Next-generation phenotyping of inherited retinal diseases from multimodal imaging with Eye2Gene
Pontikos N., Woof WA., Lin S., Ghoshal B., Mendes BS., Veturi A., Nguyen Q., Javanmardi B., Georgiou M., Hustinx A., Ibarra-Arellano MA., Moghul I., Liu Y., Pfau K., Pfau M., Shah M., Yu J., Al-Khuzaei S., Wagner SK., Daich Varela M., Cabral de Guimarães TA., Sen S., Naik G., Sumodhee D., Fu DJ., Kabiri N., Furman J., Liefers B., Lee AY., De Silva SR., Marques C., Motta F., Fujinami-Yokokawa Y., Hardcastle AJ., Arno G., Lorenz B., Herrmann P., Fujinami K., Sallum J., Madhusudhan S., Downes SM., Holz FG., Balaskas K., Webster AR., Mahroo OA., Krawitz PM., Michaelides M.
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 (n = 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.