Large-scale machine learning-based phenotyping significantly improves\n genomic discovery for optic nerve head morphology

2020/11/25 by Babak Alipanahi, Farhad Hormozdiari, Alipanahi, Babak +22 · 2 citations
Medicine · #Applications (stat.AP) #FOS: Biological sciences #FOS: Computer and information sciences #Genomics (q-bio.GN) #Glaucoma and retinal disorders #Retinal Diseases and Treatments #Retinal Imaging and Analysis

paper · pdf · doi:10.48550/arxiv.2011.13012

openalex publication_date 2020/11/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Genome-wide association studies (GWAS) require accurate cohort phenotyping,\nbut expert labeling can be costly, time-intensive, and variable. Here we\ndevelop a machine learning (ML) model to predict glaucomatous optic nerve head\nfeatures from color fundus photographs. We used the model to predict vertical\ncup-to-disc ratio (VCDR), a diagnostic parameter and cardinal endophenotype for\nglaucoma, in 65,680 Europeans in the UK Biobank (UKB). A GWAS of ML-based VCDR\nidentified 299 independent genome-wide significant (GWS; P\≤5\×10^-8)\nhits in 156 loci. The ML-based GWAS replicated 62 of 65 GWS loci from a recent\nVCDR GWAS in the UKB for which two ophthalmologists manually labeled images for\n67,040 Europeans. The ML-based GWAS also identified 92 novel loci,\nsignificantly expanding our understanding of the genetic etiologies of glaucoma\nand VCDR. Pathway analyses support the biological significance of the novel\nhits to VCDR, with select loci near genes involved in neuronal and synaptic\nbiology or known to cause severe Mendelian ophthalmic disease. Finally, the\nML-based GWAS results significantly improve polygenic prediction of VCDR and\nprimary open-angle glaucoma in the independent EPIC-Norfolk cohort.\n

Cited by

• Do We Really Even Need Data? A Modern Look at Drawing Inference with Predicted Data
• Genotype‐by‐sex interaction analyses for alcohol use disorder across biobanks

Related

• An RNA Sequencing Analysis of Glaucoma Genesis in Mice
• Describing the Structural Phenotype of the Glaucomatous Optic Nerve Head Using Artificial Intelligence
• 3D Structural Phenotype of the Optic Nerve Head at the Intersection of Glaucoma and Myopia -- A Key to Improving Glaucoma Diagnosis in Myopic Populations
• The Emory Optic Nerve Head Atlas - Using 3D Anatomical Mapping to Study Optic Neuropathies with an Initial Focus on Glaucoma
• Geometric Deep Learning to Identify the Critical 3D Structural Features of the Optic Nerve Head for Glaucoma Diagnosis