Real-World Prospective Validation and Economic Evaluation of Deep Learning– Based Diabetic Retinopathy Detection From Fundus Photographs: A Systematic Review and Meta-analysis
Published version of a preprint
Abstract
Background Deep learning (DL) has shown promise in delivering diagnostic and economic benefits for detecting diabetic retinopathy (DR) from fundus photographs (FPs). However, evidence synthesis of model validation in prospective, real-world settings remains limited. Purpose To assess the feasibility of implementing DL-DR systems using FPs across different countries by synthesizing prospective validation and economic evidence. Data sources Five databases were searched until 13 August 2025. Study selection Studies prospectively assessing diagnostic performance and/or studies conducting economic analyses of DL-DR systems using FPs were selected. Data extraction Characteristics of all studies, performance parameters of prospective validation studies, and economic outcomes of economic analysis studies were extracted. Data synthesis Forty-seven studies were included in the meta-analysis. The pooled performance was the highest in detecting vision-threatening DR (area under the receiver operating characteristic curve [AUROC] 0.974), followed by any DR (AUROC 0.965), then referable DR (RDR) (AUROC 0.959). Study region, clinical pathway, mydriasis, image quality control, sample size, grading criteria, reference standard, and model architecture significantly affected model performance in RDR detection. Fifteen studies were included in the economic commentary, showing that DL-based DR screening was cost-effective in high-income countries, whereas results in middle-income countries were m…
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
AI DR screening has high discriminative performance, particularly for vision-threatening DR, but performance is affected by region, clinical pathway, mydriasis, image quality control, sample size, grading criteria, reference standard, and model architecture.
“Ran and colleagues reviewed 47 prospective validation studies and found high discriminative performance, particularly for vision-threatening DR, while also showing that region, clinical pathway, mydriasis, image quality control, sample size, grading criteria, reference standard, and model architecture affected performance (15).”
From From validation to public health impact: implementing equitable AI-enabled diabetic retinopathy screening (2026) · cites this paper as [15]
The diagnostic evidence base for AI-enabled DR screening is now substantial.
“The diagnostic evidence base for AI-enabled DR screening is now substantial.”
From From validation to public health impact: implementing equitable AI-enabled diabetic retinopathy screening (2026) · cites this paper as [15]
Deep learning-based DR screening appeared generally favorable in high-income countries, while results in middle-income countries were mixed and sensitive to compliance rates, baseline glycemic control, and initial implementation costs; evidence from low-income countries remains sparse.
“Ran and colleagues found that deep learning-based DR screening appeared generally favorable in high-income countries, whereas results in middle-income countries were mixed and sensitive to compliance rates, baseline glycemic control, and initial implementation costs; evidence from low-income countries remains sparse (15).”
From From validation to public health impact: implementing equitable AI-enabled diabetic retinopathy screening (2026) · cites this paper as [15]
Cites
