A Comparison of Artificial Intelligence and Human Diabetic Retinal Image Interpretation in an Urban Health System
Open accessAbstract
Introduction Artificial intelligence (AI) diabetic retinopathy (DR) software has the potential to decrease time spent by clinicians on image interpretation and expand the scope of DR screening. We performed a retrospective review to compare Eyenuk's EyeArt software (Woodland Hills, CA) to Temple Ophthalmology optometry grading using the International Classification of Diabetic Retinopathy scale. Methods Two hundred and sixty consecutive diabetic patients from the Temple Faculty Practice Internal Medicine clinic underwent 2-field retinal imaging. Classifications of the images by the software and optometrist were analyzed using sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and McNemar's test. Ungradable images were analyzed to identify relationships with HbA1c, age, and ethnicity. Disagreements and a sample of 20% of agreements were adjudicated by a retina specialist. Results On patient level comparison, sensitivity for the software was 100%, while specificity was 77.78%. PPV was 19.15%, and NPV was 100%. The 38 disagreements between software and optometrist occurred when the optometrist classified a patient's images as non-referable while the software classified them as referable. Of these disagreements, a retina specialist agreed with the optometrist 57.9% the time (22/38). Of the agreements, the retina specialist agreed with both the program and the optometrist 96.7% of the time (28/29). There was a significant difference in numb…
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?
Eyenuk offers a "spellcheck"-like, assistive-AI function for ophthalmologists who read retinal images for other diseases such as glaucoma and age-related macular degeneration, which are not currently FDA-cleared for autonomous diagnosis.
“Of note, they also offer a “spellcheck”-like, assistive-AI function for ophthalmologists who read these images for other diseases such as glaucoma and age-related macular degeneration, which are not currently FDA-cleared for autonomous diagnosis.”
From Autonomous Artificial Intelligence in Diabetic Retinopathy Testing—Lessons Learned on Successful Health System Adoption (2026) · cites this paper as [27]
Artificial intelligence algorithms have demonstrated a high sensitivity of 95% to 100% in clinical implementation, whereas specificity is relatively lower and with greater variation at 60% to 90%.
“Artificial intelligence algorithms have demonstrated a high sensitivity of 95% to 100% in clinical implementation, whereas specificity is relatively lower and with greater variation at 60% to 90%.38,40,41,46”
From Autonomous Artificial Intelligence in Diabetic Retinopathy Testing—Lessons Learned on Successful Health System Adoption (2026) · cites this paper as [41]
No citation lists for this paper
No citation lists for this paper yet — checked again daily.
References 11 · Cited by 23
- Authors
- Mokhashi, N., Grachevskaya, J., Cheng, L., Yu, D., Lu, X., Zhang, Y., & Henderer, J. D.
- Affiliations
- University of Pennsylvania (US)
- Corresponding author
- Mokhashi, Nikita
- Venue
- Journal of Diabetes Science and Technology
- Publisher
- SAGE Publications
- Published
- 2021-03-10
- Volume
- 16
- Issue
- 4
- Pages
- 1003-1007
- ISSN
- 1932-2968 (ISSN-L)
- PMC
- PMC9264425
- OpenAlex
- W3133683246
- Cited by
- 23
- References
- 11
- Citations by year
- 2026: 6 · 2025: 8 · 2024: 6 · 2023: 3
- FWCI
- 1.19
- Type
- journal article
- Language
- en
- Open access
- green
- www.ncbi.nlm.nih.gov
- Locations
- Journal of Diabetes Science and Technology (publishedVersion)
- PubMed Central (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Retinal Imaging and Analysis
- Health Sciences › Medicine › Ophthalmology › Retinal Diseases and Treatments
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Keywords
- diabetic retinopathy, artificial intelligence, diabetic retinopathy screening, diagnostic accuracy, unnecessary referrals
- MeSH terms
- Aged, Artificial Intelligence, Diabetes Mellitus, Diabetic Retinopathy, Humans, Mass Screening, Photography, Retina, Sensitivity and Specificity, Urban Health
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
