Addressing Youth Mental Health Through Schools and Primary Care Clinics Using the Connected for Wellness Mobile App: Protocol for a Stepped-Wedge Trial
Bibliographic record
Abstract
BACKGROUND: Youth in the United States are experiencing rising rates of anxiety, depression, and other mental health challenges, yet many remain underserved due to systemic barriers such as poverty, limited access to care, and shortages in the mental health workforce. Schools and primary care clinics are trusted, community-based settings that offer strategic opportunities for early identification, prevention, and intervention. As part of a public health approach, integrating digital mental health tools into these settings can support broad access, enhance mental health literacy, and promote help-seeking behaviors among all students. When co-designed with youth and embedded within existing care systems, these tools offer a scalable, proactive solution to support well-being across diverse school-aged populations. OBJECTIVE: This protocol describes the design and implementation of a stepped-wedge clinical trial to evaluate the Connected for Wellness mobile app, a youth- and caregiver-facing digital mental health intervention. Developed using participatory informatics and human-centered design principles, the app provides culturally relevant content in English and Spanish. Features include self-guided wellness activities, well-being screeners, psychoeducational videos, and localized service directories. Machine learning algorithms personalize content recommendations based on user inputs and behavioral patterns. METHODS: This trial uses a stepped-wedge cluster randomized design across 20 community-based sites (10 high schools and 10 primary care clinics) in 2 counties in California. These counties were selected for their high proportions of underserved youth populations. All youth aged 13 to 22 years and their caregivers will be invited to access the app. Sites are randomized into 2 implementation waves. The app is introduced site-wide as a universal public health intervention supported by on-site navigators and peer ambassadors. The primary outcomes are derived from a cascade-of-care framework, including identification of mental health need, referral to services, initiation of services, and engagement (defined as ≥3 treatment visits). Data will be collected via anonymous in-app analytics, monthly World Health Organization-Five Well-Being Index assessments, and deidentified electronic health and administrative records. Generalized linear mixed models will be used to evaluate differences in cascade outcomes between pre- and postimplementation phases while accounting for clustering and site-level variability. RESULTS: As of May 2025, the mobile app has been finalized, institutional review board approvals have been secured, and all study sites have been recruited. Participant recruitment is projected to begin in August 2025. Data collection and initial analyses will begin in early 2026, with preliminary findings expected by October 2026. CONCLUSIONS: This study tests a novel digital health intervention integrated into trusted care systems. If effective, the Connected for Wellness mobile app may serve as a scalable strategy to reduce disparities in mental health care access and engagement for youth across the United States. TRIAL REGISTRATION: ClinicalTrials.gov NCT06122688; https://clinicaltrials.gov/study/NCT06122688. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/73721.
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 | 0.037 | 0.039 |
| Meta-epidemiology (narrow) | 0.006 | 0.004 |
| Meta-epidemiology (broad) | 0.007 | 0.004 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.005 | 0.004 |
| Scholarly communication | 0.005 | 0.004 |
| Open science | 0.004 | 0.003 |
| Research integrity | 0.008 | 0.010 |
| Insufficient payload (model declined to judge) | 0.093 | 0.017 |
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".