PMID- 38316534
OWN - NLM
STAT- Publisher
LR  - 20240424
IS  - 1468-2079 (Electronic)
IS  - 0007-1161 (Linking)
DP  - 2024 Apr 24
TI  - Prediction of retinopathy progression using deep learning on retinal images 
      within the Scottish screening programme.
LID - bjo-2023-323400 [pii]
LID - 10.1136/bjo-2023-323400 [doi]
AB  - 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.
CI  - (c) Author(s) (or their employer(s)) 2024. No commercial re-use. See rights and 
      permissions. Published by BMJ.
FAU - Mellor, Joseph
AU  - Mellor J
AUID- ORCID: 0000-0003-1452-887X
AD  - Usher Institute, The University of Edinburgh, Edinburgh, UK joe.mellor@ed.ac.uk.
FAU - Jiang, Wenhua
AU  - Jiang W
AD  - Usher Institute, The University of Edinburgh, Edinburgh, UK.
FAU - Fleming, Alan
AU  - Fleming A
AUID- ORCID: 0000-0003-0642-7331
AD  - Institute of Genetics and Cancer, The University of Edinburgh, Edinburgh, UK.
FAU - McGurnaghan, Stuart J
AU  - McGurnaghan SJ
AUID- ORCID: 0000-0002-3292-4633
AD  - Usher Institute, The University of Edinburgh, Edinburgh, UK.
AD  - Institute of Genetics and Cancer, The University of Edinburgh, Edinburgh, UK.
FAU - Blackbourn, Luke A K
AU  - Blackbourn LAK
AUID- ORCID: 0000-0003-4234-8040
AD  - Institute of Genetics and Cancer, The University of Edinburgh, Edinburgh, UK.
FAU - Styles, Caroline
AU  - Styles C
AUID- ORCID: 0000-0002-6515-1032
AD  - Queen Margaret Hospital, NHS Fife, Dunfermline, Fife, UK.
FAU - Storkey, Amos
AU  - Storkey A
AUID- ORCID: 0000-0002-8100-506X
AD  - School of Informatics, The University of Edinburgh, Edinburgh, UK.
FAU - McKeigue, Paul M
AU  - McKeigue PM
AUID- ORCID: 0000-0002-5217-1034
AD  - Usher Institute, The University of Edinburgh, Edinburgh, UK.
FAU - Colhoun, Helen M
AU  - Colhoun HM
AUID- ORCID: 0000-0002-8345-3288
AD  - Institute of Genetics and Cancer, The University of Edinburgh, Edinburgh, UK.
LA  - eng
PT  - Journal Article
DEP - 20240424
PL  - England
TA  - Br J Ophthalmol
JT  - The British journal of ophthalmology
JID - 0421041
SB  - IM
OTO - NOTNLM
OT  - Epidemiology
COIS- 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.
EDAT- 2024/02/06 00:42
MHDA- 2024/02/06 00:42
CRDT- 2024/02/05 21:13
PHST- 2023/02/09 00:00 [received]
PHST- 2023/07/09 00:00 [accepted]
PHST- 2024/02/06 00:42 [pubmed]
PHST- 2024/02/06 00:42 [medline]
PHST- 2024/02/05 21:13 [entrez]
AID - bjo-2023-323400 [pii]
AID - 10.1136/bjo-2023-323400 [doi]
PST - aheadofprint
SO  - Br J Ophthalmol. 2024 Apr 24:bjo-2023-323400. doi: 10.1136/bjo-2023-323400.