Systematic review and meta-analysis of regulator-approved deep learning systems for fundus diabetic retinopathy detections – npj Digital Medicine

Yau, J. W. et al. Global prevalence and major risk factors of diabetic retinopathy. Diab. Care 35, 556–64 (2012).

Google Scholar 

Teo, Z. L. et al. Global prevalence of diabetic retinopathy and projection of burden through 2045: systematic review and meta-analysis. Ophthalmology 128, 1580–1591 (2021).

Google Scholar 

International Diabetes Federation. IDF Diabetes Atlas, 10th ed.; 2021.

Flaxel, C. J. et al. Diabetic retinopathy preferred practice pattern®. Ophthalmology 127, P66–P145 (2020).

Google Scholar 

Cheung, N. et al. Diabetic retinopathy. Lancet 376, 124–36 (2010).

Google Scholar 

Solomon, S. D. et al. Diabetic retinopathy: a position statement by the American Diabetes Association. Diab. Care 40, 412–418, https://doi.org/10.2337/dc16-2641 (2017).

Google Scholar 

Rahmati, M. et al. Factors affecting global adherence for the uptake of diabetic retinopathy screening: a systematic review and meta-analysis. Am. J. Ophthalmol. 268, 94–107 (2024).

Google Scholar 

Teo, Z. L. et al. Do we have enough ophthalmologists to manage vision-threatening diabetic retinopathy? A global perspective. Eye 34, 1255–1261 (2020).

Google Scholar 

Liew, G., Michaelides, M. & Bunce, C. A comparison of the causes of blindness certifications in England and Wales in working age adults (16–64 years), 1999–2000 with 2009–2010. BMJ Open 4, e004015 (2014).

Google Scholar 

Gulshan, V. et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA 316, 2402–2410 (2016).

Google Scholar 

Ting, D. S. W. et al. Development and validation of a deep-learning system for diabetic retinopathy in multi-ethnic populations. JAMA 318, 2211–2223 (2017).

Google Scholar 

Bellemo, V. et al. Artificial intelligence using deep learning to screen for referable and vision-threatening diabetic retinopathy in Africa: a clinical validation study. Lancet Digit. health 1, e35–e44 (2019).

Google Scholar 

Alqahtani, A. S. et al. “The efficacy of artificial intelligence in diabetic retinopathy screening: a systematic review and meta-analysis.” Int. J. Retina Vitreous 1148. 2025.

Abràmoff, M. D. et al. Pivotal trial of an autonomous AI system for detection of diabetic retinopathy. npj Digit. Med. 1, 39 (2018).

Google Scholar 

Ipp, E. et al. Pivotal evaluation of an AI system for autonomous detection of diabetic retinopathy. JAMA Netw. Open 4, e2134254 (2021).

Google Scholar 

Bhaskaranand, M. et al. Automated DR screening with the EyeArt system: >100 000 encounters. Diab. Technol. Ther. 21, 635–643 (2019).

Google Scholar 

Lim, J. I. et al. Artificial intelligence detection of diabetic retinopathy: subgroup comparison of the EyeArt System with ophthalmologists’ dilated examinations. Ophthalmol. Sci. 3, 100228 (2022).

Google Scholar 

Kaushal, A., Altman, R. & Langlotz, C. Geographic and demographic bias in AI diagnostic performance. Nat. Med. 28, 1328–1334 (2022).

Google Scholar 

Khinvasara, T., Tzenios, N. & Shankar, A. Post-market surveillance of medical devices using AI. J. Complement. Altern. Med. Res. 25, 108–22 (2024).

Google Scholar 

Khan, Z. et al. Diagnostic accuracy of IDx-DR: a systematic review and meta-analysis. Am. J. Ophthalmol. 273, 192–204 (2025).

Google Scholar 

Brant, A. et al. Performance of a deep learning diabetic retinopathy algorithm in India. JAMA Netw. Open 8, e250984 (2025).

Google Scholar 

Chotcomwongse, P. et al. Transforming non-digital, clinical workflows to detect and track vision-threatening diabetic retinopathy via a digital platform integrating artificial intelligence: implementation research. Ophthalmol. Ther. 14, 447–460 (2025).

Google Scholar 

Tan-Torres, A. et al. Validation oF A Deep Learning Model For Diabetic Retinopathy On Patients With Young-onset Diabetes. Ophthalmol. Ther. 14, 1147–1155 (2025).

Google Scholar 

Wei, Q. et al. Practical applications of artificial intelligence diagnostic systems in fundus retinal disease screening. Int. J. Gen. Med. 18, 1173–1180 (2025).

