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

Anand E. Rajesh; Abraham Olvera-Barrios; Alasdair N. Warwick; Yue Wu; Kelsey V. Stuart; Mahantesh I. Biradar; Chuin Ying Ung; Anthony P. Khawaja; Robert Luben; Paul J. Foster; Charles R. Cleland; William U. Makupa; Alastair K. Denniston; Matthew J. Burton; Andrew Bastawrous; Pearse A. Keane; Mark A. Chia; Angus W. Turner; Cecilia S. Lee; Adnan Tufail; Aaron Y. Lee; Catherine Egan; Naomi Allen; Tariq Aslam; Denize Atan; Konstantinos Balaskas; Sarah Barman; Jenny Barrett; Paul Bishop; Graeme Black; Tasanee Braithwaite; Roxana Carare; Usha Chakravarthy; Michelle Chan; Sharon Chua; Alexander Day; Parul Desai; Baljean Dhillon; Andrew Dick; Alexander Doney; Sarah Ennis; John Gallacher; David Ted Garway-Heath; Jane Gibson; Jeremy Guggenheim; Chris Hammond; Alison Hardcastle; Simon Harding; Ruth Hogg; Pirro Hysi; Gerassimos Lascaratos; Thomas Littlejohns; Andrew Lotery; Phil Luthert; Tom MacGillivray; Sarah Mackie; Savita Madhusudhan; Bernadette McGuinness; Gareth McKay; Martin McKibbin; Tony Moore; James Morgan; Eoin O’Sullivan; Richard Oram; Chris Owen; Praveen Patel; Euan Paterson; Tunde Peto; Axel Petzold; Nikolas Pontikos; Jugnoo Rahi; Alicja Rudnicka; Naveed Sattar; Jay Self; Panagiotis Sergouniotis; Sobha Sivaprasad; David Steel; Irene Stratton; Nicholas Strouthidis; Cathie Sudlow; Zihan Sun; Robyn Tapp; Dhanes Thomas; Emanuele Trucco; Ananth Viswanathan; Veronique Vitart; Mike Weedon; Katie Williams; Cathy Williams; Jayne Woodside; Max Yates; Yalin Zheng

doi:10.1038/s41467-024-55198-7

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

A Anand E. Rajesh A Abraham Olvera-Barrios A Alasdair N. Warwick Y Yue Wu (Genomic Analysis Laboratory, Salk Institute for Biological Studies, La Jolla, CA, USA.) K Kelsey V. Stuart M Mahantesh I. Biradar C Chuin Ying Ung A Anthony P. Khawaja R Robert Luben P Paul J. Foster C Charles R. Cleland W William U. Makupa A Alastair K. Denniston M Matthew J. Burton A Andrew Bastawrous P Pearse A. Keane M Mark A. Chia A Angus W. Turner C Cecilia S. Lee A Adnan Tufail A Aaron Y. Lee C Catherine Egan N Naomi Allen T Tariq Aslam D Denize Atan K Konstantinos Balaskas S Sarah Barman J Jenny Barrett P Paul Bishop G Graeme Black T Tasanee Braithwaite R Roxana Carare U Usha Chakravarthy M Michelle Chan S Sharon Chua A Alexander Day P Parul Desai B Baljean Dhillon A Andrew Dick A Alexander Doney S Sarah Ennis J John Gallacher D David Ted Garway-Heath J Jane Gibson J Jeremy Guggenheim C Chris Hammond A Alison Hardcastle S Simon Harding R Ruth Hogg P Pirro Hysi G Gerassimos Lascaratos T Thomas Littlejohns A Andrew Lotery P Phil Luthert T Tom MacGillivray S Sarah Mackie S Savita Madhusudhan B Bernadette McGuinness G Gareth McKay M Martin McKibbin T Tony Moore J James Morgan E Eoin O’Sullivan R Richard Oram C Chris Owen P Praveen Patel E Euan Paterson T Tunde Peto A Axel Petzold N Nikolas Pontikos J Jugnoo Rahi A Alicja Rudnicka N Naveed Sattar (School of Cardiovascular and Metabolic Health, University of Glasgow, Glasgow, United Kingdom) J Jay Self P Panagiotis Sergouniotis S Sobha Sivaprasad D David Steel I Irene Stratton N Nicholas Strouthidis C Cathie Sudlow Z Zihan Sun R Robyn Tapp D Dhanes Thomas E Emanuele Trucco A Ananth Viswanathan V Veronique Vitart M Mike Weedon K Katie Williams C Cathy Williams J Jayne Woodside M Max Yates Y Yalin Zheng

Abstract

AbstractFew 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.

