Post

New research · Ophthalmology
Asia-Pacific journal of ophthalmology (Philadelphia, Pa.) · 3d
AI / informaticsAsia-Pacific journal of ophthalmology (Philadelphia, Pa.) · 2026

Multimodal foundation model assistance for differentiating primary open-angle glaucoma in highly myopic eyes.

Houfa Yin, Kaikai Zhao, Qi Miao … Kai Jin
Read paper
OphthalmologyAI / informatics

Artificial intelligence assistance modestly raised ophthalmologists' sensitivity for glaucoma in highly myopic eyes

Multimodal foundation model assistance for differentiating primary open-angle glaucoma in highly myopic eyes.

Houfa Yin … Kai Jin
Asia-Pacific journal of ophthalmology (Philadelphia, Pa.) · 2026
Purpose

To develop and evaluate a multimodal foundation-model-assisted system for differentiating primary open-angle glaucoma (primary open-angle glaucoma) from non-glaucoma in highly myopic eyes and assessing whether artificial intelligence (artificial intelligence) assistance changes ophthalmologist diagnostic performance.

Methods

Model development used 603 eye-level cases (502 primary open-angle glaucoma, 101 non-glaucoma); a fixed 150-case set from 149 patients was used for internal test reporting and the paired reader evaluation.

n = 149 patients
Results

Artificial intelligence help raised how often doctors correctly spotted real glaucoma cases

68%
Sensitivity
91.3%
Specificity
More results

The final multimodal model achieved an AUC of 0.911 (95% confidence interval [CI], 0.862-0.950) on the fixed 150-case set.

Reader-level diagnostic differences were not significant after multiplicity adjustment and were exploratory.

“
Conclusion · 1 of 2

In this internal retrospective study, the artificial intelligence-assisted phase showed numerically higher mean sensitivity, accuracy, confidence, and inter-reader agreement than the unaided phase, with unchanged mean specificity.

Conclusion · 2 of 2

Reader-level diagnostic differences were not statistically significant after multiplicity adjustment and should be considered exploratory. Prospective multicenter validation is required before clinical deployment.

Read paper
0 comments

No comments yet. Be the first.

Related papers

LatestFoundational
AI / Informatics
0·962 for OCT
MerMED-FM was very accurate at diagnosing diseases using eye scans
AI / Informatics
0.98
Artificial intelligence's eyelid-height measurements matched doctors' manual measurements almost perfectly
AI / Informatics
92.1%
combining eye scans and photos correctly told benign from cancerous lesions apart nearly every time
Cohort Study
28.6%
recurred locally in more than 1 in 4 patients over years of follow-up
Cohort Study
-0.395
excision group's post-op eyelid fullness score was lower - greater improvement
Cohort Study
86.7%
of infants probed after 12 months still had unresolved tear duct blockage
Observational
16%
eyelid tissue in rosacea patients showed less of this key repair-signaling protein inside cell nuclei
Cohort Study
25%
about 1 in 4 treated cases had symptoms return after improving