Effectiveness of a Digital Health Intervention Leveraging Reinforcement Learning to Increase Physical Activity: Results from the DIAMANTE Randomized Clinical trial (Preprint)

Abstract

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

The 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.

Design, Setting, and Participants: From January 2020 to June 2022, participants were recruited from four San Francisco-based public primary care clinics and through online platforms to participate in the 6-month randomized clinical trial. Eligibility criteria included English- or Spanish-language preference and a documented diagnosis of diabetes and elevated depression symptoms. Intervention: The trial had three 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. Main Outcomes and Measures: 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 sub-analysis compared the primary step count outcome within recruitment samples.

In total, 168 participants were analyzed, including 24% Spanish language preference and 38% from clinic-based recruitment. Participants in the adaptive messaging arm showed a significant step count increase of 19% (P<0.001), in contrast to 1.6% and 3.9% step count increase in the random and control arms, respectively. Intervention effectiveness differences were observed between participants recruited from the San Francisco clinics and those via online platforms, with the significant step count trend persisting across both samples for participants in the adaptive group.

Our study supports the use of reinforcement learning algorithms for personalizing text messaging interventions to increase physical activity in a diverse sample of people with diabetes and depression. It is the first to test this approach in a large, diverse, and multilingual sample.

ClinicalTrials.gov Identifier: NCT03490253

RR2-10.1136/bmjopen-2019-034723