Investigative Ophthalmology & Visual Science Cover Image for Volume 65, Issue 7
June 2024
Volume 65, Issue 7
Open Access
ARVO Annual Meeting Abstract  |   June 2024
Validation of deep learning systems for predicting 1, 2 and 3 year emergent referable diabetic retinopathy and maculopathy
Author Affiliations & Notes
  • Paul Nderitu
    Section of Ophthalmology, King’s College London, London, United Kingdom
    King's Ophthalmology Research Unit, King’s College Hospital, London, United Kingdom
  • Joan M Nunez do Rio
    Section of Ophthalmology, King’s College London, London, United Kingdom
  • Laura Webster
    South East London Diabetic Eye Screening Programme, Guy’s and St Thomas’ NHS Foundation Trust, London, United Kingdom
  • Samantha Mann
    South East London Diabetic Eye Screening Programme, Guy’s and St Thomas’ NHS Foundation Trust, London, United Kingdom
    Department of Ophthalmology, Guy’s and St Thomas’ NHS Foundation Trust, London, United Kingdom
  • David Hopkins
    Department of Diabetes, King's College London, London, United Kingdom
    Institute of Diabetes, Endocrinology and Obesity, King's Health Partners, London, United Kingdom
  • M. Jorge Cardoso
    School of Biomedical Engineering & Imaging Sciences, King’s College London, London, United Kingdom
  • Marc Modat
    School of Biomedical Engineering & Imaging Sciences, King’s College London, London, United Kingdom
  • Christos Bergeles
    School of Biomedical Engineering & Imaging Sciences, King’s College London, London, United Kingdom
  • Timothy L Jackson
    Section of Ophthalmology, King’s College London, London, United Kingdom
    King's Ophthalmology Research Unit, King’s College Hospital, London, United Kingdom
  • Footnotes
    Commercial Relationships   Paul Nderitu None; Joan Nunez do Rio None; Laura Webster None; Samantha Mann Novartis, Code F (Financial Support), Bayer, Code R (Recipient), Allergan, Code R (Recipient); David Hopkins None; M. Jorge Cardoso None; Marc Modat None; Christos Bergeles None; Timothy Jackson REGENERON, Code C (Consultant/Contractor), OXURION, Code F (Financial Support), ROCHE, Code F (Financial Support), BAYER, Code F (Financial Support)
  • Footnotes
    Support  The model development study was funded by Diabetes UK via a Sir George Alberti research training fellowship grant to Dr Paul Nderitu (20/0006144) who was supervised by Professor Tim Jackson and Dr Christos Bergeles. The external validation study was funded by King’s College Hospital Charity via a research grant to Dr Paul Nderitu and Professor Tim Jackson (D2312/102022/Jackson/991). The study was also supported by a Wellcome/EPSRC Centre for Medical Engineering grant (WT 203148/Z/16/Z) to Dr Christos Bergeles.
Investigative Ophthalmology & Visual Science June 2024, Vol.65, 2768. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Paul Nderitu, Joan M Nunez do Rio, Laura Webster, Samantha Mann, David Hopkins, M. Jorge Cardoso, Marc Modat, Christos Bergeles, Timothy L Jackson; Validation of deep learning systems for predicting 1, 2 and 3 year emergent referable diabetic retinopathy and maculopathy. Invest. Ophthalmol. Vis. Sci. 2024;65(7):2768.

      Download citation file:


      © ARVO (1962-2015); The Authors (2016-present)

      ×
  • Supplements
Abstract

Purpose : 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 validated trained 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 : DLS were trained using data from 162,339 development set eyes from the south-east London diabetic eye screening programme (DESP, UK, Figure 1A), of which 110,837 eyes had eligible longitudinal data, and the remaining 51,502 eyes were used for DLS pretraining. Internal and external (Birmingham DESP, UK, Figure 1B) validation datasets included 27,996, and 6,928 eyes respectively. DLS outcomes were predicting emergent (1) referable DR (R2+), (2) referable maculopathy (M1) or (3) either (R2+ | M1) within 1, 2 or 3 years.

Results : Internal validation 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 validation 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. Multimodal and image DLS performance was significantly better than tabular DLS for all emergent referable disease outcomes and prediction intervals. Multimodal DLS was significantly better than image DLS prediction of emergent referable maculopathy within 2 and 3 years on internal validation.

Conclusions : DLS accurately predict 1, 2 and 3 year emergent referable DR and referable maculopathy using fundal photographs, with additional risk factor characteristics conferring further 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.

This abstract was presented at the 2024 ARVO Annual Meeting, held in Seattle, WA, May 5-9, 2024.

 

 

×
×

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.

×