Assessing the Efficacy and Safety of a Digital Therapeutic for Symptoms of Depression in Adolescents: Protocol for a Randomized Controlled Trial
Bibliographic record
Abstract
BACKGROUND: Depression is a serious, prevalent, recurrent, and undertreated disorder in adolescents. Low levels of treatment seeking and treatment adherence in this age group, combined with a growing national crisis in access to mental health care, have increased efforts to identify effective treatment alternatives for this demographic. Digital health interventions for mental illness can provide cost-effective, engaging, and accessible means of delivering psychotherapy to adolescents. OBJECTIVE: This protocol describes a virtual randomized controlled trial designed to evaluate the efficacy and safety of a self-guided, mobile app-based implementation of behavioral activation therapy, SparkRx, for the adjunct treatment of symptoms of depression in adolescents. METHODS: Participants are recruited directly through web-based and print advertisements. Following eligibility screening and consenting, participants are randomly assigned to a treatment arm (SparkRx) or a control arm (assessment-enhanced usual care) for 5 weeks. The primary efficacy outcome, total score on the 8-item Patient Health Questionnaire (PHQ-8), is assessed at the end of the 5-week intervention period. Additional participant-reported outcomes are assessed at baseline, the postintervention time point, and 1-month follow-up. The safety of the intervention is assessed by participant report (and legal guardian report, if the participant is younger than 18 years) and by patterns of symptom deterioration on the PHQ-8, as part of a larger clinical safety monitoring protocol. The primary efficacy outcome, total PHQ-8 score at the postintervention time point, will be compared between SparkRx and enhanced usual care arms using mixed effect modeling, with baseline PHQ-8 and current antidepressant medication status included as covariates. Secondary efficacy outcomes, including the proportion of participants exhibiting treatment response, remission, and minimal clinically significant improvement (all derived from total PHQ-8 scores), will be compared between groups using chi-square tests. Symptom severity at 1-month follow-up will also be compared between arms. Planned subgroup analyses will examine the robustness of treatment effects to differences in baseline symptom severity (PHQ-8 score <15 or ≥ 15) and age (younger than 18 years and older than 18 years). The primary safety outcome, the number of psychiatric serious adverse events, will be compared between trial arms using the Fisher exact test. All other adverse events will be presented descriptively. RESULTS: As of May 2023, enrollment into the study has concluded; 223 participants were randomized. The analysis of the efficacy and safety data is expected to be completed by Fall 2023. CONCLUSIONS: We hypothesize that the results of this trial will support the efficacy and safety of SparkRx in attenuating symptoms of depression in adolescents. Positive results would more broadly support the prospect of using accessible, scientifically validated, digital therapeutics in the adjunct treatment of mental health disorders in this age range. TRIAL REGISTRATION: ClinicalTrials.gov NCT05462652; https://clinicaltrials.gov/study/NCT05462652. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/48740.
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 | 0.054 | 0.048 |
| Meta-epidemiology (narrow) | 0.008 | 0.004 |
| Meta-epidemiology (broad) | 0.013 | 0.008 |
| Bibliometrics | 0.004 | 0.005 |
| Science and technology studies | 0.005 | 0.005 |
| Scholarly communication | 0.007 | 0.005 |
| Open science | 0.005 | 0.003 |
| Research integrity | 0.010 | 0.012 |
| Insufficient payload (model declined to judge) | 0.094 | 0.016 |
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".