Examining Mobile Health App Engagement In A North American Employee Population: A One-year Longitudinal Observational Study
Bibliographic record
Abstract
PURPOSE: Mobile health (mHealth) apps may help promote physical activity and other health behaviors among office-based workers however low app engagement is typical. The purpose of this study was to examine engagement with a rewards-based mHealth app and identify factors influencing engagement. METHODS: A one-year observational study was conducted with office-based workers in Canada and the U.S. using an employer sponsored rewards-based mHealth app between January 1 and December 31, 2020. The primary study outcome was weekly app opens. Kaplan-Meier survival curves were used to examine engagement patterns from a ‘multiple-lives’ perspective (i.e., time to first disengagement, re-engagement, second disengagement). Participants were considered ‘engaged’ after their first app open. Alternatively, participants were considered ‘disengaged’ when experiencing their first occurrence of four consecutive weeks without an app open. Accordingly, a ‘disengaged’ participant was considered ‘re-engaged’ after four consecutive weeks of app opens. Regression models were used to identify participant- (e.g., sociodemographic and health characteristics) and company-level factors (e.g., company size, reward type and size) influencing engagement. RESULTS: The study sample included 38 unique companies and 2,253 participants (39.3 ± 10.7 years; 35.7% female; 57% Canadian; BMI 26.7 ± 10.7 kg/m2). After one month of app use, 51.2% of participants disengaged. The majority of these (66.4%) disengaged in the first week. Risk of first disengagement was highest for 56-to-75 years-old participants (44%-106% higher) as well as for participants who were part of larger businesses and whose companies offered “off-platform” rewards (2.6% and 35.8% higher, respectively). On the contrary, rewards worth $10 per month lowered this risk (46% lower). Nine out of ten of participants who disengaged did not re-engage, and only a small proportion (11.5%) of our study sample was engaged at the end of the one-year study period. CONCLUSIONS: These findings may help digital health stakeholders address persistent low mHealth app engagement moving forward (e.g., by targeting higher risk users at higher risk timepoints with intervention features known to limit attrition).
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 | 0.002 | 0.003 |
| Meta-epidemiology (narrow) | 0.000 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.002 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".