Predicting 1, 2 and 3 year emergent referable diabetic retinopathy and maculopathy using deep learning
Open accessAbstract
BACKGROUND: Predicting diabetic retinopathy (DR) progression could enable individualised screening with prompt referral for high-risk individuals for sight-saving treatment, whilst reducing screening burden for low-risk individuals. We developed and validated deep learning systems (DLS) that predict 1, 2 and 3 year emergent referable DR and maculopathy using risk factor characteristics (tabular DLS), colour fundal photographs (image DLS) or both (multimodal DLS). METHODS: From 162,339 development-set eyes from south-east London (UK) diabetic eye screening programme (DESP), 110,837 had eligible longitudinal data, with the remaining 51,502 used for pretraining. Internal and external (Birmingham DESP, UK) test datasets included 27,996, and 6928 eyes respectively. RESULTS: Internal multimodal DLS emergent referable DR, maculopathy or either area-under-the receiver operating characteristic (AUROC) were 0.95 (95% CI: 0.92-0.98), 0.84 (0.82-0.86), 0.85 (0.83-0.87) for 1 year, 0.92 (0.87-0.96), 0.84 (0.82-0.87), 0.85 (0.82-0.87) for 2 years, and 0.85 (0.80-0.90), 0.79 (0.76-0.82), 0.79 (0.76-0.82) for 3 years. External multimodal DLS emergent referable DR, maculopathy or either AUROC were 0.93 (0.88-0.97), 0.85 (0.80-0.89), 0.85 (0.76-0.85) for 1 year, 0.93 (0.89-0.97), 0.79 (0.74-0.84), 0.80 (0.76-0.85) for 2 years, and 0.91 (0.84-0.98), 0.79 (0.74-0.83), 0.79 (0.74-0.84) for 3 years. CONCLUSIONS: Multimodal and image DLS performance is significantly better than tabular DLS at all intervals. DLS accurately predict 1, 2 and 3 year emergent referable DR and referable maculopathy using colour fundal photographs, with additional risk factor characteristics conferring improvements in prognostic performance. Proposed DLS are a step towards individualised risk-based screening, whereby AI-assistance allows high-risk individuals to be closely monitored while reducing screening burden for low-risk individuals.
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.
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
Saeedi, P., Petersohn, I., Salpea, P., Malanda, B., Karuranga, S., Unwin, N., Colagiuri, S., Guariguata, L., Motala, A. A., Ogurtsova, K., et al. (2019) · Diabetes Research and Clinical Practice · doi:10.1016/j.diabres.2019.107843 · Cited by 10,792 · see citing works
Steinmetz, J. D., Bourne, R. R. A., Briant, P. S., Flaxman, S. R., Taylor, H. R. B., Jonas, J. B., Abdoli, A. A., Abrha, W. A., Abualhasan, A., Abu-Gharbieh, E. G., et al. (2021) · The Lancet Global Health · doi:10.1016/s2214-109x(20)30489-7 · Cited by 3,189 · see citing works
EfficientNetV2: Smaller Models and Faster TrainingPreprint
Tan, M., & Le, Q. V. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.00298 · Cited by 1,473 · see citing works
Ting, D. S. W., Cheung, G. C. M., & Wong, T. Y. (2016) · Clinical & Experimental Ophthalmology · doi:10.1111/ceo.12696 · Cited by 1,066 · see citing works
A foundation model for generalizable disease detection from retinal images
Zhou, Y., Chia, M. A., Wagner, S. K., Ayhan, M. S., Williamson, D. J., Struyven, R. R., Liu, T., Xu, M., Lozano, M. G., Woodward-Court, P., et al. (2023) · Nature · doi:10.1038/s41586-023-06555-x · Cited by 1,014 · see citing works
Photocoagulation Treatment of Proliferative Diabetic Retinopathy
The Diabetic Retinopathy Study Research Group (1981) · Ophthalmology · doi:10.1016/s0161-6420(81)34978-1 · Cited by 981 · 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
A deep learning system for predicting time to progression of diabetic retinopathy
Dai, L., Sheng, B., Chen, T., Wu, Q., Liu, R., Cai, C., Wu, L., Yang, D., Hamzah, H., Liu, Y., et al. (2024) · Nature Medicine · doi:10.1038/s41591-023-02702-z · Cited by 339 · see citing works
