PubMed ID: 42818461
Author(s): Aman AM, Zaher E, Diaz-Torres S, Driessen SJ, de Vries VA, van der Heide FC, Kolovos A, Schmidt JM, Marshall HN, Saleh L, Schulze A, Blokland GA, Webers CA, van der Kallen CJ, Wesselius A, Arts I, van Asten F, Gorski M, Zimmermann ME, Stark KJ, Heid IM, Young TL, Pasquale LR, Segre AV, Wiggs JL, Khawaja AP, Zack DJ, Wong RC, Hewitt AW, Schuster AK, Berendschot TT, Thiadens AA, van Garderen KA, Klaver CCW, Hysi PG, Hammond CJ, Brandl C, Craig JE, Ramdas WD, Wang YX, Jonas JB, Roosta F, Hunter ML, MacGregor S, Lee SS, Mackey DA, Trzaskowski M, Gharahkhani P. Genetic discovery using deep learning-derived optic nerve integrity phenotypes. medRxiv [Preprint]. 2026 Sep 10:2026.09.08.26362398. doi: 10.64898/2026.09.08.26362398. PMID 42818461
Journal: Med Rxiv : The Preprint Server For Health Sciences, Sep 2026
The peripapillary retinal nerve fibre layer (pRNFL) thickness and Bruch’s membrane opening-minimum rim width (BMO-MRW) are three-dimensional retinal biomarkers for glaucoma. We aimed to demonstrate that AI-derived thickness from two-dimensional fundus images can act as proxies, enabling the discovery of novel neurodegenerative loci. AI-derived pRNFL and BMO-MRW strongly correlated with OCT-derived thickness (r: 0.69 and 0.79, respectively). After validation, these phenotypes were predicted in two cohorts lacking disc-centred OCT: the UK Biobank and the Canadian Longitudinal Study on Aging. The predicted phenotypes showed strong genetic correlations with directly measured phenotypes from a previous study for both phenotypes (0.70 and 0.96, respectively). This data increased statistical power, identifying 29 loci for pRNFL thickness and 122 loci for BMO-MRW, including 14 loci that were independent of VCDR. We observed shared and sector-specific thickness loci overlapping glaucoma loci and revealed loci independent of known risk factors. Together, these results emphasise that multidimensional inferences can be drawn from 2D imaging, enabling downstream genetic analyses.