Supplemental Intervention for Alcohol Use Disorder Treatment Patients With a Co-Occurring Anxiety Disorder: Technical Development and Functional Testing of an Autonomous Digital Program
Bibliographic record
Abstract
Background: Anxiety disorders are common in alcohol use disorder (AUD) treatment patients. Such co-occurring conditions ("comorbidity") have negative prognostic implications for AUD treatment outcomes, yet they commonly go unaddressed in standard AUD care. Over a decade ago, we developed and validated a cognitive behavioral therapy intervention to supplement standard AUD care that, when delivered by trained therapists, improves outcomes in comorbid patients. However, this validated intervention, like many others in addiction care, has not been taken up in community-based AUD treatment programs. This phenomenon-empirically validated treatments that fail to be widely adopted in community care-has been termed the "research-to-practice gap." Researchers have suggested that the availability of fully autonomous digital equivalents of validated therapist-delivered therapies could reduce some barriers underlying the research-to-practice gap, especially by eliminating the need for costly and intensive therapist training and supervision. Objective: With this in mind, we obtained a Program Development Grant (R34) to conduct formative work in the development of a fully autonomous digital version of our previously validated therapist-delivered intervention for AUD treatment patients with a comorbid anxiety disorder. Methods: In the first phase of the project, we developed the digital intervention. This process included: (1) identifying appropriate collaborators and vendors; (2) consultation with an e-learning expert to develop a storyboard and accompanying graphics and narrative; (3) video production and editing; and (4) interactive programming. The second phase of the project was functional testing of the newly developed digital intervention conducted in 52 residential AUD treatment patients with a comorbid anxiety disorder. Patients underwent the 3 one-hour segments of the newly developed intervention and completed user surveys, knowledge quizzes, and behavioral competence tests. Results: While the development of the digital intervention was successful, the timeline was approximately double that projected (1 vs 2 years) due to false starts and inefficiencies that we describe, including lessons learned. Functional testing of the newly developed digital intervention showed that, on average, patients rated the user experience in the upper (favorable) 20% of the response scales. Knowledge quizzes and behavioral demonstrations showed that over 80% of participants gained functional mastery of the key skills and information taught in the program. Conclusions: Functional testing results in this study justify a randomized controlled trial of the digital intervention's efficacy, which is currently ongoing. In sharing the details of our challenges and solutions in developing the digital intervention, we hope to inform others developing digital tools. The extent to which the availability of empirically validated, fully autonomous digital interventions achieves their potential to reduce the research-to-practice gap remains an open but important empirical question. The present work stands as a necessary first step toward that end.
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 | 0.005 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.010 | 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".