Nudges and Prompts Increase Engagement in Self-Guided Digital Health Treatment for Depression and Anxiety: Results From a 3-Arm Randomized Controlled Trial
Bibliographic record
Abstract
BACKGROUND: Accessible and effective approaches to mental health treatment are important because of common barriers such as cost, stigma, and provider shortage. The effectiveness of self-guided treatment is well established, and its use has intensified because of the COVID-19 pandemic. Engagement remains important as dose-response relationships have been observed. Platforms such as Facebook (Meta Platform, Inc), LinkedIn (Microsoft Corp), and X Corp (formerly known as Twitter, Inc) use principles of behavioral economics to increase engagement. We hypothesized that similar concepts would increase engagement in self-guided digital health. OBJECTIVE: This 3-arm randomized controlled trial aimed to test whether members of 2 digital self-health courses for anxiety and depression would engage with behavioral nudges and prompts. Our primary hypothesis was that members would click on 2 features: tips and a to-do checklist. Our secondary hypothesis was that members would prefer to engage with directive tips in arm 2 versus social proof and present bias tips in arm 3. Our tertiary hypothesis was that rotating tips and a to-do checklist would increase completion rates. The results of this study will form a baseline for future artificial intelligence-directed research. METHODS: Overall, 13,224 new members registered between November 2021 and May 2022 for Evolution Health's self-guided treatment courses for anxiety and depression. The control arm featured a member home page without nudges or prompts. Arm 2 featured a home page with a tip-of-the-day section. Arm 3 featured a home page with a tip-of-the-day section and a to-do checklist. The research protocol for this study was published in JMIR Research Protocols on August 15, 2022. RESULTS: =92.2; P<.001) than the other 2 arms. Control arm members (1788/13,224, 13.52%) completed an average of 1.5 course components. Arm 2 members (865/13,224, 6.54%) clicked on 5% of tips and completed an average of 1.8 course components. Arm 3 members (1914/13,224, 14.47%) clicked on 5% of tips, completed 2.7 of 8 to-do checklist items, and completed an average of 2.11 course components. Completion rates in arm 2 were greater than those in arm 1 (z score=3.37; P<.001), and completion rates in arm 3 were greater than those in arm 1 (z score=12.23; P<.001). Engagement in all 8 components in arm 3 was higher than that in arm 2 (z score=1.31; P<.001). CONCLUSIONS: Members engaged with behavioral nudges and prompts. The results of this study may be important because efficacy is related to increased engagement. Due to its novel approach, the outcomes of this study should be interpreted with caution and used as a guideline for future research in this nascent field. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): RR2-10.2196/37231.
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 | 0.006 | 0.013 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.005 | 0.005 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.004 | 0.004 |
| Insufficient payload (model declined to judge) | 0.014 | 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".