Optimizing and Testing an Individualized and Adaptive Physical Activity Digital Health Intervention: Protocol for a Control Optimization Trial Embedded Within a Randomized Controlled Trial
Bibliographic record
Abstract
BACKGROUND: While effective physical activity (PA) interventions exist, interventions often work only for some individuals or only for a limited time. Thus, there is a need for digital health interventions that account for dynamic, idiosyncratic PA determinants to support each person's PA. We hypothesize that supporting individuals with their personal PA goals requires a personalized intervention that both supports each person in forming daily habits of walking more and develops personalized knowledge, skills, and practices regarding engaging in exercise routines. We operationalized these adaptive features via a digital health intervention called YourMove that uses a control systems approach to support personalized habit formation and a self-experimentation approach to develop personalized knowledge, skills, and practices. OBJECTIVE: The primary aim is to evaluate differences in minutes of moderate to vigorous PA (MVPA) per week at 12 months comparing our personalized intervention, called YourMove, with an active control that is similar but without personalization of the intervention components and mimics best-in-class digital health worksite wellness programs. METHODS: The YourMove study is a 12-month randomized controlled trial that involves 386 inactive adults aged 25 to 80 years. All participants receive (1) a Fitbit Versa smartwatch and corresponding smartphone app; (2) weekly PA goal suggestions and feedback, behavior change strategies, and reminders via SMS text messaging; and (3) up to US $50 in incentives for reaching daily step goals. Participants randomized to the active control group, modeled after worksite wellness programs, receive all the elements described in addition to a static daily step goal and static point rewards. Participants randomized to the intervention group receive (1) a habit formation element with daily personalized step goals and personalized point rewards generated through a control optimization trial approach and (2) a knowledge, skill, and practice development element featuring a self-guided self-experimentation tool that helps individuals find strategies to improve MVPA. The primary outcome is objectively assessed weekly minutes of MVPA via an ActiGraph monitor. RESULTS: Recruitment began in October 2022 and concluded in August 2024. Data collection will conclude in August 2025, with results expected by early 2026. CONCLUSIONS: We hypothesize that the intervention group will show greater improvement in MVPA than the active control group at 12 months. If the hypothesis is supported, this will provide compelling evidence to suggest that personalized and perpetually adaptive support can enhance PA more effectively than intervention elements commonly used in digital health worksite wellness programs. If the trial is successful, the results will provide justification to explore both the control optimization trial approach and self-experimentation approach for other complex, idiosyncratic, and dynamic behaviors such as weight management, smoking, or substance abuse. TRIAL REGISTRATION: ClinicalTrials.gov NCT05598996; https://clinicaltrials.gov/study/NCT05598996. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/70599.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.031 | 0.031 |
| Meta-epidemiology (narrow) | 0.007 | 0.003 |
| Meta-epidemiology (broad) | 0.010 | 0.004 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.004 | 0.004 |
| Scholarly communication | 0.004 | 0.003 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.007 | 0.007 |
| Insufficient payload (model declined to judge) | 0.068 | 0.011 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".