Zhang, K., Liu, X., Xu, J., Yuan, J., Cai, W., Chen, T., Wang, K., Gao, Y., Nie, S., Xu, X., et al. (2021) · Nature Biomedical Engineering · doi:10.1038/s41551-021-00745-6 · Cited by 324 · see citing works
Predicting the risk of developing diabetic retinopathy using deep learning
Bora, A., Balasubramanian, S., Babenko, B., Virmani, S., Venugopalan, S., Mitani, A., de Oliveira Marinho, G., Cuadros, J., Ruamviboonsuk, P., Corrado, G. S., et al. (2021) · The Lancet Digital Health · doi:10.1016/s2589-7500(20)30250-8 · Cited by 270 · see citing works
The Relation of Retinal Vessel Caliber to the Incidence and Progressionof Diabetic Retinopathy
Klein, R. (2004) · Archives of Ophthalmology · doi:10.1001/archopht.122.1.76 · Cited by 235 · see citing works
Heydon, P., Egan, C. A., Bolter, L., Chambers, R., Anderson, J., Aldington, S. J., STRATTON, I. M., Scanlon, P. H., Webster, L., Mann, S. S., et al. (2020) · British Journal of Ophthalmology · doi:10.1136/bjophthalmol-2020-316594 · Cited by 183 · see citing works
Self-citationAspelund, T., Þórisdóttir, Ó., Ólafsdóttir, E. S., Guðmundsdóttir, A., Einarsdottir, A. B., Mehlsen, J., Einarsson, S., Palsson, O. S., Einarsson, G., Bek, T., et al. (2011) · Diabetologia · doi:10.1007/s00125-011-2257-7 · Cited by 168 · see citing works
Diabetic Retinopathy Screening: A Systematic Review on Patients’ Non-Attendance
Kashim, R., Newton, P., & Ojo, O. (2018) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph15010157 · Cited by 128 · see citing works
Lund, S. H., Aspelund, T., Kirby, P., Russell, G., Einarsson, S., Palsson, O., & Stefánsson, E. (2016) · British Journal of Ophthalmology · doi:10.1136/bjophthalmol-2015-307341 · Cited by 84 · see citing works
Extending the diabetic retinopathy screening interval beyond 1 year: systematic review
Taylor‐Phillips, S., Mistry, H., Leslie, R., Todkill, D., Tsertsvadze, A., Connock, M. J., & Clarke, A. (2015) · British Journal of Ophthalmology · doi:10.1136/bjophthalmol-2014-305938 · Cited by 83 · see citing works
A Simple Risk Stratification for Time to Development of Sight-Threatening Diabetic Retinopathy
STRATTON, I. M., Aldington, S. J., Taylor, D. J., et al. (2012) · Diabetes Care · doi:10.2337/dc12-0625 · Cited by 83 · see citing works
Scanlon, P. H. (2021) · Acta Diabetologica · doi:10.1007/s00592-021-01687-w · Cited by 67 · see citing works
Leese, G. P., Stratton, I. M., Land, M., Bachmann, M. O., Jones, C., Scanlon, P., Looker, H. C., & Ferguson, B. (2015) · Diabetes Care · doi:10.2337/dc14-1778 · Cited by 50 · see citing works
the ISDR Study Group, Broadbent, D., Wang, A., Cheyne, C. P., James, M., Lathe, J., STRATTON, I. M., Roberts, J., Moitt, T., Vora, J. P., et al. (2020) · Diabetologia · doi:10.1007/s00125-020-05313-2 · Cited by 42 · see citing works
for the Individualised Screening for Diabetic Retinopathy (ISDR) Study Group, Eleuteri, A., Fisher, A. C., Broadbent, D., García‐Fiñana, M., Cheyne, C. P., Wang, A., STRATTON, I. M., Gabbay, M., Seddon, D., et al. (2017) · Diabetologia · doi:10.1007/s00125-017-4386-0 · Cited by 38 · see citing works
Thomas, R., Luzio, S. D., North, R. V., Banerjee, S., Zekite, A., Bunce, C., & Owens, D. R. (2017) · BMJ Open · doi:10.1136/bmjopen-2016-015024 · Cited by 37 · see citing works
Rom, Y., Aviv, R., Ianchulev, T., & Dvey-Aharon, Z. (2022) · BMJ Open Ophthalmology · doi:10.1136/bmjophth-2022-001140 · Cited by 34 · see citing works
Prognostic models of diabetic microvascular complications: a systematic review and meta-analysis
Saputro, S. A., Pattanaprateep, O., Pattanateepapon, A., Karmacharya, S., & Thakkinstian, A. (2021) · Systematic Reviews · doi:10.1186/s13643-021-01841-z · Cited by 33 · see citing works
Prognostic prediction models for diabetic retinopathy progression: a systematic review
Haider, S., Sadiq, S. N., Moore, D., Price, M. J., & Nirantharakumar, K. (2019) · Eye · doi:10.1038/s41433-018-0322-x · Cited by 31 · see citing works