Shamseer, L., Moher, D., Clarke, M., Ghersi, D., Liberati, A., Petticrew, M., Shekelle, P., Stewart, L. A., & the PRISMA-P Group (2015) · BMJ · doi:10.1136/bmj.g7647 · Cited by 13,120 · see citing works
Wilkinson, C. P., Ferris, F. L., Klein, R., Lee, P. P., Agardh, C., Davis, M., Dills, D. G., Kampik, A., Pararajasegaram, R., & Verdaguer, J. (2003) · Ophthalmology · doi:10.1016/s0161-6420(03)00475-5 · Cited by 3,786 · see citing works
Deeks, J. J., Macaskill, P., & Irwig, L. (2005) · Journal of Clinical Epidemiology · doi:10.1016/j.jclinepi.2005.01.016 · Cited by 2,910 · see citing works
Ting, D. S. W., Cheung, C. Y.-L., Lim, G., Tan, G. S. W., Quang, N. D., Gan, A., Hamzah, H., Garcia-Franco, R., San Yeo, I. Y., Lee, S. Y., et al. (2017) · JAMA · doi:10.1001/jama.2017.18152 · Cited by 2,402 · see citing works
Self-citationThe diagnostic odds ratio: a single indicator of test performance
Glas, A. S., Lijmer, J. G., Prins, M. H., Bonsel, G. J., & Bossuyt, P. M. M. (2003) · Journal of Clinical Epidemiology · doi:10.1016/s0895-4356(03)00177-x · Cited by 2,261 · see citing works
The Lancet Global Health Commission on Global Eye Health: vision beyond 2020
Burton, M. J., Ramke, J., Marques, A. P., Bourne, R. R. A., Congdon, N., Jones, I., Ah Tong, B. A. M., Arunga, S., Bachani, D., Bascaran, C., et al. (2021) · The Lancet Global Health · doi:10.1016/s2214-109x(20)30488-5 · Cited by 1,624 · see citing works
Self-citationRuopp, M. D., Perkins, N. J., Whitcomb, B. W., & Schisterman, E. F. (2008) · Biometrical Journal · doi:10.1002/bimj.200710415 · Cited by 1,320 · see citing works
Guidelines on Diabetic Eye Care
Wong, T. Y., Sun, J., Kawasaki, R., Ruamviboonsuk, P., Gupta, N., Lansingh, V. C., Maia, M., Mathenge, W., Moreker, S., Muqit, M. M. K., et al. (2018) · Ophthalmology · doi:10.1016/j.ophtha.2018.04.007 · Cited by 839 · see citing works
Self-citationEmpirical Comparison of Publication Bias Tests in Meta-Analysis
Lin, L., Chu, H., Murad, M. H., Hong, C., Qu, Z., Cole, S. R., & Chen, Y. (2018) · Journal of General Internal Medicine · doi:10.1007/s11606-018-4425-7 · Cited by 464 · see citing works
The English National Screening Programme for diabetic retinopathy 2003–2016
Scanlon, P. H. (2017) · Acta Diabetologica · doi:10.1007/s00592-017-0974-1 · Cited by 439 · see citing works
The STARD-AI reporting guideline for diagnostic accuracy studies using artificial intelligence
Sounderajah, V., Guni, A., Liu, X., Collins, G. S., Karthikesalingam, A., Markar, S. R., Golub, R. M., Denniston, A. K., Shetty, S., Moher, D., et al. (2025) · Nature Medicine · doi:10.1038/s41591-025-03953-8 · Cited by 352 · see citing works
Lee, A. Y., Yanagihara, R. T., Lee, C. S., Blazes, M., Jung, H. C., Chee, Y. E., Gencarella, M. D., Gee, H., Maa, A. Y., Cockerham, G. C., et al. (2021) · Diabetes Care · doi:10.2337/dc20-1877 · Cited by 194 · see citing works
Rajesh, A. E., Davidson, O. Q., Lee, C. S., & Lee, A. (2023) · Diabetes Care · doi:10.2337/dci23-0032 · Cited by 166 · see citing works
Gomez Rossi, J., Rojas-Perilla, N., Krois, J., & Schwendicke, F. (2022) · JAMA Network Open · doi:10.1001/jamanetworkopen.2022.0269 · Cited by 141 · see citing works
Scanlon, P. H., Aldington, S. J., Leal, J., Luengo-Fernández, R., Oke, J. L., Sivaprasad, S., Gazis, A., & STRATTON, I. M. (2015) · Health Technology Assessment · doi:10.3310/hta19740 · Cited by 138 · see citing works
Self-citationVerbraak, F. D., Abramoff, M. D., Bausch, G. C. F., Klaver, C., Nijpels, G., Schlingemann, R. O., & van der Heijden, A. A. (2019) · Diabetes Care · doi:10.2337/dc18-0148 · Cited by 115 · see citing works
Availability and variability in guidelines on diabetic retinopathy screening in Asian countries