Download PDF View Original

APA MLA Chicago BibTeX RIS

Article Details

Journal Nature Communications

Volume / Issue Vol. 16, Issue 1

Published January 02, 2025

DOI 10.1038/s41467-024-55198-7

ISSN 2041-1723

Publisher Nature Portfolio

Journal Info

Nature Communications

Nature Portfolio

ISSN: 2041-1723 Open Access Life Sciences

Authors (92)

A

Anand E. Rajesh

A

Abraham Olvera-Barrios

A

Alasdair N. Warwick

Y

Yue Wu

Genomic Analysis Laboratory, Salk Institute for Biological Studies, La Jolla, CA, USA.

K

Kelsey V. Stuart

M

Mahantesh I. Biradar

C

Chuin Ying Ung

A

Anthony P. Khawaja

R

Robert Luben

P

Paul J. Foster

C

Charles R. Cleland

W

William U. Makupa

A

Alastair K. Denniston

M

Matthew J. Burton

A

Andrew Bastawrous

P

Pearse A. Keane

M

Mark A. Chia

A

Angus W. Turner

C

Cecilia S. Lee

A

Adnan Tufail

A

Aaron Y. Lee

C

Catherine Egan

N

Naomi Allen

T

Tariq Aslam

D

Denize Atan

K

Konstantinos Balaskas

S

Sarah Barman

J

Jenny Barrett

P

Paul Bishop

G

Graeme Black

T

Tasanee Braithwaite

R

Roxana Carare

U

Usha Chakravarthy

M

Michelle Chan

S

Sharon Chua

A

Alexander Day

P

Parul Desai

B

Baljean Dhillon

A

Andrew Dick

A

Alexander Doney

S

Sarah Ennis

J

John Gallacher

D

David Ted Garway-Heath

J

Jane Gibson

J

Jeremy Guggenheim

C

Chris Hammond

A

Alison Hardcastle

S

Simon Harding

R

Ruth Hogg

P

Pirro Hysi

G

Gerassimos Lascaratos

T

Thomas Littlejohns

A

Andrew Lotery

P

Phil Luthert

T

Tom MacGillivray

S

Sarah Mackie

S

Savita Madhusudhan

B

Bernadette McGuinness

G

Gareth McKay

M

Martin McKibbin

T

Tony Moore

J

James Morgan

E

Eoin O’Sullivan

R

Richard Oram

C

Chris Owen

P

Praveen Patel

E

Euan Paterson

T

Tunde Peto

A

Axel Petzold

N

Nikolas Pontikos

J

Jugnoo Rahi

A

Alicja Rudnicka

N

Naveed Sattar

School of Cardiovascular and Metabolic Health, University of Glasgow, Glasgow, United Kingdom

J

Jay Self

P

Panagiotis Sergouniotis

S

Sobha Sivaprasad

D

David Steel

I

Irene Stratton

N

Nicholas Strouthidis

C

Cathie Sudlow

Z

Zihan Sun

R

Robyn Tapp

D

Dhanes Thomas

E

Emanuele Trucco

A

Ananth Viswanathan

V

Veronique Vitart

M

Mike Weedon

K

Katie Williams

C

Cathy Williams

J

Jayne Woodside

M

Max Yates

Y

Yalin Zheng

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

Abstract

Article Details

Journal Info

Authors (92)

Related Articles from this Journal

Synthesis of adaptive 15N-nitrosyl-Co7 nanocluster for electrocatalytic C–H functionalization

Pan-Ebolavirus nanoparticle vaccine provides protection in rodents from lethal infection by Zaire and Sudan viruses

Multi-population GWAS meta-analysis identifies bladder cancer susceptibility loci and highlights genetic regulation of smoking-related risk

Genome-wide annotation of human multi-nucleotide variants reveals widespread functional differences from single nucleotide variants

Allele-specific chromatin architecture shapes imprinted domains and coordinates a distal enhancer and antisense transcription at the mouse Mest-Copg2 domain