AI screening that detects glaucoma across diverse populations

Developing Population-Generalizable Deep Learning Models for Automated Glaucoma Screening

NIH-funded research Schepens Eye Research Institute · NIH-11184318

This project builds AI that reads retinal photos and OCT scans to find glaucoma early for people from different racial and ethnic backgrounds.

Quick facts

Grant typeR01 grant
Study typeNIH-funded research
Funding institutionSchepens Eye Research Institute NIH-funded
Lab location1 site (Boston, United States)
Project IDNIH-11184318 on NIH RePORTER

What this research studies

You would have routine retinal photos and optical coherence tomography (OCT) scans analyzed by an AI program designed to work well across groups such as Asian, Black, and other populations. The team will train models using images labeled by clinical guidelines and compare their new methods to standard approaches like oversampling and transfer learning. They will also create new performance measures that penalize models that do well on some groups but poorly on others, aiming for consistent results across populations. The work is done at Schepens Eye Research Institute with partner datasets and clinics to include a broad range of patients.

Who could benefit from this research

Good fit: Ideal candidates would be adults who can have retinal photos or OCT scans taken during routine eye care or screening visits, especially individuals from underrepresented racial or ethnic groups.

Not a fit: People without access to retinal imaging, those whose disease cannot be detected by fundus/OCT imaging, or patients already diagnosed and stably treated for glaucoma may not get direct benefit from participation.

Why it matters

Potential benefit: If successful, this could enable low-cost, widely available glaucoma screening in primary care and pharmacies that catches disease earlier and reduces preventable vision loss.

How similar studies have performed: Previous AI work has shown promise detecting glaucoma from retinal images but often performs worse when moved to different populations, so this project focuses on improving that real-world consistency.

Where this research is happening

Boston, United States

Researchers

About this research

  1. This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
  2. Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
  3. For full project details, budget, and progress reports, visit the official NIH RePORTER page below.
Last reviewed 2026-06-13 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.