Development and Validation of a Deep Learning System for the Provision of a District‐Wide Diabetes Retinal Screening Service
Clinical & Experimental Ophthalmology · 2025
DOI: 10.1111/ceo.14560 ↗Kurz gefasst
Validierungsstudie in der Zeitschrift Clinical & Experimental Ophthalmology, 2025. Verfasst von Jason R Daley und 12 weiteren Autor:innen. Beteiligte Einrichtung: Liverpool Hospital, Sydney, Australia. Hauptthemen laut MEDLINE: Deep Learning, Diabetic Retinopathy, Mass Screening. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Ophthalmic Research Institute of Australia.
Themen: Diabetes mellitus
Abstract (Originalsprache)
Background
Artificial intelligence (AI) enhanced retinal screening could reduce the impact of diabetic retinopathy (DR), the leading cause of preventable blindness in Australia. This study assessed the performance and validity of a dual‐modality, deep learning system for detection of vision‐threatening diabetic retinopathy (vtDR) in a multi‐ethnic community.
Methods
Cross‐sectional (algorithm‐validation) study with the deep learning system assessing fundus photographs for gradability and severity of DR, and optical coherence tomography (OCT) scans for diabetic macular oedema (DMO). Internal validation of each algorithm was performed using a computer‐randomised 80:20 split. External validation was by comparison to standard grading provided by two ophthalmologists in 748 prospectively recruited persons with diabetes (age ≥ 10) from hospital diabetes clinics and a general practice. Main outcome measures included sensitivity, specificity and the area under the receiver operating characteristic curve (AUC).
Results
Internal validation revealed robust test characteristics. When compared to ophthalmologists, the system achieved an AUC of 0.92 (95% CI 0.90–0.94) for fundus photograph gradeability, 0.91 (95% CI 0.85–0.94) for the diagnosis of severe non‐proliferative DR/proliferative DR and 0.90 (95% CI 0.87–0.96) for DMO detection from OCT scans. It demonstrated real‐world applicability with an AUC of 0.94 (95% CI 0.91–0.97), sensitivity of 92.7% and specificity of 95.5% for detection of vtDR. Ungradable images occurred in 55 participants (7.4%).
Conclusions
The dual‐modality, deep learning system can diagnose vtDR from fundus photographs and OCT scans with high levels of accuracy and specificity. This could support a novel model of care for DR screening in our community.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Liverpool Hospital, Sydney, Australia.
- The University of Sydney, Sydney, Australia.
- The University of New South Wales, Sydney, Australia.
- Healthfocus Family Practice, Sydney, Australia.
- Royal Prince Alfred Hospital, Sydney, Australia.
- Westmead Hospital, Sydney, Australia.
ORCID-Profile: Jason R Daley, Peter Heydon
Förderung
- Ophthalmic Research Institute of Australia
Zitieren
APA
Daley, J. R., Wang, X., Ngo, N., Khoo, C. L., Heydon, P., Liew, G., Vallayutham, V., Kongbrailatpam, T., Osuagwu, U. L., Andric, M., Xuan, W., Simmons, D., & Kaushik, S. (2025). Development and Validation of a Deep Learning System for the Provision of a District‐Wide Diabetes Retinal Screening Service. Clinical & Experimental Ophthalmology. https://doi.org/10.1111/ceo.14560
Vancouver
Daley JR, Wang X, Ngo N, Khoo CL, Heydon P, Liew G, et al. Development and Validation of a Deep Learning System for the Provision of a District‐Wide Diabetes Retinal Screening Service. Clinical & Experimental Ophthalmology. 2025. doi:10.1111/ceo.14560
BibTeX
@article{Daley2025,
author = {Daley, Jason R and Wang, Xingdi and Ngo, Natalie and Khoo, Chee L and Heydon, Peter and Liew, Gerald and Vallayutham, Vallimayil and Kongbrailatpam, Tobias and Osuagwu, Uchechukwu L and Andric, Marko and Xuan, Wei and Simmons, David and Kaushik, Shweta},
title = {Development and Validation of a Deep Learning System for the Provision of a District‐Wide Diabetes Retinal Screening Service},
journal = {Clinical & Experimental Ophthalmology},
year = {2025},
doi = {10.1111/ceo.14560}
}
EUVIMED