Machine learning derived retinal pigment score from ophthalmic imaging shows ethnicity is not biology.


Rajesh, Anand E, Olvera-Barrios, Abraham ORCID: 0000-0002-3305-4465, Warwick, Alasdair N, Wu, Yue, Stuart, Kelsey V ORCID: 0000-0001-7353-8774, Biradar, Mahantesh I ORCID: 0000-0002-4114-6255, Ung, Chuin Ying, Khawaja, Anthony P ORCID: 0000-0001-6802-8585, Luben, Robert ORCID: 0000-0002-5088-6343, Foster, Paul J ORCID: 0000-0002-4755-177X et al (show 13 more authors) (2025) Machine learning derived retinal pigment score from ophthalmic imaging shows ethnicity is not biology. Nature communications, 16 (1). 60-. ISSN 2041-1723, 2041-1723

Access the full-text of this item by clicking on the Open Access link.

Abstract

Few metrics exist to describe phenotypic diversity within ophthalmic imaging datasets, with researchers often using ethnicity as a surrogate marker for biological variability. We derived a continuous, measured metric, the retinal pigment score (RPS), that quantifies the degree of pigmentation from a colour fundus photograph of the eye. RPS was validated using two large epidemiological studies with demographic and genetic data (UK Biobank and EPIC-Norfolk Study) and reproduced in a Tanzanian, an Australian, and a Chinese dataset. A genome-wide association study (GWAS) of RPS from UK Biobank identified 20 loci with known associations with skin, iris and hair pigmentation, of which eight were replicated in the EPIC-Norfolk cohort. There was a strong association between RPS and ethnicity, however, there was substantial overlap between each ethnicity and the respective distributions of RPS scores. RPS decouples traditional demographic variables from clinical imaging characteristics. RPS may serve as a useful metric to quantify the diversity of the training, validation, and testing datasets used in the development of AI algorithms to ensure adequate inclusion and explainability of the model performance, critical in evaluating all currently deployed AI models. The code to derive RPS is publicly available at: https://github.com/uw-biomedical-ml/retinal-pigmentation-score .

Item Type: Article
Uncontrolled Keywords: UK Biobank Eye and Vision Consortium, Retina, Humans, Photography, Adult, Aged, Middle Aged, Female, Male, Genome-Wide Association Study, Machine Learning, Ethnicity, UK Biobank
Divisions: Faculty of Health and Life Sciences
Faculty of Health and Life Sciences > Institute of Life Courses and Medical Sciences
Depositing User: Symplectic Admin
Date Deposited: 28 Feb 2025 16:38
Last Modified: 28 Feb 2025 16:38
DOI: 10.1038/s41467-024-55198-7
Open Access URL: https://doi.org/10.1038/s41467-024-55198-7
Related Websites:
URI: https://livrepository.liverpool.ac.uk/id/eprint/3190593
Altmetric
CORE (COnnecting REpositories)