Validation of a deep learning system for the detection of diabetic retinopathy in Indigenous Australians.

Journal: The British journal of ophthalmology
PMID: 36746615

Abstract

BACKGROUND/AIMS: Deep learning systems (DLSs) for diabetic retinopathy (DR) detection show promising results but can underperform in racial and ethnic minority groups, therefore external validation within these populations is critical for health equity. This study evaluates the performance of a DLS for DR detection among Indigenous Australians, an understudied ethnic group who suffer disproportionately from DR-related blindness.

Authors

  • Mark A Chia
    NIHR Biomedical Research Centre for Ophthalmology, Moorfields Eye Hospital NHS Foundation Trust and UCL Institute of Ophthalmology, London, UK.
  • Fred Hersch
    Google Health, Palo Alto, CA, USA.
  • Rory Sayres
    Google Research, Google, LLC, Mountain View, California.
  • Pinal Bavishi
    Google Health, Google, Mountain View, CA, USA.
  • Richa Tiwari
    Work done at Google via Optimum Solutions Pte Ltd, Singapore.
  • Pearse A Keane
    National Institute for Health Research Biomedical Research Centre for Ophthalmology, Moorfields Eye Hospital NHS Foundation Trust and UCL Institute of Ophthalmology, London, UK.
  • Angus W Turner
    Lions Outback Vision, Lions Eye Institute, Nedlands, Western Australia, Australia; University of Western Australia, Perth, Western Australia, Australia.

Keywords

External Resources

Popular Topics
Recent Journals