Medical-AI trial: finding early glaucoma from fundus photos with AI (GlaukomAI) — preventing blindness and cutting waits (NCT07668193)
A study evaluating whether the AI software GlaukomAI can detect glaucoma, a leading cause of irreversible blindness, at an early stage from fundus (back-of-eye) photographs. Current diagnosis needs multiple specialist visits and tests, causing long waits and delays. At an eye institute in Rome, Italy, Phase 1 uses 100 glaucoma and 100 healthy controls to assess accuracy (sensitivity and specificity). 1,200 patients; two phases.
Trial overview (primary data)
- StatusNot yet recruiting
- ConditionsGlaucoma
- InterventionsDEVICE: GlaukomAI (Sens-vue GlaukomAI)
- SponsorFondazione G.B. Bietti, IRCCS
- Target enrollment1,200 participants
- Period2026-06-01 〜 2028-05-01
Key points
- A study of whether the AI software GlaukomAI can detect glaucoma, a leading cause of irreversible blindness, early from fundus photographs.
- Current diagnosis needs multiple specialist visits and tests, causing long waits and delays.
- At an eye institute in Rome, Italy, in two phases; Phase 1 uses 100 glaucoma and 100 healthy controls in a case-control design.
- The primary outcome is diagnostic accuracy: sensitivity and specificity. Total 1,200, including referral-accuracy assessment.
- Fundus photos are simple; AI reading could triage crowded specialty clinics. An accuracy/referral evaluation, not an establishment of diagnosis replacement.
Glaucoma damages the optic nerve at the back of the eye little by little, narrowing the visual field, and because lost vision does not return (it is irreversible), it is one of the leading causes of blindness worldwide. Early on there are few symptoms, so it is often advanced by the time it is noticed.
That is why early detection matters, yet a confirmed diagnosis requires several tests (eye pressure, visual field, fundus, OCT) and repeated specialist visits, creating waits and delays.
The GlaukomAI this study evaluates tries to widen that entry point, aiming to detect early glaucoma by analyzing fundus (back-of-eye) photographs with AI. Per the registry summary, the study is conducted at an eye institute (IRCCS Fondazione G. B. Bietti) in Rome, Italy, in two phases.
Phase 1 enrolls 200 participants (100 with diagnosed glaucoma and 100 healthy controls) to assess, in a case-control design, how accurately GlaukomAI can tell them apart. The primary outcome is diagnostic accuracy: sensitivity (not missing disease) and specificity (not misclassifying). The overall size is 1,200, including an assessment of referral accuracy.
A fundus photograph is simple enough to take at a health check or an optical shop, so if AI can read it, it could flag suspected glaucoma before specialist referral and triage crowded specialty clinics more smartly.
First confirming accuracy in a case-control design, then examining actual referral accuracy, is a sound path for evaluating a screening AI. That said, this study evaluates accuracy and referral appropriateness; it does not establish replacement of specialist diagnosis or clinical adoption.
Why it matters
A fundus photo can be taken at a health check or optical shop. If AI reading can flag suspected glaucoma before specialist referral, it could triage crowded specialty clinics. A case-control then referral-accuracy design is a sound way to evaluate a screening AI (this study is an evaluation stage, not an establishment of diagnosis replacement).
FAQ
Why does early glaucoma detection matter?
Does the AI replace the eye doctor diagnosis?
Sources (primary)
Source: ClinicalTrials.gov (U.S. NIH/NLM, public domain). This site does not provide medical advice. Verify the latest and exact details with the official source. This site is not endorsed or certified by the NIH/NLM.
- ClinicalTrials.gov (study record, original)
- NCT ID: NCT07668193