AI tool that reads eye photos to find trachoma
The Development of Clinically-Motivated and Explainable Machine-Learning-Based Image Classifiers to Detect Trachoma
An easy-to-use AI that looks at photos of eyes to spot signs of trachoma, meant to help health workers and children in affected communities.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of Vermont & St Agric College NIH-funded |
| Lab location | 1 site (Burlington, United States) |
| Project ID | NIH-11259523 on NIH RePORTER |
What this research studies
If you or your child live in a place where trachoma happens, health teams would take standardized photos of the eye and the new software would learn to spot the key signs of active trachoma. The processing will include explainable outputs so graders and clinicians can see why an image was flagged. The team will improve photography methods, expand training data, and refine the machine-learning model based on previously published work. This aims to support community surveys and screening where trained graders are scarce.
Who could benefit from this research
Good fit: Ideal candidates are children and community members in trachoma-endemic areas who can have noninvasive eye photographs taken during screening or surveys.
Not a fit: People who cannot access clinics or survey teams that take standardized eye photos, or whose eye problems clearly come from other diseases, may not benefit from this tool.
Why it matters
Potential benefit: Could make screening more consistent and accurate so cases are found and treated sooner, helping prevent vision loss from trachoma.
How similar studies have performed: Prior work, including the investigators' published machine-learning model for trachoma photos, has shown promise, but fully explainable, field-ready tools are still under development.
Where this research is happening
Burlington, United States
- University of Vermont & St Agric College — Burlington, United States (Active)
Researchers
- Principal investigator: Brady, Christopher John — University of Vermont & St Agric College
- Study coordinator: Brady, Christopher John
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.