative Medicine, Duke-NUS Medical School, National University of Singapore, Singapore, Singapore.
  • Faculty of Technology, Policy, and Management, Delft Technical University, Delft, Netherlands.
  • Action Research Center (ARC) for Health Equity, Department of Medicine, University of California-San Francisco, San Francisco, CA, United States.
  • Department of Psychological Sciences, University of California Irvine, Irvine, CA, United States.

ORCID profiles: Adrian Aguilera, Marvyn Arévalo Avalos, Jing Xu, Bibhas Chakraborty, Caroline Figueroa, Faviola Garcia, Karina Rosales, Rosa Hernandez-Ramos, Chris Karr, Joseph Williams, Lisa Ochoa-Frongia, Urmimala Sarkar, Elad Yom-Tov, Courtney Lyles

Funding

  • NIDDK NIH HHS
  • AHRQ HHS

Cite

APA

Aguilera, A., Arévalo Avalos, M., Xu, J., Chakraborty, B., Figueroa, C., Garcia, F., Rosales, K., Hernandez-Ramos, R., Karr, C., Williams, J., Ochoa-Frongia, L., Sarkar, U., Yom-Tov, E., & Lyles, C. (2024). Effectiveness of a Digital Health Intervention Leveraging Reinforcement Learning: Results From the Diabetes and Mental Health Adaptive Notification Tracking and Evaluation (DIAMANTE) Randomized Clinical Trial. Journal of Medical Internet Research. https://doi.org/10.2196/60834

Vancouver

Aguilera A, Arévalo Avalos M, Xu J, Chakraborty B, Figueroa C, Garcia F, et al. Effectiveness of a Digital Health Intervention Leveraging Reinforcement Learning: Results From the Diabetes and Mental Health Adaptive Notification Tracking and Evaluation (DIAMANTE) Randomized Clinical Trial. Journal of Medical Internet Research. 2024. doi:10.2196/60834

BibTeX
@article{Aguilera2024,
  author = {Aguilera, Adrian and Arévalo Avalos, Marvyn and Xu, Jing and Chakraborty, Bibhas and Figueroa, Caroline and Garcia, Faviola and Rosales, Karina and Hernandez-Ramos, Rosa and Karr, Chris and Williams, Joseph and Ochoa-Frongia, Lisa and Sarkar, Urmimala and Yom-Tov, Elad and Lyles, Courtney},
  title = {Effectiveness of a Digital Health Intervention Leveraging Reinforcement Learning: Results From the Diabetes and Mental Health Adaptive Notification Tracking and Evaluation (DIAMANTE) Randomized Clinical Trial},
  journal = {Journal of Medical Internet Research},
  year = {2024},
  doi = {10.2196/60834}
}
Start for free →