Maximizing Engagement, Trust, and Clinical Benefit of AI-Generated Recovery Support Messages for Alcohol Use Disorder: Protocol for an Optimization Study
Bibliographic record
Abstract
BACKGROUND: Successful recovery from alcohol use disorder requires long-term lapse risk monitoring. Self-monitoring is difficult, given the dynamic, complex interplay of the many risk factors over time. An automated recovery monitoring support system embedded with a machine learning lapse prediction model could improve sustained, adaptive, and personalized self-monitoring by delivering daily support messages. OBJECTIVE: We propose to optimize the components included in daily support messages to increase engagement with a recovery monitoring support system. METHODS: The participants will include 304 US adults with moderate to severe alcohol use disorder. Participants will complete daily surveys and provide geolocation data for 17 weeks. Participants will receive daily support messages, starting in week 2, that convey a combination of individualized information from a lapse prediction model. Manipulated message components include (1) lapse probability and lapse probability change, (2) an important model feature, (3) a risk-relevant recommendation, and (4) message personalization on tone preference. RESULTS: The National Institute on Alcohol Abuse and Alcoholism funded this project (R01AA031762) on August 9, 2024, with a funding period from August 20, 2024, to July 31, 2029. The institutional research board of the University of Wisconsin-Madison Health Sciences approved this project (IRB #2024-0869). Enrollment will begin in December 2025. CONCLUSIONS: Message components that either increase engagement or improve clinical outcomes will be recommended for use in future recovery monitoring support systems and digital therapeutics. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/81697.
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 | 0.026 | 0.041 |
| Meta-epidemiology (narrow) | 0.003 | 0.002 |
| Meta-epidemiology (broad) | 0.004 | 0.005 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.003 | 0.002 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.003 | 0.007 |
| Insufficient payload (model declined to judge) | 0.050 | 0.007 |
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".