Integration of a Mental Health App (e-MICHI) Into a Blended Treatment of Depression in Adolescents: Single-Group, Naturalistic Feasibility Trial
Bibliographic record
Abstract
Background: Major depressive disorder is a common diagnosis among adolescents. Cognitive behavioral therapy is recommended as the first line of treatment. Digital health interventions, such as apps, could contribute to treatment. Advantages could be easy accessibility and availability, reduced time for face-to-face therapy, and the ability to intensify therapy by incorporating it into the patients' everyday lives. Challenges such as low adherence rates are common in digital health interventions. Therefore, they need to undergo rigorous testing for feasibility and effectiveness. Objective: An evaluated, cognitive behavioral therapy-based face-to-face therapy program for depression in adolescents was transformed into an app called e-MICHI. This study examined its feasibility and efficacy for use in blended therapy in outpatient settings. Methods: Adolescents aged 12 to 18 years with major depressive disorder receiving outpatient care were recruited from 2 university hospitals (n=36 included in analysis). The e-MICHI intervention combined daily app engagement over 6 weeks with 3 face-to-face sessions with a therapist. Feasibility was measured using various variables, including an adherence score (0=no or little patient engagement to 3=excellent engagement) and engagement rates (number of modules completed, number of messages sent by participants via the in-app messenger), satisfaction ratings from both participants and therapists, as well as participants' ratings of the usefulness of the antidepressant strategies covered in the app and the transfer of these strategies to everyday practice. Trends of efficacy were evaluated from multiple perspectives (participant self-rating, independent rater, or therapist), using the Beck Depression Inventory-II, the Children's Depression Rating Scale-Revised, and the Clinical Global Impressions-Severity Scale. Feasibility metrics were assessed by analyzing their central tendency and dispersion, efficacy data were analyzed using a repeated measures ANOVA. Results: e-MICHI was positively evaluated by both participants and therapists (participants: mean 7.3, SD 1.2 and therapists: mean 7.3, SD 1.1, on a scale from 0=bad to 10=excellent). Participants demonstrated high adherence rates (nearly 80%, n=25, received a "good" or "excellent" adherence score) and showed overall good engagement (app modules completed [maximum 6]: mean 5.03, SD 1.27 and messages sent via messenger: mean 23, SD 22.1). Participants rated the psychoeducational content of the app as particularly useful and reported consistent practice of the e-MICHI strategies in everyday life. Use of the app was associated with a significant reduction of depressive symptoms (before app use vs 3-month follow-up, Beck Depression Inventory-II: mean -6.76, SD 11.49, P=.01; Children's Depression Rating Scale-Revised: mean -16.45, SD 16.76, P<.001; Clinical Global Impressions-Severity Scale: mean -1.1, SD 1.24, P<.001). Conclusions: While acknowledging its limitations, such as the small number of participants and the limited validity concerning efficacy, this study confirms the feasibility of e-MICHI for treating adolescent depression in outpatient settings.
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 | 0.004 | 0.006 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.003 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.003 | 0.003 |
| Insufficient payload (model declined to judge) | 0.005 | 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".