Google Scholar 

Wroblewski, J. J. et al. Diabetic retinopathy screening using smartphone-based fundus photography and deep-learning artificial intelligence in the Yucatan Peninsula: a field study. J. Diab. Sci. Technol. 19, 370–376 (2025).

Google Scholar 

Doğan, M. E. et al. Head-to-head comparison of diagnostic performance of three non-mydriatic cameras for diabetic retinopathy screening with artificial intelligence. Eye 38, 1694–1701 (2024).

Google Scholar 

Grzybowski, A. et al. Diagnostic accuracy of automated diabetic retinopathy image assessment software: IDx-DR and RetCAD. Ophthalmol. Ther. 14, 73–84 (2025).

Google Scholar 

Grzybowski, A. et al. Evaluating the efficacy of AI systems in diabetic retinopathy detection: a comparative analysis of Mona DR and IDx-DR. Acta Ophthalmol. 103, 388–395 (2025).

Google Scholar 

Ibañez-Bruron, M. C. et al. Uso de inteligencia artificial en el tamizaje de retinopatía diabética: experiencia en un servicio de salud de Santiago, Chile” [Use of artificial intelligence in diabetic retinopathy screening: experience in a health service in Santiago, Chile]. Rev. Med. Chile 152, 1148–1153 (2024).

Google Scholar 

Karabeg, M. et al. A pilot cost-analysis study comparing AI-based EyeArt® and ophthalmologist assessment of diabetic retinopathy in minority women in Oslo, Norway. Int. J. Retin. Vitreous 10, 40 (2024).

Google Scholar 

Li, Z. et al. Application of artificial intelligence remote screening system for diabetic retinopathy in Yinchuan community of Ningxia. Int. Eye Sci. 12, 1365–1368 (2022). (2022).

Google Scholar 

Musetti, D. et al. Autonomous artificial intelligence versus teleophthalmology for diabetic retinopathy. Eur. J. Ophthalmol. 35, 232–238 (2025).

Google Scholar 

Espeut, J., Molina, F. & Van, T. N. N. Effectiveness of artificial intelligence for diabetic retinopathy screening in community in Binh Dinh Province, Vietnam. Taiwan J. Ophthalmol. 14, 394–402 (2024).

Google Scholar 

Piatti, A. et al. Feasibility and accuracy of the screening for diabetic retinopathy using a fundus camera and an artificial intelligence pre-evaluation application. Acta Diabetol. 61, 63–68 (2024).

Google Scholar 

Piatti, A. et al. Diabetic retinopathy screening with confocal fundus camera and artificial intelligence – assisted grading. Eur. J. Ophthalmol. 35, 679–688 (2025).

Google Scholar 

Riotto, E. et al. Accuracy of autonomous artificial intelligence-based diabetic retinopathy screening in real-life clinical practice. J. Clin. Med. 13, 4776 (2024).

Google Scholar 

Šín, M. et al. Comparison of the Aireen system with telemedicine evaluation by an ophthalmologist – a real-world study. Clin. Ophthalmol. 19, 957–964 (2025).

Google Scholar 

Taylor, J. R. et al. Real-world evaluation of RetCAD deep-learning system for the detection of referable diabetic retinopathy and age-related macular degeneration. Clin. Exp. Optomet. 1-6 (2024).

Yao, L. et al. Screening and evaluation of diabetic retinopathy via a deep learning network model: a prospective study. World J. Diab. 15, 2302–2310 (2024).

Google Scholar 

Chia, M. A. et al. Validation of a deep learning system for the detection of diabetic retinopathy in Indigenous Australians. Br. J. Ophthalmol. 108, 268–273 (2024).

Google Scholar 

Dow, E. R. et al. AI-human hybrid workflow enhances teleophthalmology for the detection of diabetic retinopathy. Ophthalmol. Sci. 3, 100330 (2023).

Google Scholar 

Grzybowski, A. et al. Diagnostic accuracy of automated diabetic retinopathy image assessment softwares: IDx-DR and medios artificial intelligence. Ophthalmic Res. 66, 1286–1292 (2023).

Google Scholar 

He, S. et al. Cross-camera performance of deep learning algorithms to diagnose common ophthalmic diseases: a comparative study highlighting feasibility to portable fundus camera use. Curr. Eye Res. 48, 857–863 (2023).

Google Scholar 

Kemp, O. et al. Real-world evaluation of smartphone-based artificial intelligence to screen for diabetic retinopathy in Dominica: a clinical validation study. BMJ Open Ophthalmol. 8, e001491 (2023).