Wang, L. Z., Cheung, C. Y.-L., Tapp, R. J., Hamzah, H., Tan, G. S. W., Ting, D. S. W., Lamoureux, E. L., & Wong, T. Y. (2017) · British Journal of Ophthalmology · doi:10.1136/bjophthalmol-2016-310002 · Cited by 91 · see citing works
Self-citationCost-effectiveness of artificial intelligence screening for diabetic retinopathy in rural China
Huang, X.-M., Yang, B.-F., Zheng, W.-L., Liu, Q., Xiao, F., Ouyang, P.-W., Li, M.-J., Li, X.-Y., Meng, J., Zhang, T.-T., et al. (2022) · BMC Health Services Research · doi:10.1186/s12913-022-07655-6 · Cited by 89 · see citing works
Wolf, R. M., Channa, R., Abramoff, M. D., & Lehmann, H. P. (2020) · JAMA Ophthalmology · doi:10.1001/jamaophthalmol.2020.3190 · Cited by 87 · see citing works
Elvidge, J., Hawksworth, C., Avşar, T. S., Zemplenyi, A. T., Chalkidou, A., Petrou, S., Petykó, Z. I., Srivastava, D., Chandra, G., Delaye, J., et al. (2024) · Value in Health · doi:10.1016/j.jval.2024.05.006 · Cited by 80 · see citing works
Wang, Y., Liu, C., Hu, W., Luo, L., Shi, D., Zhang, J., Yin, Q., Zhang, L., Han, X., & He, M. (2024) · npj Digital Medicine · doi:10.1038/s41746-024-01032-9 · Cited by 76 · see citing works
Sivaprasad, S., Wong, T. Y., Gardner, T. W., Sun, J. K., & Bressler, N. M. (2025) · Nature Reviews Disease Primers · doi:10.1038/s41572-025-00646-x · Cited by 65 · see citing works
Self-citationFuller, S. D., Hu, J. Q., Liu, J. C., Gibson, E., Gregory, M. H., Kuo, J., & Rajagopal, R. (2020) · Journal of Diabetes Science and Technology · doi:10.1177/1932296820967011 · Cited by 60 · see citing works
Lin, S., Ma, Y., Xu, Y., Lu, L., He, J., Zhu, J., Peng, Y., Yu, T., Congdon, N., & Zou, H. (2023) · JMIR Public Health and Surveillance · doi:10.2196/41624 · Cited by 52 · see citing works
Zhang, J., Lin, S., Cheng, T., Xu, Y., Lu, L., He, J., Yu, T., Peng, Y., Zhang, Y., Zou, H., et al. (2024) · npj Digital Medicine · doi:10.1038/s41746-024-01109-5 · Cited by 51 · see citing works
Gu, C., Wang, Y., Jiang, Y., Xu, F., Wang, S., Liu, R., Yuan, W., Abudureyimu, N., Wang, Y., Lu, Y., et al. (2023) · British Journal of Ophthalmology · doi:10.1136/bjo-2022-322940 · Cited by 39 · see citing works
Hu, W., Lin, Z., Clark, M., Henwood, J., Shang, X., Chen, R., Kiburg, K., Zhang, L., Ge, Z., van Wijngaarden, P., et al. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-01436-1 · Cited by 28 · see citing works
Li, H., Li, G., Li, N., Liu, C., Yuan, Z., Gao, Q., Hao, S., Fan, S., & Yang, J. (2023) · PLOS ONE · doi:10.1371/journal.pone.0291390 · Cited by 27 · see citing works
Yang, Y., Pan, J., Yuan, M., Lai, K., Xie, H., Ma, L., Xu, S., Deng, R., Zhao, M., Luo, Y., et al. (2022) · Annals of Translational Medicine · doi:10.21037/atm-22-350 · Cited by 25 · see citing works
Dong, X., Du, S., Zheng, W., Cai, C., Liu, H., & Zou, J. (2022) · Frontiers in Medicine · doi:10.3389/fmed.2022.883462 · Cited by 23 · see citing works
National Use of Artificial Intelligence for Eye Screening in Singapore
Gunasekeran, D. V., Miller, S., Hsu, W., Lee, M. L., Wong, H. T., Lee, M. T., Lamoureux, E. L., Ting, D. S. W., Tan, G. S. W., & Wong, T. Y. (2024) · NEJM AI · doi:10.1056/aics2400404 · Cited by 20 · see citing works
Self-citationCost-effectiveness of AI for pediatric diabetic eye exams from a health system perspective
Ahmed, M., Dai, T., Channa, R., Abràmoff, M. D., Lehmann, H. P., & Wolf, R. M. (2025) · npj Digital Medicine · doi:10.1038/s41746-024-01382-4 · Cited by 20 · see citing works
Macdonald, T., Zhelev, Z., Liu, X., Hyde, C., Fajtl, J., Egan, C. A., Tufail, A., Rudnicka, A. R., Shinkins, B., Given-Wilson, R., et al. (2025) · The Lancet Digital Health · doi:10.1016/j.landig.2024.12.004 · Cited by 15 · see citing works
