Deep learning in population-based screening for glaucoma
- 15 April 2026
- journal article
- Published by BMJ in British Journal of Ophthalmology
Abstract
Background/aims: Deep learning algorithms have shown promise for glaucoma detection using retinal imaging. The Northern Finland Birth Cohort Eye Study is a randomised prospective cohort designed to evaluate the efficacy and cost-effectiveness of glaucoma screening in a middle-aged population. This study assessed the performance and generalisability of G-RISK, a deep learning model for glaucoma screening from fundus images, in individuals aged 45–49 years with low glaucoma prevalence (1.1%). Methods: Four screening scenarios were evaluated: detection of (1) glaucoma eyes, (2) glaucoma patients, (3) glaucoma and glaucoma suspect eyes and (4) glaucoma and glaucoma suspect patients. Performance across four photographic modalities was assessed using the area under the receiver operating characteristic curve (AUC), the precision–recall AUC (PR-AUC), and sensitivity at 95% specificity. Results: G-RISK achieved its highest performance when screening for glaucoma eyes using colour fundus photographs, with an AUC of 0.83 (95% CI 0.75 to 0.90), PR-AUC of 0.16 (95% CI 0.05 to 0.28) and sensitivity at 95% specificity of 0.43 (95% CI 0.28 to 0.59). Furthermore, discrimination remained consistent across other modalities (AUC 0.75–0.78). Performance was higher for confirmed glaucoma than combined glaucoma and glaucoma suspect cases (AUC 0.83 vs 0.67). Conclusions: G-RISK achieved the best results on colour fundus images, while maintaining discrimination across other imaging modalities. Screening metrics were constrained by the relatively young age and low glaucoma prevalence of the cohort. The reduced performance observed when including glaucoma suspects may relate to variability and uncertainty in their clinical definition.Keywords
Funding Information
- Mary och Georg C. Ehrnrooths Stiftelse (not available)
This publication has 17 references indexed in Scilit:
- Evaluation of performance measures in predictive artificial intelligence models to support medical decisions: overview and guidanceThe Lancet Digital Health, 2025
- Deep learning on fundus images detects glaucoma beyond the optic discScientific Reports, 2021
- A Deep Learning Algorithm to Quantify Neuroretinal Rim Loss From Optic Disc PhotographsAmerican Journal of Ophthalmology, 2019
- From Machine to MachineOphthalmology, 2019
- Prevalence of glaucoma in Germany: results from the Gutenberg Health StudyGraefe's Archive for Clinical and Experimental Ophthalmology, 2018
- A machine-learning graph-based approach for 3D segmentation of Bruch’s membrane opening from glaucomatous SD-OCT volumesMedical Image Analysis, 2017
- Global Prevalence of Glaucoma and Projections of Glaucoma Burden through 2040Ophthalmology, 2014
- The Finnish evidence‐based guideline for open‐angle glaucomaActa Ophthalmologica Scandinavica, 2003
- Confirmation of Visual Field Abnormalities in the Ocular Hypertension Treatment StudyArchives of Ophthalmology (1950), 2000
- Prevalence of Open-angle Glaucoma in AustraliaOphthalmology, 1996