García‐Fiñana, M., Hughes, D. M., Cheyne, C. P., Broadbent, D., Wang, A., Komárek, A., STRATTON, I. M., Mobayen‐Rahni, M., Alshukri, A., Vora, J. P., et al. (2018) · Diabetes Obesity and Metabolism · doi:10.1111/dom.13552 · Cited by 29 · see citing works
Oke, J. L., STRATTON, I. M., Aldington, S. J., et al. (2015) · Diabetic Medicine · doi:10.1111/dme.13053 · Cited by 20 · see citing works
Automated image curation in diabetic retinopathy screening using deep learning
Nderitu, P., do Rio, J. M. N., Webster, M. L., Mann, S. S., Hopkins, D., Cardoso, M. J., Marc Modat, A., Bergeles, C., & Jackson, T. L. (2022) · Scientific Reports · doi:10.1038/s41598-022-15491-1 · Cited by 19 · see citing works
Self-citationArcadu, F., Benmansour, F., Maunz, A., et al. (2020) · npj Digital Medicine · doi:10.1038/s41746-020-00365-5 · Cited by 18 · see citing works
Sharif, A., JENDLE, J. H., & Hellgren, K. (2020) · Diabetes Therapy · doi:10.1007/s13300-020-00957-0 · Cited by 15 · see citing works
Olvera‐Barrios, A., Rudnicka, A. R., Anderson, J., Bolter, L., Chambers, R., Warwick, A., Welikala, R. A., Fajtl, J., Barman, S. A., Remgnino, P., et al. (2023) · British Journal of Ophthalmology · doi:10.1136/bjo-2023-324097 · Cited by 11 · see citing works
Haider, S., Sadiq, S. N., Lufumpa, E., Sihre, H. K., Tallouzi, M., Moore, D., Nirantharakumar, K., & Price, M. J. (2020) · BMJ Open Ophthalmology · doi:10.1136/bmjophth-2020-000579 · Cited by 10 · see citing works
Byrne, P., Thetford, C., Gabbay, M., Clarke, P. M., Doncaster, E., Harding, S. P., for the ISDR Study Group, Harding, S. P., Broadbent, D., Byrne, P., et al. (2020) · BMC Public Health · doi:10.1186/s12889-020-08974-1 · Cited by 8 · see citing works
Flagged first, then by citations
Research works printed but not linked: 2
- [29]Arik, S. O. & Pfister, T. TabNet: attentive interpretable tabular learning. arXiv:1908.07442. https://ui.adsabs.harvard.edu/abs/2019arXiv190807442A (2019). · arXiv
- [37]Nderitu, P. Github Code Respository: Automated Image Curation in Diabetic Retinopathy Screening using Deep Learning, https://github.com/pnderitu/DUK_Automated_Curation (2022). PMC9249740 35778615
Cited by
Sorted by citations
Schouten, D., Nicoletti, G., Dille, B., Chia, C., Vendittelli, P., Schuurmans, M., Litjens, G., & Khalili, N. (2025) · Medical Image Analysis · doi:10.1016/j.media.2025.103621 · Cited by 108 · see citing works
- Authors
- Nderitu, P., Nunez do Rio, J. M., Webster, L., Mann, S., Cardoso, M. J., Modat, M., Hopkins, D., Bergeles, C., & Jackson, T. L.
- Affiliations
- King's College London (GB)
- St Thomas' Hospital (GB)
- Kings Health Partners (GB)
- Corresponding author
- Nderitu, Paul
- ORCID
- Venue
- Communications Medicine
- Published
- 2024-08-21
- Volume
- 4
- Issue
- 1
- Pages
- 167-167
- ISSN
- 2730-664X (ISSN-L)
- PMC
- PMC11339445
- OpenAlex
- W4401793494
- Cited by
- 16
- References
- 34
- Citations by year
- 2026: 10 · 2025: 6
- FWCI
- 4.06
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- Communications Medicine (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Research Portal (King's College London) (publishedVersion, other-oa)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- Research Portal (King's College London) (submittedVersion, cc-by)
- Funders
- Wellcome Trust
- Diabetes UK (20/0006144)
- King's College London (WT203148/Z/16/Z)
- Engineering and Physical Sciences Research Council ([WT203148/Z/16/Z], WT 203148/Z/16/, 203148/ Z/16/Z)
- Topics
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Retinal Imaging and Analysis
- Health Sciences › Medicine › Ophthalmology › Retinal Diseases and Treatments
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- diabetic retinopathy, diabetic maculopathy, disease progression prediction, deep learning, multimodal prediction, diabetic retinopathy screening, external validation, retinal thickness, retinal thickness changes, retinal blood flow, retinal vessel density, retinal vessel diameter, retinal vessel tortuosity
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
