Post

New research · Ophthalmology
Ophthalmology science · 3d
AI / informaticsOphthalmology science · 2026

Artificial Intelligence-Driven Multimodal Prediction of 10-Year Incident Glaucoma Integrating Genetic and Deep Learning-Derived Imaging Features.

Fengze Wu, Xiaoyi Raymond Gao
Read paper
OphthalmologyAI / informatics

AI model using imaging and genetic data predicts 10-year glaucoma risk accurately

Artificial Intelligence-Driven Multimodal Prediction of 10-Year Incident Glaucoma Integrating Genetic and Deep Learning-Derived Imaging Features.

Fengze Wu, Xiaoyi Raymond Gao
Ophthalmology science · 2026
Background

Glaucoma is the leading cause of irreversible blindness worldwide.

Purpose

Glaucoma is the leading cause of irreversible blindness worldwide.

Methods

The primary analytic cohort for strictly defined incident primary open-angle glaucoma (primary open-angle glaucoma) comprised 340 cases and 9374 controls; the secondary broadly defined primary open-angle glaucoma cohort comprised 1241 cases and 34 216 controls.

n = 9374 controls
Results

correctly told apart future glaucoma cases from those who stayed healthy

AUC 0.93 (95% CI 0.90 to 0.96)
null 0
0.90
0.96
CI excludes the null - significant
More results

The corresponding XGBoost model for broadly defined primary open-angle glaucoma showed modestly lower discrimination while maintaining similarly strong calibration.

SHapley Additive exPlanations analysis identified the color fundus photographs deep learning score, age, polygenic risk scores, and intraocular pressure as the most influential predictors.

More results

A reduced model using only the top 4 SHAP-ranked features retained performance comparable to the all-features multimodal model.

“
Conclusion

Our multimodal machine learning framework integrating genetic and deep learning-derived imaging features enables accurate and interpretable prediction of incident primary open-angle glaucoma.

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