Using smart predictions to connect people living with HIV to timely care
Official title: Harnessing Data Science to Improve HIV Care Continuum Outcomes: A Hybrid Type 2 Trial Evaluating a Machine-Learning Algorithm-Based Implementation Strategy
Funded at Hunter College · NIH-11289464 · Data updated 2026-11-12
This project uses a computer program to spot people living with HIV who are likely to need urgent care soon so care teams can reach them earlier.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Hunter College NIH-funded |
| Lab location | 1 site (New York, United States) |
| Project start | March 1, 2025 |
| Project end | January 31, 2030 |
| Funding year | 2026 |
| Award (this year) | $554,362 |
| NIH project number | 5R01MH136903-02 |
| Project ID | NIH-11289464 on NIH RePORTER |
Who could benefit from this research
✓Could help
Ideal candidates are people living with HIV who receive services through the participating health‑home or clinic partners and who may be at risk of short‑term emergency care use.
✕Less likely to help
People who do not receive care from the participating health‑home or clinics, who lack the electronic records used by the algorithm, or who are already stable and low‑risk may not get direct benefit from this project.
What this research studies
A validated machine‑learning algorithm developed with a local health‑home partner flags people living with HIV who are likely to visit the emergency department within the next two weeks. When someone is flagged, care managers will offer focused Comprehensive Care Management and Care Coordination services right away to address needs like medicines, appointments, or social supports. The project compares this targeted, just‑in‑time approach to usual care while tracking emergency visits, hospital stays, viral load, CD4 counts, and whether people stay engaged in care. The work is done in partnership with CCMP Health Home and participating clinics in New York using real patient records to guide and measure who gets extra support.
Why it matters
Potential benefit: If successful, the approach could reduce emergency visits and hospitalizations and help more people living with HIV stay in care and keep their virus suppressed.
How similar studies have gone: Comprehensive Care Management and Care Coordination have previously improved outcomes for people with HIV, while using machine‑learning to target such services is relatively new but supported by promising preliminary data.
Where this research is happening
-
Hunter College
New York, United States Active
Researchers
- Principal investigator: Golub, Sarit a — Hunter College
- Study coordinator: Golub, Sarit a
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.