Building the world’s first truly global medical foundation model
Tham, Y. C., Goh, J. H. L., Nderitu, P., Zhou, Y., Ran, A. R., Srinivasan, S., Yang, G. D., Kitema, G. F., Rawlinson, P., Jiang, H., et al. (2025) · Nature Medicine · doi:10.1038/s41591-025-03859-5 · Cited by 13 · see citing works
Self-citationNguyen, T. X., Jiang, M., Yang, D., Ran, A. R., Tang, Z., Zhang, S., Hu, X., Tran, V. T., Dai, T. B. L., Le, D. T., et al. (2024) · NEJM AI · doi:10.1056/aioa2400091 · Cited by 11 · see citing works
Self-citationChawla, S., Chawla, A., Chawla, R., Jaggi, S., Singh, D. V., & Trehan, S. (2022) · International Journal of Diabetes in Developing Countries · doi:10.1007/s13410-021-01037-0 · Cited by 7 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Dave, D., Steinhubl, S. R., & McQueen, R. B. (2026) · Diabetes Care · doi:10.2337/dci25-0123 · Cited by 2 · see citing works
Scan Density Matters: Reproducibility of AI-Derived OCT Biomarkers in Diabetic Macular Edema
Cocuzza, M., Ziafati, M., Lattanzio, R., Midena, E., Bandello, F. M., & Cicinelli, M. V. (2026) · Translational Vision Science & Technology · doi:10.1167/tvst.15.5.12 · Cited by 1 · see citing works
Chen, J., & Chen, B. (2026) · Frontiers in Public Health · doi:10.3389/fpubh.2026.1976572
A tribute to Charles L. Schepens, twenty years on
Hanhart, J., & Schepens, P. (2026) · AJO International · doi:10.1016/j.ajoint.2026.100296
Quantum–Classical Interpolation Model for Early Diagnosis of Diabetic Retinopathy
Guduru, M., Reddy, A., & Prakash, K. B. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-28594-2_43
Zhang, C., Wang, L., Huang, S., Zheng, R., Li, J., Sun, X., Wu, S., Zhang, T., Zhang, X., Xu, Q., et al. (2026) · Frontiers in Endocrinology · doi:10.3389/fendo.2026.1941613
When the Algorithm Speaks First: Trust, Reliance and the Reconstruction of Clinical Metacognition
Hanhart, J., & Zohar, A. E. (2026) · Journal of Evaluation in Clinical Practice · doi:10.1111/jep.70652
- Authors
- Ran, A. R., Ding, J. L., Tang, Z., Lam, C., Nguyen, T. X., Zhou, J., Zhang, S., Fang, D., Yang, D., Ng, V., Lin, D., Lin, H., Tham, C. C., Chan, C. K. M., Szeto, S. K. H., Wong, T. Y., Sivaprasad, S., & Cheung, C. Y.
- Affiliations
- Chinese University of Hong Kong (HK)
- Imperial College London (GB)
- University Hospitals Birmingham NHS Foundation Trust (GB)
- Sun Yat-sen University (CN)
- Singapore National Eye Center (SG)
- NIHR Moorfields Biomedical Research Centre (GB)
- ORCID
- Venue
- Diabetes Care
- Publisher
- American Diabetes Association
- Published
- 2025-11-19
- Volume
- 49
- Issue
- 3
- Pages
- 510-525
- ISSN
- 0149-5992 (ISSN-L)
- 1935-5548
- OpenAlex
- W4416370954
- Cited by
- 7
- References
- 36
- Citations by year
- 2026: 7
- FWCI
- 1.10
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Diabetes Care (publishedVersion)
- PubMed (publishedVersion)
- Funders
- Research Grants Council, University Grants Committee (14101324)
- Topics
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Retinal Imaging and Analysis
- Health Sciences › Medicine › Ophthalmology › Retinal Diseases and Treatments
- Health Sciences › Medicine › Ophthalmology › Ophthalmology and Visual Health Research
- Keywords
- diabetic retinopathy, deep learning, fundus images, vision-threatening diabetic retinopathy, referable diabetic retinopathy, diagnostic accuracy, cost-effectiveness, automated retinopathy detection, diabetic macular edema, pupil dilation, image quality control
- MeSH terms
- Deep Learning, Cost-Benefit Analysis, Diabetic Retinopathy, Fundus Oculi, Humans, Photography, Prospective Studies
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
