A Personalized Exercise Assistant using Reinforcement Learning (PEARL): Results from a Large-Scale Mobile Health Randomized-Controlled Trial

Background: Consistent physical inactivity among adults and adolescents poses a major global health challenge. Mobile health (mHealth) interventions, particularly Just-in-Time Adaptive Interventions (JITAIs), offer a promising avenue for scalable and personalized physical activity promotion. However, developing and evaluating such adaptive interventions at scale, while integrating robust behavioral science, presents methodological hurdles. Objective: The PEARL study aimed to assess the feasibility and effectiveness of a reinforcement learning (RL) algorithm, informed by health behavior change theory (COM-B), to personalize the content and timing of physical activity nudges via the Fitbit app compared to fixed and random nudging strategies, and to a control group with no nudges. Methods: We conducted a large-scale, four-arm randomized controlled trial (RCT) enrolling 13,463 Fitbit users. Participants were randomized to: (1) Control (no nudges); (2) Random (random content/timing); (3) Fixed (logic based on baseline COM-B survey); and (4) RL (adaptive algorithm). The primary outcome was the change in average daily step count from baseline to 2 months. Secondary outcomes included user engagement and survey responses regarding capability, opportunity, and motivation. Results: 7,711 participants were included in the primary analysis (mean age 42.1 years; 86.3% female). At 1 month, the RL group showed a significant increase in daily steps compared to Control (+296 steps, P<.001), Random (+218 steps, P=.005), and Fixed (+238 steps, P=.002) groups. At 2 months, the RL group sustained a significant increase against the Control (+210 steps, P=.01). Generalized estimating equation (GEE) models confirmed a sustained significant increase in the RL group (+208 steps, P=.002). In exit surveys, the RL group reported higher favorable responses regarding nudge customization (37%) compared to other groups. Conclusions: This study demonstrates the feasibility and early efficacy of using RL to personalize digital health nudges at scale. While long-term retention remains a challenge, the adaptive approach outperformed static behavioral rules, showcasing the promise of dynamic personalization in a real-world mHealth setting. Clinical Trial: doi: 10.17605/OSF.IO/TW7UP