Improving glaucoma risk prediction with genetics and AI

Enhancing Glaucoma Risk Prediction through Advanced Genomics and Machine Learning

['FUNDING_R01'] · MASSACHUSETTS EYE AND EAR INFIRMARY · NIH-11160777

This project combines genetic information and artificial intelligence to create more accurate glaucoma risk scores for people at risk of or living with glaucoma.

Quick facts

Phase['FUNDING_R01']
Study typeNih_funding
SexAll
SponsorMASSACHUSETTS EYE AND EAR INFIRMARY (nih funded)
Locations1 site (BOSTON, UNITED STATES)
Trial IDNIH-11160777 on ClinicalTrials.gov

What this research studies

You may hear that researchers are using the text in medical records, genetic data, and eye images to build better tools that predict who will develop or worsen from glaucoma. They will use AI to read doctors' notes and refine how glaucoma is identified from records, run large genetic analyses across more than a million participants, and combine those results with machine-learning features from eye structure to make stronger risk scores. The work is led at a major eye center and uses data from multiple hospitals and biobanks so findings could apply to many people. If successful, these tools could help doctors find high-risk patients earlier and tailor monitoring or treatment.

Who could benefit from this research

Good fit: Ideal candidates are adults with glaucoma, people with a family history of glaucoma, or patients receiving eye care at participating centers who can share medical records, genetic data, or eye imaging.

Not a fit: People without available genetic data, eye imaging, or linkage to the participating medical centers/biobanks, and those with eye conditions unrelated to glaucoma, are unlikely to see direct benefit from this project.

Why it matters

Potential benefit: If successful, this could identify people at high risk for glaucoma earlier and help target monitoring or treatment to prevent vision loss.

How similar studies have performed: Prior studies show polygenic risk scores can predict glaucoma risk to a moderate degree, but combining refined electronic-health-record phenotypes and imaging-derived machine-learning features is newer and may substantially improve performance.

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.

View on NIH RePORTER →

Last reviewed 2026-05-15 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.