Google Scholar 

Lupidi, M. et al. Artificial intelligence in diabetic retinopathy screening: clinical assessment using handheld fundus camera in a real-life setting. Acta Diabetolog. 60, 1083–1088 (2023).

Google Scholar 

Meredith, S. et al. “Performance of an artificial intelligence automated system for diabetic eye screening in a large English population.” Diabetic Med. 40, e15055 (2023).

Fleming, A. D. et al. Deep learning detection of diabetic retinopathy in Scotland’s diabetic eye screening programme. Br. J. Ophthalmol. 108, 984–988 (2024).

Google Scholar 

Salongcay, R. P. et al. Accuracy of integrated artificial intelligence grading using handheld retinal imaging in a Community Diabetic Eye Screening Program. Ophthalmol. Sci. 4, 100457 (2023).

Google Scholar 

Vought, R. et al. EyeArt artificial intelligence analysis of diabetic retinopathy in retinal screening events. Int. Ophthalmol. 43, 4851–4859 (2023).

Google Scholar 

Arenas-Cavalli, J. T. et al. Clinical validation of an artificial intelligence-based diabetic retinopathy screening tool for a national health system. Eye 36, 78–85 (2022).

Google Scholar 

Dong, X. et al. Evaluation of an artificial intelligence system for the detection of diabetic retinopathy in chinese community healthcare centers. Front. Med. 9, 883462 (2022).

Han, R. et al. Validating automated eye disease screening AI algorithm in community and in-hospital scenarios. Front. Public Health 10, 944967 (2022).

Google Scholar 

Hao, S. et al. Clinical evaluation of AI-assisted screening for diabetic retinopathy in rural areas of midwest China. PloS One 17, e0275983 (2022).

Google Scholar 

Li, F. et al. A multicenter clinical study of the automated fundus screening algorithm. Transl. Vis. Sci. Technol. 11, 22 (2022).

Google Scholar 

Mehra, A. A. et al. Diabetic retinopathy telemedicine outcomes with artificial intelligence-based image analysis, reflex dilation, and image overread. Am. J. Ophthalmol. 244, 125–132 (2022).

Google Scholar 

Mokhashi, N. et al. A comparison of artificial intelligence and human diabetic retinal image interpretation in an urban health system. J. Diab. Sci. Technol. 16, 1003–1007 (2022).

Google Scholar 

Paul, S. et al. Einsatz von künstlicher Intelligenz im Screening auf diabetische Retinopathie an einer diabetologischen Schwerpunktklinik” [Use of artificial intelligence in screening for diabetic retinopathy at a tertiary diabetes center]. Die Ophthalmol. 119, 705–713 (2022).

Google Scholar 

Pei, X. et al. Efficacy of artificial intelligence-based screening for diabetic retinopathy in type 2 diabetes mellitus patients. Diab. Res.Clin. Pract. 184, 109190 (2022).

Google Scholar 

Rao, D. P. et al. Towards a device agnostic AI for diabetic retinopathy screening: an external validation study. Clin. Ophthalmol. 16, 2659–2667 (2022).

Google Scholar 

Nunez do Rio, J. M. et al. Evaluating a deep learning diabetic retinopathy grading system developed on mydriatic retinal images when applied to non-mydriatic community screening. J. Clin. Med. 11, 614 (2022).

Google Scholar 

Ruamviboonsuk, P. et al. Real-time diabetic retinopathy screening by deep learning in a multisite national screening programme: a prospective interventional cohort study. Lancet Digit. Health 4, e235–e244 (2022).

Google Scholar 

Skevas, C. et al. Simultaneous screening and classification of diabetic retinopathy and age-related macular degeneration based on fundus photos—a prospective analysis of the RetCAD system. Int. J. Ophthalmol. 15, 1985–1993 (2022).

Google Scholar 

Sedova, A. et al. Comparison of early diabetic retinopathy staging in asymptomatic patients between autonomous AI-based screening and human-graded ultra-widefield colour fundus images. Eye 36, 510–516 (2022).

Google Scholar 

Tsai, M.-J. et al. Cross-camera external validation for artificial intelligence software in diagnosis of diabetic retinopathy. J. Diab. Res. 2022, 5779276 (2022).

Google Scholar 

Yang, Y. et al. Performance of the AIDR Screening system in detecting diabetic retinopathy in the fundus photographs of Chinese patients: a prospective, multicenter, clinical study. Ann. Transl. Med. 10, 1088 (2022).

Google Scholar 

Bhuiyan et al. Combined automated screening for age-related macular degeneration and diabetic retinopathy in primary care settings. Ann. Eye Sci. 6, 12 (2021).

