Understanding the Effect of Adding Automated and Human Coaching to a Mobile Health Physical Activity App for Afghanistan and Iraq Veterans: Protocol for a Randomized Controlled Trial of the Stay Strong Intervention
Bibliographic record
Abstract
BACKGROUND: Although maintaining a healthy weight and physical conditioning are requirements of active military duty, many US veterans rapidly gain weight and lose conditioning when they separate from active-duty service. Mobile health (mHealth) interventions that incorporate wearables for activity monitoring have become common, but it is unclear how to optimize engagement over time. Personalized health coaching, either through tailored automated messaging or by individual health coaches, has the potential to increase the efficacy of mHealth programs. In an attempt to preserve conditioning and ward off weight gain, we developed Stay Strong, a mobile app that is tailored to veterans of recent conflicts and tracks physical activity monitored by Fitbit Charge 2 devices and weight measured on a Bluetooth-enabled scale. OBJECTIVE: The goal of this study is to determine the effect of activity monitoring plus health coaching compared with activity monitoring alone. METHODS: In this randomized controlled trial, with Stay Strong, a mobile app designed specifically for veterans, we plan to enroll 350 veterans to engage in an mHealth lifestyle intervention that combines the use of a wearable physical activity tracker and a Bluetooth-enabled weight scale. The Stay Strong app displays physical activity and weight data trends over time. Enrolled participants are randomized to receive the Stay Strong app (active comparator arm) or Stay Strong + Coaching, an enhanced version of the program that adds coaching features (automated tailored messaging with weekly physical activity goals and up to 3 telephone calls with a health coach-intervention arm) for 1 year. Our primary outcome is change in physical activity at 12 months, with weight, pain, patient activation, and depression serving as secondary outcome measures. All processes related to recruitment, eligibility screening, informed consent, Health Insurance Portability and Accountability Act authorization, baseline assessment, randomization, the bulk of intervention delivery, and outcome assessment will be accomplished via the internet or smartphone app. RESULTS: The study recruitment began in September 2017, and data collection is expected to conclude in 2019. A total of 465 participants consented to participate and 357 (357/465, 77%) provided baseline levels of physical activity and were randomized to 1 of the 2 interventions. CONCLUSIONS: This novel randomized controlled trial will provide much-needed findings about whether the addition of telephone-based human coaching and other automated supportive-coaching features will improve physical activity compared with using a smartphone app linked to a wearable device alone. TRIAL REGISTRATION: ClinicalTrials.gov NCT02360293; https://clinicaltrials.gov/ct2/show/NCT02360293 (Archived by WebCite at http://www.webcitation.org/75KQeIFwh). INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/12526.
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 | 0.026 | 0.027 |
| Meta-epidemiology (narrow) | 0.006 | 0.003 |
| Meta-epidemiology (broad) | 0.010 | 0.007 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.004 | 0.004 |
| Scholarly communication | 0.004 | 0.004 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.008 | 0.010 |
| Insufficient payload (model declined to judge) | 0.061 | 0.010 |
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".