Optimizing Engagement in an Online Dietary Intervention for Depression (My Food & Mood Version 3.0): Cohort Study
Bibliographic record
Abstract
BACKGROUND: Online interventions can be a cost-effective and efficient way to deliver programs to large numbers of people regardless of geographic location. However, attrition in web-based interventions is often an issue. Developing ways to keep participants engaged is important for ensuring validity and limiting potential biases. We developed a web-based dietary intervention as part of The My Food & Mood study which aimed to optimize ways to engage participants with low mood or depressive symptoms to promote dietary behavior change. Different versions of the My Food & Mood program were tested during optimization. Iterations were developed based on user feedback and usage analysis. OBJECTIVE: The purpose of this study was to compare engagement and nonusage attrition across 4 program iterations-which differed by platform format, delivery mode, and activity type-to create an optimized version. METHODS: Each program version contained modular videos with key activities with respect to implementing behavior change techniques of equivalent levels of required participation and length: version 1.0, desktop program and smartphone app; version 2.1, desktop or smartphone program; version 2.2, desktop program; and version 3.0, smartphone app. Adults with PHQ-8 scores of 5 or greater were recruited online and assigned to 1 of the 4 versions. Participants were asked to use the program for 8 weeks and complete measures at weeks 4 and 8. Engagement data were collected from the web-based platform system logs and customized reports. Cox regression survival analysis examined nonusage attrition and Kruskal-Wallis tests compared engagement across each cohort. RESULTS: A total of 614 adults participated. Kruskal-Wallis tests showed significant differences across the 4 cohorts in all engagement measures. The smartphone app (version 3.0) had the greatest engagement as measured by weeks engaged, total usage time, total time key activities, number of active sessions, percentage of activities completed against protocol, goals completed, and percentage of videos watched. Cox regression multivariate survival analysis showed referral from a health practitioner (hazard ratio [HR] 0.344, P=.001) and greater proficiency with computers (HR 0.796, P=.049) reduced the risk of nonusage attrition. Computer confidence was associated with an increased risk of nonusage attrition. CONCLUSIONS: My Food & Mood version 3.0, a dietary intervention delivered via smartphone app with self-monitoring tools for diet quality and mood monitoring, was the version with greatest engagement in a population with low mood or depression. The iterative design techniques employed and analysis of feedback from participants resulted in a program that achieved lower rates of nonusage attrition and higher rates of intensity of use.
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 | 0.005 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 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) | 0.002 | 0.001 |
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".