Which alcohol use disorder treatment will work best for you
Predicting individual responses to treatment for alcohol use disorder.
This project uses data from past clinical trials and machine learning to predict how well different treatments for alcohol use disorder might work for individual patients.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of New Mexico NIH-funded |
| Lab location | 1 site (Albuquerque, United States) |
| Project ID | NIH-11414952 on NIH RePORTER |
What this research studies
If you have alcohol use disorder, this project combines data from 11 past randomized trials—six behavioral relapse-prevention programs and five medication trials—to learn which types of people did better with which treatments. The team trains and cross-validates machine-learning algorithms to make individualized predictions of treatment response and to estimate uncertainty around those predictions. They will test methods for pooling data across trials and improving prediction precision so results can be useful in clinical care. At the end they will publish algorithms that compare expected outcomes for different treatment options for new individuals.
Who could benefit from this research
Good fit: Adults with alcohol use disorder—especially those with recent heavy drinking or considering behavioral or medication treatment—would be the primary group who could benefit from these findings.
Not a fit: People without alcohol use disorder, those needing urgent medical detox or inpatient care, or individuals with conditions not represented in the original trials may not benefit from these predictions.
Why it matters
Potential benefit: If successful, this work could help match people with alcohol use disorder to treatments they are most likely to benefit from, reducing trial-and-error and potentially lowering relapse.
How similar studies have performed: Early studies applying machine learning to clinical trial data for AUD and other psychiatric conditions have shown promise but have not yet produced widely used clinical decision tools.
Where this research is happening
Albuquerque, United States
- University of New Mexico — Albuquerque, United States (Active)
Researchers
- Principal investigator: Van Horn, M Lee — University of New Mexico
- Study coordinator: Van Horn, M Lee
About this research
- This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
- Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
- For full project details, budget, and progress reports, visit the official NIH RePORTER page below.