Article Text

Download PDFPDF
Prediction of retinopathy progression using deep learning on retinal images within the Scottish screening programme
  1. Joseph Mellor1,
  2. Wenhua Jiang1,
  3. Alan Fleming2,
  4. Stuart J McGurnaghan1,2,
  5. Luke A K Blackbourn2,
  6. Caroline Styles3,
  7. Amos Storkey4,
  8. Paul M McKeigue1,
  9. Helen M Colhoun2
  1. 1 Usher Institute, The University of Edinburgh, Edinburgh, UK
  2. 2 Institute of Genetics and Cancer, The University of Edinburgh, Edinburgh, UK
  3. 3 Queen Margaret Hospital, NHS Fife, Dunfermline, Fife, UK
  4. 4 School of Informatics, The University of Edinburgh, Edinburgh, UK
  1. Correspondence to Dr Joseph Mellor, The University of Edinburgh, Edinburgh, EH10 5HF, UK; joe.mellor{at}ed.ac.uk

Abstract

Background/aims National guidelines of many countries set screening intervals for diabetic retinopathy (DR) based on grading of the last screening retinal images. We explore the potential of deep learning (DL) on images to predict progression to referable DR beyond DR grading, and the potential impact on assigned screening intervals, within the Scottish screening programme.

Methods We consider 21 346 and 247 233 people with type 1 diabetes mellitus (T1DM) and type 2 diabetes mellitus (T2DM), respectively, each contributing on average 4.8 and 4.4 screening intervals of which 1339 and 4675 intervals concluded with a referable screening episode. Information extracted from fundus images using DL was used to predict referable status at the end of interval and its predictive value in comparison to screening-assigned DR grade was assessed.

Results The DL predictor increased the area under the receiver operating characteristic curve in comparison to a predictor using current DR grades from 0.809 to 0.87 for T1DM and from 0.825 to 0.87 for T2DM. Expected sojourn time—the time from becoming referable to being rescreened—was found to be 3.4 (T1DM) and 2.7 (T2DM) weeks less for a DL-derived policy compared with the current recall policy.

Conclusions We showed that, compared with using the current retinopathy grade, DL of fundus images significantly improves the prediction of incident referable retinopathy before the next screening episode. This can impact screening recall interval policy positively, for example, by reducing the expected time with referable disease for a fixed workload—which we show as an exemplar. Additionally, it could be used to optimise workload for a fixed sojourn time.

  • Epidemiology

Data availability statement

Data may be obtained from a third party and are not publicly available. SDRN-Epi is not a data custodian and is not permitted to directly provision data externally. However, the component datasets can be obtained by data governance-trained bona fide researchers through the Public Benefit and Privacy Panel for Health and Social Care. See https://www.informationgovernance.scot.nhs.uk/pbpphsc/ on how to apply.

Statistics from Altmetric.com

Request Permissions

If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.

Data availability statement

Data may be obtained from a third party and are not publicly available. SDRN-Epi is not a data custodian and is not permitted to directly provision data externally. However, the component datasets can be obtained by data governance-trained bona fide researchers through the Public Benefit and Privacy Panel for Health and Social Care. See https://www.informationgovernance.scot.nhs.uk/pbpphsc/ on how to apply.

View Full Text

Footnotes

  • Contributors JM conceived and designed the study. HMC, PMM and AS made important contributions to study design. SJM and LAKB were involved in the cleaning up, harmonisation, quality control and databasing of data in Scotland. JM and WJ performed the analyses. JM developed data analysis methods. JM, WJ and AF contributed to code preparation. JM and WJ drafted the initial manuscript. All authors critically made important contributions to manuscript revision. All authors approved the final manuscript. HMC is guarantor of the overall content.

  • Funding This study was funded by Juvenile Diabetes Research Foundation United States of America (2-SRA-2019-857-S-B)

  • Competing interests HMC is principal investigator on the JDRF grant detailed in the paper. The employment of AF and JM was with this funding. HMC and PMM have declared stock options in Bayer and Roche Pharmaceuticals. HMC has received grants from AstraZeneca, Regeneron, Pfizer, Novo Nordisk and Eli Lilly and Company and is on advisory panels or boards of Novo Nordisk, Eli Lilly and Company, Regeneron, Novartis Pharmaceuticals, Bayer and Sanofi Aventis. HMC has received payments for Speakers Bureaus and honoraria from Eli Lilly and Company, Regeneron and Novartis Pharmaceuticals.

  • Provenance and peer review Not commissioned; externally peer reviewed.

  • Supplemental material This content has been supplied by the author(s). It has not been vetted by BMJ Publishing Group Limited (BMJ) and may not have been peer-reviewed. Any opinions or recommendations discussed are solely those of the author(s) and are not endorsed by BMJ. BMJ disclaims all liability and responsibility arising from any reliance placed on the content. Where the content includes any translated material, BMJ does not warrant the accuracy and reliability of the translations (including but not limited to local regulations, clinical guidelines, terminology, drug names and drug dosages), and is not responsible for any error and/or omissions arising from translation and adaptation or otherwise.

Linked Articles

  • Highlights from this issue
    Frank Larkin