MétaCan
Menu
Back to cohort
Record W4415201439 · doi:10.2196/81444

Real-World Symptom Trajectories in Adolescents With and Without Suicide Risk Receiving Care from Rula Health: Retrospective Study

2025· article· en· W4415201439 on OpenAlexvenueno aff
Lara Baez, Kelsey McAlister, Douglas Newton, Sam Seiniger, Jennifer Huberty

Bibliographic record

VenueJMIR Pediatrics and Parenting · 2025
Typearticle
Languageen
FieldPsychology
TopicSuicide and Self-Harm Studies
Canadian institutionsnot available
Fundersnot available
KeywordsDepression (economics)AnxietySuicide RiskRetrospective cohort studySuicide preventionMental healthOccupational safety and healthPoison control

Abstract

fetched live from OpenAlex

BACKGROUND: More than 5 million US adolescents experience mental or behavioral health conditions, yet two-thirds remain untreated, and suicide is the second leading cause of death. These gaps highlight the urgent need for accessible care. Digital mental health interventions that integrate measurement-based care (MBC) and personalized mental health care provider matching offer a promising solution, but few studies have examined their real-world impact among adolescents at elevated suicide risk. OBJECTIVE: This study aims to evaluate symptom improvements among adolescents with and without elevated suicide risk receiving care from Rula Health, an MBC-based digital mental health intervention with personalized intake through mental health care provider matching. We aimed to (1) compare baseline demographic and clinical characteristics between adolescents with and without elevated suicide risk at intake and (2) examine depression and anxiety symptom trajectories over the first 12 visits between adolescents with and without elevated suicide risk at intake. METHODS: We conducted a retrospective analysis of real-world clinical data from adolescents who received mental health services through Rula Health. Adolescents were classified as no suicide risk or elevated suicide risk based on the Columbia-Suicide Severity Rating Scale. Depression and anxiety symptoms were assessed using the Patient Health Questionnaire-9 (PHQ-9) and the Generalized Anxiety Disorder-7 (GAD-7) at baseline and before each session. Minimal clinically important differences were defined as a reduction of 5 more points for PHQ-9 and 4 or more points for GAD-7. Symptom changes were examined up to 12 visits. We used t tests and chi-square tests to compare baseline characteristics between suicide risk groups and linear mixed-effects models (adjusted for demographics and clinical factors) to assess symptom change and trajectory differences over time. RESULTS: The sample included 3533 adolescents in the no suicide risk group and 2712 in the elevated suicide risk group. The elevated suicide risk group had a greater proportion of female adolescents, younger adolescents (P<.001), non-Hispanic individuals (P=.002), and those with a primary depressive diagnosis, comorbid conditions, psychiatric involvement, and higher baseline PHQ-9 and GAD-7 scores (P<.001). The no suicide risk group attended more sessions and stayed in care longer (P<.001). Depression and anxiety scores decreased over visits (PHQ-9: B=-0.39; P<.001; GAD-7: B=-0.35; P<.001), with average improvements exceeding minimal clinically important difference thresholds. The elevated suicide risk group's depression and anxiety symptoms decreased at a higher rate than those of the no suicide risk group (PHQ-9: B=-0.32; P<.001; GAD-7: B=-0.18; P<.001). CONCLUSIONS: Adolescents with elevated suicide risk showed greater and faster improvement in depression and anxiety symptoms, reaching similar levels as those without elevated suicide risk by 12 visits. Rula Health's model can support high-risk youth in real-world settings. Future research should assess the impact of MBC and mental health care provider matching, including study designs that isolate their specific effects on outcomes.

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 imitation

Not 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.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.003
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.014
Threshold uncertainty score0.027

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.003
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0010.000
Scholarly communication0.0010.001
Open science0.0000.001
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0010.000

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.

Opus teacher head0.021
GPT teacher head0.336
Teacher spread0.314 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
Domainnot available
GenreEmpirical

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".

Quick stats

Citations1
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueJMIR Pediatrics and ParentingSame topicSuicide and Self-Harm StudiesFrench-language works237,207