AI tools to help people with HIV in Florida stay on treatment and reach undetectable viral loads
Artificial Intelligence and Counterfactually Actionable Responses to End HIV (AI-CARE-HIV)
This project will build AI using health records and clinical notes to find people with HIV in Florida who are at risk of falling out of care and suggest actions to help them stay on treatment.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of Florida NIH-funded |
| Lab location | 1 site (Gainesville, United States) |
| Project ID | NIH-11309192 on NIH RePORTER |
What this research studies
Researchers will combine electronic health records, insurance claims, and clinical notes from Florida patients to train AI models. They will use natural language processing to pull out behavioral and social details—like alcohol use or domestic violence—that are often missing from structured records. The models aim to identify who is likely to miss care or fail on antiretroviral therapy and to generate counterfactual, actionable suggestions about what could change those outcomes. The work focuses on high-need groups in Florida, including rural and underserved populations, to inform future outreach or interventions.
Who could benefit from this research
Good fit: People living with HIV in Florida—especially those with gaps in care, unstable adherence, signs of substance use, or who live in rural or underserved areas—would be the main candidates for the project's findings and potential outreach.
Not a fit: People outside Florida, those without accessible electronic health records in the project's data sources, or individuals whose care is already well-controlled may not directly benefit from this project.
Why it matters
Potential benefit: If successful, this work could help clinicians and outreach teams identify patients who need extra support and offer targeted actions that improve treatment adherence and viral suppression.
How similar studies have performed: Previous AI and NLP work has successfully identified risk patterns and adherence issues from EHR data, but building AI that proposes counterfactual, actionable responses to change outcomes is a newer and less-tested approach.
Where this research is happening
Gainesville, United States
- University of Florida — Gainesville, United States (Active)
Researchers
- Principal investigator: Prosperi, Mattia — University of Florida
- Study coordinator: Prosperi, Mattia
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.