Using machine learning to understand alcohol use in LGBTQ+ people with overlapping identities
Machine learning methods for identifying person-level mechanisms of alcohol use among sexual and gender minority intersections
This project uses advanced computer-learning on large U.S. health datasets to find personal and policy factors linked to alcohol use among sexual and gender minority adolescents and adults, especially people with overlapping identities.
Quick facts
| Grant type | NIH-funded research |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of Washington NIH-funded |
| Lab location | 1 site (Seattle, United States) |
| Project ID | NIH-11374918 on NIH RePORTER |
What this research studies
This work applies machine-learning and multilevel methods to large U.S. datasets (for example, the All of Us Research Program) to identify personal, social, and policy-related drivers of alcohol use among sexual and gender minority (SGM) people. It focuses on intersecting identities — such as bisexual people, transgender people, and young women of color — and examines how state policies and events like the COVID-19 pandemic may change risk. The team analyzes existing survey and cohort data rather than running new clinical tests, and the grant also supports the investigator's mentored training to build an independent research program.
Who could benefit from this research
Good fit: People who are sexual and/or gender minorities — including bisexual and transgender individuals, especially adolescents, young adults, and women of color — are the main groups this work focuses on.
Not a fit: People who are not sexual or gender minorities or whose alcohol use is unrelated to the social and policy factors studied may not see direct benefit from this project.
Why it matters
Potential benefit: If successful, the findings could help target prevention and support to SGM subgroups most at risk and inform policies that reduce alcohol-related harms.
How similar studies have performed: Researchers have used large datasets and machine-learning to find health risk patterns before, but applying these tools specifically to intersecting SGM groups and policy moderators is relatively new.
Where this research is happening
Seattle, United States
- University of Washington — Seattle, United States (Active)
Researchers
- Principal investigator: Mccabe, Connor J — University of Washington
- Study coordinator: Mccabe, Connor J
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.