Assessing the Efficacy of the INTELLECT Cognitive Behavioral Therapy Mobile App for Anxiety and Depressive Symptoms Among At-Risk Japanese Employees: Randomized Controlled Trial
Bibliographic record
Abstract
Background: In Japan, the prevalence of anxiety and depressive symptoms within the working population has risen. This has been accentuated by the economic repercussions of the COVID-19 pandemic and the social isolation resulting from remote work setups. Mobile health apps, particularly those incorporating cognitive behavioral therapy (CBT) features, have shown potential in addressing these symptoms. These self-guided CBT interventions hold promise in alleviating the heightened depressive and anxiety symptoms often observed among Japanese employees. Objective: Using a randomized controlled trial, we compared the efficacy of the "INTELLECT" app against a no-treatment control group in improving depressive symptoms and CBT skills among Japanese full-time employees at postintervention and 2-month follow-up. Methods: A total of 123 full-time Japanese employees were randomly allocated to either the intervention group (INTELLECT), where they engaged with self-help CBT features, or to a control group receiving no treatment. Intervention participants were required to engage with these features for at least 20 minutes per week over a span of 4 weeks. Weekly self-reported assessments were collected from all participants starting from baseline and continuing until the end of the 4-week intervention period. Subsequent assessments were conducted at 1-month and 2-month follow-up intervals. Linear mixed models were used to evaluate any effects of the self-guided intervention on depressive symptoms, as measured by the Patient Health Questionnaire-4, and cognitive behavioral skills, as measured by the Cognitive Behavioral Therapy Skills Scale. The app's feasibility, usability, and acceptability ratings were also examined using the Implementation Outcome Scales for Digital Mental Health (iOSDMH). Results: The final sample (n=73) consisted of 46 (63%) participants who were female, 23 (32%) participants who were male, and 4 (6%) participants who identified as other genders, with a mean age of 40.4 (SD 10.7) years. Significant time × group interactions were found at postintervention and 2-month follow-up, with the intervention group (n=34) reporting significantly lower depressive symptoms than the control group (n=38) at postintervention (t364.7426=-2.243; P=.03; Cohen d=-0.57, 95% CI -1.07 to -0.06) and 2-month follow-up (t364.6948=-3.284; P<.001; Cohen d=-0.85, 95% CI -1.38 to -0.32). In addition, intervention participants reported significantly greater improvements in self-monitoring cognitive skills than control participants at postintervention (t120.7526=2.672; P=.01; Cohen d=0.68, 95% CI 0.17 to 1.18) but not follow-up (t121.5475=1.947; P=.05; Cohen d=0.50, 95% CI -0.01 to 1.02). Conclusions: This study provides evidence that CBT features on the INTELLECT app are effective in improving depressive symptoms and self-monitoring cognitive skills.
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 | 0.002 | 0.003 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.005 | 0.004 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.003 | 0.003 |
| Insufficient payload (model declined to judge) | 0.008 | 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".