Google Scholar 

Grzybowski, A. & Brona, P. Analysis and comparison of two artificial intelligence diabetic retinopathy screening algorithms in a pilot study: IDx-DR and retinalyze. J. Clin. Med. 10, 2352 (2021).

Google Scholar 

Heydon, P. et al. Prospective evaluation of an artificial intelligence-enabled algorithm for automated diabetic retinopathy screening of 30 000 patients. Br. J. Ophthalmol. 105, 723–728 (2021).

Google Scholar 

Jain, A. et al. Use of offline artificial intelligence in a smartphone-based fundus camera for community screening of diabetic retinopathy. Indian J. Ophthalmol. 69, 3150–3154 (2021).

Google Scholar 

Kim, T. N. et al. Comparison of automated and expert human grading of diabetic retinopathy using smartphone-based retinal photography. Eye 35, 334–342 (2021).

Google Scholar 

Li, N. et al. A stratified analysis of a deep learning algorithm in the diagnosis of diabetic retinopathy in a real-world study. J. Diab. 14, 111–120 (2022).

Google Scholar 

Li, Y.-H. et al. The clinical influence after implementation of convolutional neural network-based software for diabetic retinopathy detection in the primary care setting. Life 11, 200 (2021).

Google Scholar 

Lin, D. et al. Application of Comprehensive Artificial intelligence Retinal Expert (CARE) system: a national real-world evidence study. Lancet Digit. health 3, e486–e495 (2021).

Google Scholar 

Ming, S. et al. Evaluation of a novel artificial intelligence-based screening system for diabetic retinopathy in community of China: a real-world study. Int. Ophthalmol. 41, 1291–1299 (2021).

Google Scholar 

Shah, A. et al. Validation of automated screening for referable diabetic retinopathy with an autonomous diagnostic artificial intelligence system in a Spanish population. J. Diab. Sci. Technol. 15, 655–663 (2021).

Google Scholar 

Wintergerst, M. W. M. et al. Telemedical Diabetic Retinopathy Screening in a Primary Care Setting: Quality of Retinal Photographs and Accuracy of Automated Image Analysis. Ophthalmic Epidemiol. 29, 286–295 (2022).

Google Scholar 

González-Gonzalo, C. et al. Evaluation of a deep learning system for the joint automated detection of diabetic retinopathy and age-related macular degeneration. Acta Ophthalmol. 98, 368–377 (2020).

Google Scholar 

He, J. et al. Artificial intelligence-based screening for diabetic retinopathy at community hospital. Eye 34, 572–576 (2020).

Google Scholar 

Hsieh, Y.-T. et al. Application of deep learning image assessment software VeriSee™ for diabetic retinopathy screening. J. Formos. Med. Assoc. = Taiwan yi zhi 120, 165–171 (2021).

Google Scholar 

Li, Z. X. et al. Zhonghua Yi Xue Za Zhi 100, 3835–3840 (2020).

Google Scholar 

Olvera-Barrios, A. et al. Diagnostic accuracy of diabetic retinopathy grading by an artificial intelligence-enabled algorithm compared with a human standard for wide-field true-colour confocal scanning and standard digital retinal images. Br. J. Ophthalmol. 105, 265–270 (2021).

Google Scholar 

Sarao, V. et al. Automated diabetic retinopathy detection with two different retinal imaging devices using artificial intelligence: a comparison study. Graefe’s. Arch. Clin. Exp. Ophthalmol. = Albrecht Graefes Arch. Klinische Exp. Ophthalmol. 258, 2647–2654 (2020).

Google Scholar 

Sosale, B. et al. Medios- An offline, smartphone-based artificial intelligence algorithm for the diagnosis of diabetic retinopathy. Indian J. Ophthalmol. 68, 391–395 (2020).

Google Scholar 

Sosale, B. et al. Simple, Mobile-based Artificial Intelligence Algorithm in the detection of Diabetic Retinopathy (SMART) study. BMJ Open Diab. Res. Care 8, e000892 (2020).

Google Scholar 

Zhang, Y. et al. Artificial intelligence-enabled screening for diabetic retinopathy: a real-world, multicenter and prospective study. BMJ Open Diab. Res. Care 8, e001596 (2020).

Google Scholar 

Gulshan, V. et al. Performance of a deep-learning algorithm vs manual grading for detecting diabetic retinopathy in India. JAMA Ophthalmol. 137, 987–993 (2019).

Google Scholar 

Natarajan, S. et al. Diagnostic accuracy of community-based diabetic retinopathy screening with an offline artificial intelligence system on a smartphone. JAMA Ophthalmol. 137, 1182–1188 (2019).

