Artificial Intelligence-Driven Multimodal Prediction of 10-Year Incident Glaucoma Integrating Genetic and…

AI / informaticsOphthalmology science· Aug 2026

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

Fengze Wu, Xiaoyi Raymond Gao

GlaucomaAI / informaticsPrognosisQ1IF 5.5

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 · Aug 2026 · Q1 in Ophthalmology

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.

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

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

Related papers