Cross-Camera External Validation for Artificial Intelligence Software in Diagnosis of Diabetic Retinopathy
Open accessAbstract
Aims. To investigate the applicability of deep learning image assessment software VeriSee DR to different color fundus cameras for the screening of diabetic retinopathy (DR). Methods. Color fundus images of diabetes patients taken with three different nonmydriatic fundus cameras, including 477 Topcon TRC-NW400, 459 Topcon TRC-NW8 series, and 471 Kowa nonmyd 8 series that were judged as “gradable” by one ophthalmologist were enrolled for validation. VeriSee DR was then used for the diagnosis of referable DR according to the International Clinical Diabetic Retinopathy Disease Severity Scale. Gradability, sensitivity, and specificity were calculated for each camera model. Results. All images (100%) from the three camera models were gradable for VeriSee DR. The sensitivity for diagnosing referable DR in the TRC-NW400, TRC-NW8, and non-myd 8 series was 89.3%, 94.6%, and 95.7%, respectively, while the specificity was 94.2%, 90.4%, and 89.3%, respectively. Neither the sensitivity nor the specificity differed significantly between these camera models and the original camera model used for VeriSee DR development ( p = 0.40 , p = 0.065 , respectively). Conclusions. VeriSee DR was applicable to a variety of color fundus cameras with 100% agreement with ophthalmologists in terms of gradability and good sensitivity and specificity for the diagnosis of referable DR.
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?
AI-enabled screening can reproduce or worsen inequity if devices are unavailable, internet connectivity is weak, staff are inadequately trained, costs are shifted to patients, or algorithms perform differently across populations and camera systems.
“However, the same technology can reproduce or worsen inequity if devices are unavailable, internet connectivity is weak, staff are inadequately trained, costs are shifted to patients, or algorithms perform differently across populations and camera systems (10,(31)(32)(33).”
From From validation to public health impact: implementing equitable AI-enabled diabetic retinopathy screening (2026) · cites this paper as [32]
The Introduction says real-world performance may be less satisfactory because images differ across racial groups and fundus cameras; the Discussion calls for cross-camera validation. The paper does not address weak internet connectivity, inadequate staff training, device unavailability, or costs shifted to patients, so it supports only the population-and-camera portion of the inequity claim. (LLM, conf=0.88)
Experimental — accuracy not yet measured
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
Abràmoff, M. D., Lou, Y., Erginay, A., Clarida, W., Amelon, R., Folk, J. C., & Niemeijer, M. (2016) · Investigative Opthalmology & Visual Science · doi:10.1167/iovs.16-19964 · Cited by 1,101 · see citing works
Verbraak, 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
Flagged first, then by citations
Research works printed but not linked: 15
- [1]Yau J. W. Rogers S. L. Kawasaki R. Global prevalence and major risk factors of diabetic retinopathy Diabetes Care 2012 35 3 556 564 10.2337/dc11-1909 2-s2.0-84859030420 22301125 PMC3322721 · DOI · Paper page
- [2]Sabanayagam C. Yip W. Ting D. S. Tan G. Wong T. Y. Ten emerging trends in the epidemiology of diabetic retinopathy Ophthalmic Epidemiology 2016 23 4 209 222 10.1080/09286586.2016.1193618 2-s2.0-84976370547 27355693 · DOI
- [3]Ting D. S. Cheung G. C. Wong T. Y. Diabetic retinopathy: global prevalence, major risk factors, screening practices and public health challenges: a review Clinical & Experimental Ophthalmology 2016 44 4 260 277 10.1111/ceo.12696 2-s2.0-84974782886 26716602 · DOI · Paper page
- [4]Tufail A. Rudisill C. Egan C. Automated diabetic retinopathy image assessment software: diagnostic accuracy and cost-effectiveness compared with human graders Ophthalmology 2017 124 3 343 351 10.1016/j.ophtha.2016.11.014 2-s2.0-85009255599 28024825 · DOI · Paper page