Google Scholar 

Quellec, G. et al. Instant Automatic Diagnosis of Diabetic Retinopathy (Cornell University, 2019).

Raumviboonsuk, P. et al. Deep learning versus human graders for classifying diabetic retinopathy severity in a nationwide screening program. NPJ Digit. Med. 2, 25 (2019).

Google Scholar 

Verbraak, F. D. et al. Diagnostic accuracy of a device for the automated detection of diabetic retinopathy in a primary care setting. Diab. Care 42, 651–656 (2019).

Google Scholar 

Krause, J. et al. Grader variability and the importance of reference standards for evaluating machine learning models for diabetic retinopathy. Ophthalmology 125, 1264–1272 (2018).

Google Scholar 

Rajalakshmi, R. et al. Automated diabetic retinopathy detection in smartphone-based fundus photography using artificial intelligence. Eye 32, 1138–1144 (2018).

Google Scholar 

van der Heijden, A. A. et al. Validation of automated screening for referable diabetic retinopathy with the IDx-DR device in the Hoorn Diabetes Care System. Acta Ophthalmol. 96, 63–68 (2018).

Google Scholar 

Tufail, A. et al. Automated diabetic retinopathy image assessment software: diagnostic accuracy and cost-effectiveness compared with human graders. Ophthalmology 124, 343–351 (2017).

Google Scholar 

Abràmoff, M. D. et al. Improved automated detection of diabetic retinopathy on a publicly available dataset through integration of deep learning. Investig. Ophthalmol. Vis. Sci. 57, 5200–5206 (2016).

Google Scholar 

Keel, S. et al. Feasibility and patient acceptability of a novel artificial intelligence-based screening model for diabetic retinopathy at endocrinology outpatient services: a pilot study. Sci. Rep. 8, 4330 (2018).

Google Scholar 

Higgins, J. P. T., Thompson, S. G., Deeks, J. J. & Altman, D. G. Measuring inconsistency in meta-analyses. BMJ 327, 557–560 (2003).

Google Scholar 

Rutter, C. M. & Gatsonis, C. A. A hierarchical regression approach to meta-analysis of diagnostic test accuracy evaluations. Stat. Med. 20, 2865–2884 (2001).

Google Scholar 

Macdonald, T. et al. Generating evidence to support the role of AI in diabetic eye screening: considerations from the UK National Screening Committee. Lancet Digit. Health S2589-750000271-1 (2025).

Li, Z. et al. Deep-learning-based detection of diabetic retinopathy: a systematic review and meta-analysis. PLoS One 16, e0250033 (2021).

Google Scholar 

Wolf, R. M. et al. Autonomous artificial intelligence increases screening and follow-up for diabetic retinopathy in youth: the ACCESS randomized control trial. Nat. Commun. 15, 421 (2024).

Centers for Medicare & Medicaid Services. HCPCS/CPT Code 92229 – Imaging of retina for detection or monitoring of disease; point-of-care automated analysis. Final Rule CY (2021).

Wang, T.W., Luo, W., Tu, Y. Chou, Y., & Wu, Y. (2025). Diagnostic accuracy of regulatory-approved deep-learning systems for fundus-based detection of diabetic retinopathy—a systematic review and meta-analysis. https://doi.org/10.37766/inplasy2025.5.0099.

McInnes, M. D. F. et al. Preferred reporting items for a systematic review and meta-analysis of diagnostic test accuracy studies: the PRISMA-DTA statement. JAMA 319, 388–396 (2018).

Google Scholar 

Moher, D., Liberati, A., Tetzlaff, J. & Altman, D. G. & PRISMA Group. Preferred reporting items for systematic reviews and meta-analyses: the PRISMA statement. BMJ 339, b2535 (2009).

Google Scholar 

World Bank. World Bank country classifications by income level for 2024–2025. World Bank Blogs. https://blogs.worldbank.org/opendata/world-bank-country-classifications-by-income-level-for-2024-2025.

Whiting, P. F. et al. QUADAS-2 Group. QUADAS-2: a revised tool for the quality assessment of diagnostic accuracy studies. Ann. Intern. Med. 155, 529–36 (2011).

Google Scholar 

International Council of Ophthalmology (ICO). ICO Guidelines for Diabetic Eye Care. Updated 2017.

Deeks, J. J., Macaskill, P. & Irwig, L. The performance of tests of publication bias and other sample size effects in systematic reviews of diagnostic test accuracy was assessed. J. Clin. Epidemiol. 58, 882–893 (2005).

Google Scholar