Integrating Technology Into Mental Health Intervention Trials
Bibliographic record
Abstract
Background/Aims: Innovative web-based methods of delivering wide-scale mental health interventions in an efficient and sustainable manner have the potential to overcome barriers to care and increase access. Herein we describe lessons learned using an integrated informatics architecture developed to support implementation of two large randomized mental health pragmatic trials that are currently underway at three HCSRN sites. The Strategies for Overcoming Residual Depressive Symptoms (SOAR) study is evaluating the effectiveness of an online mindfulness-based cognitive therapy (MBCT) program in 460 patients. The Suicide Prevention Outreach Trial (SPOT) is evaluating the effectiveness of two separate interventions –– an online dialectical behavior therapy skills training program or risk assessment/care management using the Columbia Suicide Severity Rating Scale with secured messaging through Epic –– in preventing suicide attempt/death in 16,000 patients. Each study integrates software tools for targeted patient outreach, retention and monitoring of suicide risk. Methods: Both studies leverage real-time patient-reported outcomes data from Epic questionnaires for cohort identification and recruitment. Patients are then invited via email to visit websites to learn about the study and provide informed consent. REDCap, DatStat or Epic questionnaires are used to collect follow-up data from participants with real-time, item-level email alerts to notify study staff of suicide risk. An email service delivers study incentives to patients on survey completion. A dashboard was developed in Epic to facilitate population management for a large volume of high-risk patients. Results: The integrated informatics architecture allows the study team to enroll patients efficiently and to maintain high patient retention with survey completion rates of 70% in the MBCT study at 6 months. We tested several approaches for suicide risk monitoring using web-based surveys to encourage patients’ acceptance of subsequent outreach. Each HCSRN site adapted an Epic dashboard function that alerts care managers to high-risk patients and tracks appointment compliance. Conclusion: Creative problem solving and effective partnerships among study staff, software and data programmers, care delivery teams, external collaborators and institutional review boards are essential for effective implementation of large pragmatic trials using multiple technologies. The integrated informatics architecture created here is essential to realize scalability, increase efficiency and support effectiveness of the interventions.
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 | 0.476 | 0.668 |
| Meta-epidemiology (narrow) | 0.003 | 0.004 |
| Meta-epidemiology (broad) | 0.004 | 0.006 |
| Bibliometrics | 0.009 | 0.007 |
| Science and technology studies | 0.001 | 0.005 |
| Scholarly communication | 0.012 | 0.011 |
| Open science | 0.004 | 0.014 |
| Research integrity | 0.006 | 0.006 |
| Insufficient payload (model declined to judge) | 0.013 | 0.003 |
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".