Predicting risky substance use in high school students with explainable AI
Interpretable Deep Forecasting of Hazardous Substance Use during High School
Using public datasets and brain scans, researchers will build an explainable AI to forecast which high-school teens are likely to engage in hazardous substance use so families and clinicians can target early support.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Stanford University NIH-funded |
| Lab location | 1 site (Stanford, United States) |
| Project ID | NIH-11172606 on NIH RePORTER |
What this research studies
If you are a teen or caregiver, this project analyzes large public datasets—including brain imaging, demographics, sleep, mental health, and behavior—to train an explainable AI that predicts risky substance use during high school. It maps fixed factors (like sex and family history) and changeable factors (like sleep, peer influences, and mood) to identify individual risk patterns. The team will link those risk patterns to brain circuit measures to learn possible neural mechanisms. The goal is to create tools that could help clinicians and families spot and support high-risk teens earlier.
Who could benefit from this research
Good fit: Best fits adolescents in or near high school (roughly ages 12–20) and families or clinicians concerned about hazardous substance use or family history of SUD.
Not a fit: Adults well past high school or people with an established, long-standing severe substance use disorder are unlikely to benefit directly from this high-school–focused prevention research.
Why it matters
Potential benefit: Could allow earlier, more personalized identification of high-risk teens so interventions can prevent or reduce progression to substance use disorder.
How similar studies have performed: Previous risk-scoring and machine-learning efforts have had limited accuracy and interpretability, and combining explainable deep forecasting with brain imaging is a relatively new and less-tested approach.
Where this research is happening
Stanford, United States
- Stanford University — Stanford, United States (Active)
Researchers
- Principal investigator: Pohl, Kilian Maria — Stanford University
- Study coordinator: Pohl, Kilian Maria
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.