Affordable Access

deepdyve-link
Publisher Website

Chances and challenges of machine learning-based disease classification in genetic association studies illustrated on age-related macular degeneration.

Authors
  • Guenther, Felix1, 2
  • Brandl, Caroline1, 3
  • Winkler, Thomas W1
  • Wanner, Veronika1
  • Stark, Klaus1
  • Kuechenhoff, Helmut2
  • Heid, Iris M1
  • 1 Department of Genetic Epidemiology, University of Regensburg, Regensburg, Germany. , (Germany)
  • 2 Statistical Consulting Unit StaBLab, Department of Statistics, Ludwig Maximilian University of Munich, Munich, Germany. , (Germany)
  • 3 Department of Ophthalmology, University Hospital Regensburg, Regensburg, Germany. , (Germany)
Type
Published Article
Journal
Genetic Epidemiology
Publisher
Wiley (John Wiley & Sons)
Publication Date
Oct 01, 2020
Volume
44
Issue
7
Pages
759–777
Identifiers
DOI: 10.1002/gepi.22336
PMID: 32741009
Source
Medline
Keywords
Language
English
License
Unknown

Abstract

Imaging technology and machine learning algorithms for disease classification set the stage for high-throughput phenotyping and promising new avenues for genome-wide association studies (GWAS). Despite emerging algorithms, there has been no successful application in GWAS so far. We establish machine learning-based phenotyping in genetic association analysis as misclassification problem. To evaluate chances and challenges, we performed a GWAS based on automatically classified age-related macular degeneration (AMD) in UK Biobank (images from 135,500 eyes; 68,400 persons). We quantified misclassification of automatically derived AMD in internal validation data (4,001 eyes; 2,013 persons) and developed a maximum likelihood approach (MLA) to account for it when estimating genetic association. We demonstrate that our MLA guards against bias and artifacts in simulation studies. By combining a GWAS on automatically derived AMD and our MLA in UK Biobank data, we were able to dissect true association (ARMS2/HTRA1, CFH) from artifacts (near HERC2) and identified eye color as associated with the misclassification. On this example, we provide a proof-of-concept that a GWAS using machine learning-derived disease classification yields relevant results and that misclassification needs to be considered in analysis. These findings generalize to other phenotypes and emphasize the utility of genetic data for understanding misclassification structure of machine learning algorithms. © 2020 The Authors. Genetic Epidemiology published by Wiley Periodicals LLC.

Report this publication

Statistics

Seen <100 times