iRISE: Machine learning to predict when people in recovery might disengage from online recovery communities
Official title: Identifying Recovery Insights through Signal Extraction (iRISE): Leveraging Machine Learning Strategies to Predict Disengagement from Recovery Communities
Funded at Trustees of Indiana University · NIH-11453245 · Data updated 2026-11-12
A new AI-based project aims to spot signs that someone in a recovery community could drift away, so help can be offered to keep them on track.
Quick facts
| Grant type | R03 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Trustees of Indiana University NIH-funded |
| Lab location | 1 site (Bloomington, United States) |
| Project start | September 1, 2026 |
| Project end | August 31, 2028 |
| Funding year | 2026 |
| Award (this year) | $308,412 |
| NIH project number | 1R03DA065173-01A1 |
| Project ID | NIH-11453245 on NIH RePORTER |
Who could benefit from this research
✓Could help
Adults 21 years and older who participate in recovery communities, including digital or online platforms.
✕Less likely to help
Individuals not engaging with recovery communities or those without access to digital recovery platforms may derive little direct benefit.
What this research studies
This project uses machine learning to analyze online recovery community data and identify signals that precede disengagement and relapse risk. By studying digital interactions and recovery-related factors, it aims to predict when someone may stop participating. The team will develop practical tools to flag these moments so support can be provided before disengagement happens. The work is rooted in real-world recovery communities, with a focus on improving long-term sobriety through timely digital interventions.
Why it matters
Potential benefit: If successful, the project could help keep people engaged in recovery communities and reduce relapse risk.
How similar studies have gone: Some prior studies show that digital cues can predict disengagement, but this approach seeks to apply those insights specifically to recovery communities using ML.
Where this research is happening
-
Trustees of Indiana University
Bloomington, United States Active
Researchers
- Principal investigator: Valdez, Danny — Trustees of Indiana University
- Study coordinator: Valdez, Danny
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.