View abstract

This abstract is assigned to session AOB Free Papers 2

Presentation type	Oral presentation
Title	Artificial Intelligence (AI) for Community-based Glaucoma Risk Stratification

Purpose	To validate a deep learning model for automated glaucoma risk stratification from fundus images by comparison with expert grading in a community screening setting.
Methods	We conducted a prospective multicenter diagnostic accuracy study, screening 1,378 individuals over the age of 40 years in the foyer of eight Belgian hospitals using questionnaires, rebound tonometry, and fundus photography, with independent image grading by 6 glaucoma experts and an AI tool.
Results	Participants were more often female (63.8%), with a mean age of 60.1 years (SD 10.8); 34 (3.3%) having self-reported glaucoma and the mean intraocular pressure was 14.8 mmHg (SD 3.9). The AI risk score showed 100% sensitivity, 74.8% specificity, and an Area Under the Curve (AUC) of 0.93. The Intraclass Correlation Coefficient values were 0.73 for cup-to-disc ratio, 0.55 for image–only risk scores, and 0.54 for risk scores including metadata.
Conclusion	Variability among glaucoma expert assessments illustrates the challenge of consistently grading glaucoma risk from fundus images. Against this backdrop, the AI model demonstrated robust accuracy (AUC 0.93), underscoring its potential to act as a supportive tool for ophthalmologists, enhancing efficiency and consistency in identifying individuals who may benefit from further specialist evaluation.
Conflict of interest	Yes
Details of conflicting interests	Ingeborg Stalmans is co-founder, shareholder, and consultant of MONA.health.

Authors 1

Initials	T
Last name	Jacobs
Department	UZL/KUL
City	Leuven

Authors 2

Initials	A
Last name	Ehongo Bidime
Department	Hôpital Erasme
City	Brussels

Authors 3

Initials	N
Last name	Collignon
Department	CHU Liège
City	Luik

Authors 4

Initials	P
Last name	Kestelyn
Department	AZ Sint-Lucas
City	Ghent

Authors 5

Initials	S
Last name	Kiekens
Department	UZA
City	Antwerp

Authors 6

Initials	S
Last name	Pourjavan
Department	Cliniques Universitaires Saint-Luc
City	Brussels

Authors 7

Initials	S
Last name	Van de Veire
Department	AZ Sint-Jan
City	Bruges

Authors 8

Initials	V
Last name	De Groot
Department	ZAS Cadix
City	Antwerp

Authors 9

Initials	I
Last name	Stalmans
Department	UZL/KUL
City	Leuven

Authors 10

Initials	J
Last name	Van Eijgen
Department	UZL/KUL
City	Leuven