Evaluating and Optimizing Just-in-Time Adaptive Interventions in a Digital Mental Health Intervention (Wysa for Chronic Pain) for Middle-Aged and Older Adults With Chronic Pain: Protocol for a Series of Randomized Trials
Bibliographic record
Abstract
BACKGROUND: On a population level, digital mental health interventions effectively reduce depression and anxiety symptoms. However, middle-aged and older adults with chronic pain and coexisting depression or anxiety have not been adequately represented in digital mental health studies. OBJECTIVE: The goal of this study is to refine an existing mobile, digital mental health intervention (Wysa for Chronic Pain) that addresses symptoms of depression, anxiety, and coexisting chronic pain for the unique challenges and technology use patterns of middle-aged and older adults. METHODS: Using a mixed methods, human-centered design approach and a series of randomized trials, we will test and iteratively refine just-in-time adaptive interventions (JITAIs) that are designed to increase engagement with a digital mental health intervention. Participants will be aged 45 years or older, endorse at least moderately severe depression or anxiety symptoms (Patient Health Questionnaire-9 or Generalized Anxiety Disorder-7 score ≥10), and have coexisting chronic pain (ie, pain on most days or every day in the past 3 months), and live in the United States. In this open, web-based trial, participants will all receive Wysa for Chronic Pain (by Wysa), which uses a behavioral activation framework and encourages users to work toward pain acceptance. The fully automated intervention also includes cognitive behavioral therapy, mindfulness, and sleep tools, among others. In each trial, participants will be randomized during a maximum 12-week study period to receive versus not receive novel JITAIs that are intended to reduce navigation burden and improve usability (and subsequent engagement and clinical effectiveness). The JITAIs are being designed with iterative user feedback, guided by the Discover, Design/Build, and Test framework and the Behavioral Intervention Technology model. The proximal outcome for each JITAI is related to engagement with Wysa for Chronic Pain after JITAI delivery (compared to when no JITAI is delivered). The primary distal clinical outcome is the Patient Health Questionnaire Anxiety and Depression Scale. Based on statistical analysis that is triangulated with qualitative feedback from a subsample of trial participants, the JITAIs will be iteratively refined and retested in subsequent microrandomized trials until retesting of refined adaptations no longer yields meaningful improvement in immediate engagement or a maximum of 5 total trials have been completed. RESULTS: Institutional review board approval was obtained on April 11, 2025. The first participant was enrolled on June 2, 2025, and recruitment is expected to conclude in 2026. CONCLUSIONS: Completion of this project will result in iteratively refined JITAIs that are designed to improve usability and engagement with a digital mental health intervention by middle-aged and older adults with depression or anxiety and coexisting chronic pain. TRIAL REGISTRATION: ClinicalTrials.gov NCT06978166; https://clinicaltrials.gov/study/NCT06978166. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/77532.
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 | 0.032 | 0.045 |
| Meta-epidemiology (narrow) | 0.007 | 0.003 |
| Meta-epidemiology (broad) | 0.011 | 0.012 |
| Bibliometrics | 0.004 | 0.003 |
| Science and technology studies | 0.004 | 0.003 |
| Scholarly communication | 0.005 | 0.005 |
| Open science | 0.004 | 0.004 |
| Research integrity | 0.007 | 0.008 |
| Insufficient payload (model declined to judge) | 0.064 | 0.011 |
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".