Predicting 1, 2 and 3 year emergent referable diabetic retinopathy and maculopathy using deep learning
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.
Authors
- Christos Bergeles (ORCID: https://orcid.org/0000-0002-9152-3194)
- Laura Webster
- Marc Modat (ORCID: https://orcid.org/0000-0002-5277-8530)
- David Hopkins (ORCID: https://orcid.org/0000-0002-0451-0900)
- Paul Nderitu (ORCID: https://orcid.org/0000-0002-8571-0751)
- Timothy L. Jackson (ORCID: https://orcid.org/0000-0001-7618-1555)
- Samantha Mann (ORCID: https://orcid.org/0000-0003-0407-4501)
- M. Jorge Cardoso (ORCID: https://orcid.org/0000-0003-1284-2558)
- Joan M. Nunez do Rio (ORCID: https://orcid.org/0000-0001-8268-5389)
Institutions
- St Thomas' Hospital (GB)
- King's College London (GB)
- Kings Health Partners (GB)
- King's College Hospital (GB)
Publication Details
- Journal
- Communications Medicine
- Published
- 2024-08-21
- DOI
- https://doi.org/10.1038/s43856-024-00590-z
- Citations
- 8
- Primary Topic
- Retinal Imaging and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 3.23
Funders
- Diabetes UK
- King's College London
- Engineering and Physical Sciences Research Council