Feasibility and Acceptability of a Mobile App–Based TEAM-CBT (Testing Empathy Assessment Methods–Cognitive Behavioral Therapy) Intervention (Feeling Good) for Depression: Secondary Data Analysis
Bibliographic record
Abstract
BACKGROUND: The Feeling Good App is an automated stand-alone digital mobile mental health tool currently undergoing beta testing with the goal of providing evidence-informed self-help lessons and exercises to help individuals reduce depressive symptoms without guidance from a mental health provider. Users work through intensive basic training (IBT) and ongoing training models that provide education regarding cognitive behavioral therapy principles from a smartphone. OBJECTIVE: The key objective of this study was to perform a nonsponsored third-party academic assessment of an industry-generated data set; this data set focused on the safety, feasibility, and accessibility of a commercial automated digital mobile mental health app that was developed to reduce feelings associated with depression. METHODS: The Feeling Good App development team created a waitlist cohort crossover design and measured symptoms of depression and anxiety using the Patient Health Questionnaire-9, Generalized Anxiety Disorder-7, and an app-specific measure of negative feelings called the 7 Dimension Emotion Slider (7-DES). The waitlist cohort crossover design divided the participants into 2 groups, where 48.6% (141/290) of the participants were given immediate access to the apps, while 51.4% (149/290) were placed on a 2-week waitlist before being given access to the app. Data collected by the Feeling Good App development team were deidentified and provided to the authors of this paper for analysis through a nonsponsored university data use agreement. All quantitative data were analyzed using SPSS Statistics (version 28.0; IBM Corp). Descriptive statistics were calculated for demographic variables. Feasibility and acceptability were descriptively assessed. All participants included in the quantitative data were given access to the Feeling Good App; this study did not include a control group. RESULTS: =30.16; P<.01). In terms of acceptability, 72.2% (166/230) of the users who started the initial 2-day IBT went on to complete it, while 34.8% (80/230) of the users who started IBT completed the entirety of the apps' 4-week protocol (150/230, 65.22% dropout rate over 4 weeks). CONCLUSIONS: This study is the first reported proof-of-concept evaluation of the Feeling Good App in terms of safety, feasibility, and statistical trends within the data set. It demonstrates a feasible and novel approach to industry and academic collaboration in the process of developing a digital mental health technology translated from an existing evidence-informed treatment. The results support the prototype app as safe for a select nonclinical population. The app had acceptable levels of engagement and dropouts throughout the intervention. Those who stay engaged showed reductions in symptom severity of depression warranting further investigation of the app's efficacy.
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 | 0.015 | 0.029 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| 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 | 0.001 | 0.002 |
| 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".