- [5]Abràmoff M. D. Folk J. C. Han D. P. Automated analysis of retinal images for detection of referable diabetic retinopathy JAMA Ophthalmology 2013 131 3 351 357 10.1001/jamaophthalmol.2013.1743 2-s2.0-84875180389 23494039 · DOI
- [6]Ting D. S. W. Pasquale L. R. Peng L. Artificial intelligence and deep learning in ophthalmology The British Journal of Ophthalmology. 2019 103 2 167 175 10.1136/bjophthalmol-2018-313173 2-s2.0-85055474664 30361278 PMC6362807 · DOI · Paper page
- [8]Gulshan V. Peng L. Coram M. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs JAMA 2016 316 22 2402 2410 10.1001/jama.2016.17216 2-s2.0-85007529863 27898976 · DOI · Paper page
- [9]Gargeya R. Leng T. Automated identification of diabetic retinopathy using deep learning Ophthalmology 2017 124 7 962 969 10.1016/j.ophtha.2017.02.008 2-s2.0-85016221341 28359545 · DOI
- [10]Ting D. S. W. Cheung C. Y. Lim G. Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes JAMA 2017 318 22 2211 2223 10.1001/jama.2017.18152 2-s2.0-85038438910 29234807 PMC5820739 · DOI · Paper page
- [11]van der Heijden A. A. Abramoff M. D. Verbraak F. van Hecke M. V. Liem A. Nijpels G. Validation of automated screening for referable diabetic retinopathy with the IDx-DR device in the Hoorn diabetes care system Acta Ophthalmologica 2018 96 1 63 68 10.1111/aos.13613 2-s2.0-85035203265 29178249 PMC5814834 · DOI · Paper page
- [13]Ting D. S. W. Peng L. Varadarajan A. V. Deep learning in ophthalmology: the technical and clinical considerations Progress in Retinal and Eye Research 2019 72 p. 100759 10.1016/j.preteyeres.2019.04.003 2-s2.0-85065560866 31048019 · DOI
- [14]Hsieh Y. T. Chuang L. M. Jiang Y. D. Application of deep learning image assessment software VeriSee™ for diabetic retinopathy screening Journal of the Formosan Medical Association 2021 120 1 165 171 10.1016/j.jfma.2020.03.024 32307321 · DOI
- [15]Wilkinson C. P. Ferris F. L. 3rd Klein R. E. Proposed international clinical diabetic retinopathy and diabetic macular edema disease severity scales Ophthalmology 2003 110 9 1677 1682 10.1016/s0161-6420(03)00475-5 2-s2.0-0042932653 13129861 · DOI
- [16]Zhong Z. Zheng L. Zheng Z. Li S. Yang Y. Camera style adaptation for person re-identification 2017 http://arxiv.org/abs/1711.10295 · arXiv
- [17]Nielsen K. B. Lautrup M. L. Andersen J. K. H. Savarimuthu T. R. Grauslund J. Deep learning-based algorithms in screening of diabetic retinopathy: a systematic review of diagnostic performance Ophthalmology Retina 2019 3 4 294 304 10.1016/j.oret.2018.10.014 2-s2.0-85070435289 31014679 · DOI
Cited by
Sorted by citations
Chen, J., & Chen, B. (2026) · Frontiers in Public Health · doi:10.3389/fpubh.2026.1976572
- Authors
- Tsai, M.-J., Hsieh, Y.-T., Tsai, C.-H., Chen, M., Hsieh, A.-T., Tsai, C.-W., & Chen, M.-L.
- Affiliations
- Tao Yuan General Hospital (TW)
- National Taiwan University Hospital (TW)
- Acer (Taiwan) (TW)
- National Defense Medical Center (TW)
- Chen Min Ling Medical Clinic, New Taipei, Taiwan
- Corresponding author
- Hsieh, Yi-Ting
- Venue
- Journal of Diabetes Research
- Publisher
- Wiley
- Published
- 2022-03-09
- Volume
- 2022
- Pages
- 1-5
- ISSN
- 2314-6745 (ISSN-L)
- 2314-6753
- PMC
- PMC8926465
- OpenAlex
- W4221036446
- Cited by
- 18
- References
- 2
- Citations by year
- 2026: 6 · 2025: 4 · 2024: 4 · 2023: 3 · 2022: 1
- FWCI
- 1.71
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- Journal of Diabetes Research (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- 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, referable diabetic retinopathy, automated diagnosis, sensitivity and specificity, non-mydriatic fundus photography
- MeSH terms
- Adult, Artificial Intelligence, Diabetes Mellitus, Diabetic Retinopathy, Female, Humans, Male, Middle Aged, Software Design, Reproducibility of Results, Chi-Square Distribution, Ophthalmoscopes
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
