Improvement and Maintenance of Clinical Outcomes in a Digital Mental Health Platform: Findings From a Longitudinal Observational Real-World Study
Bibliographic record
Abstract
BACKGROUND: Digital mental health services are increasingly being provided by employers as health benefit programs that can improve access to and remove barriers to mental health care. Stratified care models, in particular, offer personalized care recommendations that can offer clinically effective interventions while conserving resources. Nonetheless, clinical evaluation is needed to understand their benefits for mental health and their use in a real-world setting. OBJECTIVE: This study aimed to examine the changes in clinical outcomes (ie, depressive and anxiety symptoms and well-being) and to evaluate the use of stratified blended care among members of an employer-sponsored digital mental health benefit. METHODS: In a large prospective observational study, we examined the changes in depressive symptoms (9-item Patient Health Questionnaire), anxiety symptoms (7-item Generalized Anxiety Disorder scale), and well-being (5-item World Health Organization Well-Being Index) for 3 months in 509 participants (mean age 33.9, SD 8.7 years; women: n=312, 61.3%; men: n=175, 34.4%; nonbinary: n=22, 4.3%) who were newly enrolled and engaged in care with an employer-sponsored digital mental health platform (Modern Health Inc). We also investigated the extent to which participants followed the recommendations provided to them through a stratified blended care model. RESULTS: Participants with elevated baseline symptoms of depression and anxiety exhibited significant symptom improvements, with a 37% score improvement in depression and a 29% score improvement in anxiety (P values <.001). Participants with baseline scores indicative of poorer well-being also improved over the study period (90% score improvement; P=.002). Furthermore, over half exhibited clinical improvement or recovery for depressive symptoms (n=122, 65.2%), anxiety symptoms (n=127, 59.1%), and low well-being (n=82, 64.6%). Among participants with mild or no baseline symptoms, we found high rates of maintenance for low depressive (n=297, 92.2%) and anxiety (n=255, 86.7%) symptoms and high well-being (n=344, 90.1%). In total, two-thirds of the participants (n=343, 67.4%) used their recommended care, 16.9% (n=86) intensified their care beyond their initial recommendation, and 15.7% (n=80) of participants underused care by not engaging with the highest level of care recommended to them. CONCLUSIONS: Participants with elevated baseline depressive or anxiety symptoms improved their mental health significantly from baseline to follow-up, and most participants without symptoms or with mild symptoms at baseline maintained their mental health over time. In addition, engagement patterns indicate that the stratified blended care model was efficient in matching individuals with the most effective and least costly care while also allowing them to self-determine their care and use combinations of services that best fit their needs. Overall, the results of this study support the clinical effectiveness of the platform for improving and preserving mental health and support the utility and effectiveness of stratified blended care models to improve access to and use of digitally delivered mental health services.
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 | 0.005 | 0.010 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| 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 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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.
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".