Artificial Intelligence Detection of Diabetic Retinopathy
Open accessAbstract
Objective: To compare general ophthalmologists, retina specialists, and the EyeArt Artificial Intelligence (AI) system to the clinical reference standard for detecting more than mild diabetic retinopathy (mtmDR). Design: Prospective, pivotal, multicenter trial conducted from April 2017 to May 2018. Participants: Participants were aged ≥ 18 years who had diabetes mellitus and underwent dilated ophthalmoscopy. A total of 521 of 893 participants met these criteria and completed the study protocol. Testing: Participants underwent 2-field fundus photography (macula centered, disc centered) for the EyeArt system, dilated ophthalmoscopy, and 4-widefield stereoscopic dilated fundus photography for reference standard grading. Main Outcome Measures: For mtmDR detection, sensitivity and specificity of EyeArt gradings of 2-field, fundus photographs and ophthalmoscopy grading versus a rigorous clinical reference standard comprising Reading Center grading of 4-widefield stereoscopic dilated fundus photographs using the ETDRS severity scale. The AI system provided automatic eye-level results regarding mtmDR. Results: Overall, 521 participants (999 eyes) at 10 centers underwent dilated ophthalmoscopy: 406 by nonretina and 115 by retina specialists. Reading Center graded 207 positive and 792 eyes negative for mtmDR. Of these 999 eyes, 26 eyes were ungradable by the EyeArt system, leaving 973 eyes with both EyeArt and Reading Center gradings. Retina specialists correctly identified 22 of 37 eyes as positive (sensitivity 59.5%) and 182 of 184 eyes as negative (specificity 98.9%) for mtmDR versus the EyeArt AI system that identified 36 of 37 as positive (sensitivity 97%) and 162 of 184 eyes as negative (specificity of 88%) for mtmDR. General ophthalmologists correctly identified 35 of 170 eyes as positive (sensitivity 20.6%) and 607 of 608 eyes as negative (specificity 99.8%) for mtmDR compared with the EyeArt AI system that identified 164 of 170 as positive (sensitivity 96.5%) and 525 of 608 eyes as negative (specificity 86%) for mtmDR. Conclusions: The AI system had a higher sensitivity for detecting mtmDR than either general ophthalmologists or retina specialists compared with the clinical reference standard. It can potentially serve as a low-cost point-of-care diabetic retinopathy detection tool and help address the diabetic eye screening burden.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
After rigorous validation on safety and efficacy, autonomous AI-enabled DR detection could be more sensitive than examinations by retinal specialists.
“After rigorous validation on safety and efficacy, it was also shown that autonomous AI-enabled DR detection could be more sensitive than examinations by retinal specialists25”
From Autonomous AI-assisted diabetic retinopathy screening at primary care is associated with increased presentation to eye care by at risk patients (2026) · cites this paper as [25]
The Discussion reports that EyeArt was more sensitive than retina specialists for detecting more-than-mild diabetic retinopathy against a photographic reference standard. The paper describes a prospective pivotal trial and FDA clearance, but the cited passages do not establish the claimed rigorous validation of safety; the sensitivity finding is also specific to more-than-mild disease. (LLM, conf=0.85)
Experimental — accuracy not yet measuredThe autonomous AI screening strategy has high sensitivity and good specificity for the detection of referrable diabetic retinopathy compared with the traditional ophthalmologist approach.
“Our study, the first based in Canada, demonstrates a screening strategy using autonomous AI that has a high sensitivity and good specificity for the detection of referrable DR,27 compared with the traditional ophthalmologist approach, and is shown to result in lower cost per case diagnosis.”
