Making glaucoma AI work well for patients from different clinics
Improving Generalizability in Artificial Intelligence Algorithms for Glaucoma
This project aims to improve AI that predicts which people with glaucoma will get worse by using medical records from many eye centers.
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-11251983 on NIH RePORTER |
What this research studies
You would have your eye clinic records and test results (like visual fields and imaging) used—in de-identified form—by researchers to train and test AI models. The team will use the SOURCE registry, which brings together records from 23 U.S. eye centers, to see whether algorithms trained in one place work well for patients from other places. They will change how models are trained and combine data so predictions are more reliable across different patient groups and types of glaucoma. The work is meant to produce AI tools that give trustworthy risk information no matter where you get care.
Who could benefit from this research
Good fit: Ideal candidates are people diagnosed with glaucoma who receive care at one of the participating eye centers and whose medical records (including eye tests and visits) are in the SOURCE registry.
Not a fit: Patients without records at participating centers, those with very rare glaucoma types not represented in the data, or people receiving care outside the contributing clinics may not directly benefit.
Why it matters
Potential benefit: If successful, clinicians could spot people at higher risk of vision loss earlier and tailor treatments to help prevent blindness.
How similar studies have performed: Previous AI tools have shown promise detecting or predicting glaucoma in single-center datasets, but reliable multi-center generalizability has not yet been established.
Where this research is happening
Stanford, United States
- Stanford University — Stanford, United States (Active)
Researchers
- Principal investigator: Wang, Sophia Ying — Stanford University
- Study coordinator: Wang, Sophia Ying
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.