Next-generation phenotyping of inherited retinal diseases from multimodal imaging with Eye2Gene

Rare eye diseases such as inherited retinal diseases (IRDs) are challenging to diagnose genetically. IRDs are typically monogenic disorders and represent a leading cause of blindness in children and working-age adults worldwide. A growing number are now being targeted in clinical trials, with approved treatments increasingly available. However, access requires a genetic diagnosis to be established sufficiently early. Critically, the timely identification of a genetic cause remains challenging. We demonstrate that a deep learning algorithm, Eye2Gene, trained on a large multimodal imaging dataset of individuals with IRDs (<i>n</i> = 2,451) and externally validated on data provided by five different clinical centres, provides better-than-expert-level top-five accuracy of 83.9% for supporting genetic diagnosis for the 63 most common genetic causes. We demonstrate that Eye2Gene's next-generation phenotyping can increase diagnostic yield by improving screening for IRDs, phenotype-driven variant prioritization and automatic similarity matching in phenotypic space to identify new genes. Eye2Gene is accessible online (app.eye2gene.com) for research purposes.

Authors

Institutions

Publication Details

Journal
Nature Machine Intelligence
Published
2025-06-18
DOI
https://doi.org/10.1038/s42256-025-01040-8
Citations
16
Primary Topic
Retinal Development and Disorders
Type
article
Field-Weighted Citation Impact
12.90

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Next-generation phenotyping of inherited retinal diseases from multimodal imaging with Eye2Gene

Quang Nguyen, Gunjan Naik, Behnam Javanmardi, Caio Henrique Marques Texeira et al.
16 citations
Nature Machine Intelligence
Retinal Development and Disorders
12.90
article

Next-generation phenotyping of inherited retinal diseases from multimodal imaging with Eye2Gene

Quang Nguyen, Gunjan Naik, Behnam Javanmardi, Caio Henrique Marques Texeira, Saoud Al‐Khuzaei, Samantha Roshani De Silva, Peter Michael Krawitz, Maximilian Pfau, Mital Shah, Jennifer Furman, Kaoru Fujinami, Frank Gerhard Holz, Siying Lin, Bart Liefers, Bernardo Mendes, Birgit Lorenz, Siegfried K. Wagner, Aaron Lee, Dun Jack Fu, Juliana Maria Ferraz Sallum, Ismail Moghul, Andreas Balaskas, William Woof, Yoga Advaith Veturi, Biraja Ghoshal, Yu Fujinami‐Yokokawa, Nathaniel Kabiri, Thales A. C. de Guimarães, Alexander Hustinx, Gavin Arno, Dayyanah Sumodhee, Omar A. Mahroo, Alison J. Hardcastle, Kristina Pfau, Michalis Georgiou, Fabiana Louise Motta, Savita Madhusudhan, Michel Michaelides, Sagnik Sen, Susan M. Downes, Nikolas Pontikos, Malena Daich Varela, Miguel A. Ibarra-Arellano, Andrew R. Webster, Yichen Liu, Jing Yu, Philipp Herrmann
article en
16 citations

Abstract

Rare eye diseases such as inherited retinal diseases (IRDs) are challenging to diagnose genetically. IRDs are typically monogenic disorders and represent a leading cause of blindness in children and working-age adults worldwide. A growing number are now being targeted in clinical trials, with approved treatments increasingly available. However, access requires a genetic diagnosis to be established sufficiently early. Critically, the timely identification of a genetic cause remains challenging. We demonstrate that a deep learning algorithm, Eye2Gene, trained on a large multimodal imaging dataset of individuals with IRDs (<i>n</i> = 2,451) and externally validated on data provided by five different clinical centres, provides better-than-expert-level top-five accuracy of 83.9% for supporting genetic diagnosis for the 63 most common genetic causes. We demonstrate that Eye2Gene's next-generation phenotyping can increase diagnostic yield by improving screening for IRDs, phenotype-driven variant prioritization and automatic similarity matching in phenotypic space to identify new genes. Eye2Gene is accessible online (app.eye2gene.com) for research purposes.

Nature Machine IntelligenceVol. 7(6)
University of Bonn (DE), University of Washington (US), University Hospital Bonn (DE), University Hospital of Basel (CH), Royal Liverpool and Broadgreen University Hospital NHS Trust (GB), John Radcliffe Hospital (GB), Tokyo Medical Center (JP), The Retina Center (US), Faculdade São Leopoldo Mandic (BR), National Hospital Organization (JP), UCL Biomedical Research Centre (GB), Moorfields Eye Hospital (GB), Associação Paulista de Medicina (BR), University College London (GB), Universidade Federal de São Paulo (BR)
Nvidia, Amazon Web Services, Wellcome Trust, National Institute for Health and Care Research, Department of Health and Social Care, Sight Research UK, Retina UK, Moorfields Eye Charity, National Institutes of Health, National Institute on Aging, National Eye Institute
Openalex Percentile: Top 1%
Retinal Development and Disorders
12.90
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.