From Screening for diabetic retinopathy with artificial intelligence in a primary care setting: a comparative cost analysis (2026) · cites this paper as [27]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Ipp, E., Liljenquist, D., Bode, B., Shah, V. N., Silverstein, S., Regillo, C. D., Lim, J. I., Sadda, S., Domalpally, A., Gray, G., et al. (2021) · JAMA Network Open · doi:10.1001/jamanetworkopen.2021.34254 · Cited by 256 · see citing works
Self-citationBhaskaranand, M., Ramachandra, C., Bhat, S., Cuadros, J., Nittala, M. G., Sadda, S. R., & Solanki, K. (2019) · Diabetes Technology & Therapeutics · doi:10.1089/dia.2019.0164 · Cited by 211 · see citing works
Self-citationLiu, J., Gibson, E., Ramchal, S., Shankar, V., Piggott, K., Sychev, Y., Li, A. S., Rao, P. K., Margolis, T. P., Fondahn, E., et al. (2021) · Ophthalmology Retina · doi:10.1016/j.oret.2020.06.016 · Cited by 88 · see citing works
Self-citation
Flagged first, then by citations
Research works printed but not linked: 10
- [1]International Diabetes Federation IDF Diabetes Atlas 9th ed. 2019 International Diabetes Federation https://diabetesatlas.org/atlas/ninth-edition/
- [2]Peek M.E. Cargill A. Huang E.S. Diabetes health disparities: a systematic review of health care interventions Med Care Res Rev 64 suppl 5 2007 101S 156S 17881626 PMC2367214
- [4]Early Treatment Diabetic Retinopathy Study (ETDRS) Research Group Fundus photographic risk factors for progression of diabetic retinopathy: ETDRS report number 12 Ophthalmology 98 suppl 5 1991 823 833 2062515
- [5]Flaxel C.J. Adelman R.A. Bailey S.T. Diabetic retinopathy preferred practice pattern Ophthalmology 127 2020 P66 P145 31757498
- [6]The Diabetic Retinopathy Study Research Group Four risk factors for severe visual loss in diabetic retinopathy. The third report from the diabetic retinopathy study Arch Ophthalmol 97 1979 654 655 426679
- [7]Abràmoff M.D. Lavin P.T. Birch M. Pivotal trial of an autonomous AI-based diagnostic system for detection of diabetic retinopathy in primary care offices npj Digit Med 1 2018 39 31304320 PMC6550188
- [10]Early Treatment Diabetic Retinopathy Study Research Group Grading diabetic retinopathy from stereoscopic color fundus photographs - an extension of the modified Airlie House classification. ETDRS report number 10 Ophthalmology 98 suppl 5 1991 786 806 2062513
- [11]Scanlon P.H. Malhotra R. Greenwood R.H. Comparison of two reference standards in validating two field mydriatic digital photography as a method of screening for diabetic retinopathy Br J Ophthalmol 87 2003 1258 1263 14507762 PMC1920793
- [12]Heydon P. Egan C. Bolter L. Prospective evaluation of an artificial intelligence-enabled algorithm for automated diabetic retinopathy screening of 30 000 patients Br J Ophthalmol 105 2021 723 728 32606081 PMC8077216
- [14]Gangaputra S. Almukhtar T. Glassman A.R. Comparison of film and digital fundus photographs in eyes of individuals with diabetes mellitus Invest Ophthalmol Vis Sci 52 2011 6168 6173 21571677 PMC3176025
Cited by
Sorted by citations
Diaz, E. A., Seifert, M. L., Gruning, V., Stadnick, N. A., Lugo-Butler, E., Servin, A. N., Rodríguez-Rosales, C. I., Geremia, C., Ramachandra, C., Bhaskaranand, M., et al. (2025) · JAMA Network Open · doi:10.1001/jamanetworkopen.2025.38114 · Cited by 9 · see citing works
Self-citationLeong, A., Wolf, R. M., Channa, R., Wang, J., Lehmann, H., Abramoff, M. D., & Liu, T. Y. A. (2026) · npj Digital Medicine · doi:10.1038/s41746-026-02460-5 · Cited by 3 · see citing works
Di Matteo, L., Whitestone, N., & Bhambhwani, V. (2026) · BMJ Open Ophthalmology · doi:10.1136/bmjophth-2026-002904
“16 Our study, the first based in Canada, demonstrates a screening strategy using autonomous AI that has a high sensitivity and good specificity for the detection of referrable DR, 27 compared with the traditional ophthal-mologist approach, and is shown to result in lower cost per case diagnosis.”
- Authors
- Lim, J. I., Regillo, C. D., Sadda, S. R., Ipp, E., Bhaskaranand, M., Ramachandra, C., Solanki, K., Dubiner, H., Levy-Clarke, G., Pesavento, R., Sherman, M. D., Silverstein, S., Kim, B., Walman, G. B., Blodi, B. A., Domalpally, A., Reed, S., Reimers, J., Lang, K., Cohn, H., Shaw, R., Watson, S., Ewen, A., Barrett, N., Swift, M., & Gornbein, J.
- Affiliations
- University of Illinois Chicago (US)
- Thomas Jefferson University (US)
- University of California, Los Angeles (US)
- Eyenuk (United States) (US)
- Corresponding author
- Lim, Jennifer Irene
- ORCID
- Venue
- Ophthalmology Science
- Publisher
- Elsevier BV
- Published
- 2023-03
- Volume
- 3
- Issue
- 1
- Pages
- 100228
- ISSN
- 2666-9145 (ISSN-L)
- PMC
- PMC9636573
- OpenAlex
- W4298111920
- Cited by
- 157
- References
- 3
- Citations by year
- 2026: 42 · 2025: 55 · 2024: 42 · 2023: 18
- FWCI
- 16.35
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Ophthalmology Science (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Merck
- Novartis
- National Institutes of Health (2R44EY026864, 9SB1EY027241, EY01792)
- Research to Prevent Blindness
- 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, artificial intelligence, diabetic retinopathy detection, fundus photography, retina specialists, diagnostic accuracy, sensitivity and specificity, diabetes mellitus, stereoscopic fundus photography, automated grading, diabetic macular edema, diabetic retinopathy progression
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
