Brain age prediction using deep learning uncovers associated sequence variants.

Journal: Nature communications
Published Date:

Abstract

Machine learning algorithms can be trained to estimate age from brain structural MRI. The difference between an individual's predicted and chronological age, predicted age difference (PAD), is a phenotype of relevance to aging and brain disease. Here, we present a new deep learning approach to predict brain age from a T1-weighted MRI. The method was trained on a dataset of healthy Icelanders and tested on two datasets, IXI and UK Biobank, utilizing transfer learning to improve accuracy on new sites. A genome-wide association study (GWAS) of PAD in the UK Biobank data (discovery set: [Formula: see text], replication set: [Formula: see text]) yielded two sequence variants, rs1452628-T ([Formula: see text], [Formula: see text]) and rs2435204-G ([Formula: see text], [Formula: see text]). The former is near KCNK2 and correlates with reduced sulcal width, whereas the latter correlates with reduced white matter surface area and tags a well-known inversion at 17q21.31 (H2).

Authors

  • B A Jonsson
    deCODE Genetics/Amgen, Inc., 101, Reykjavik, Iceland.
  • G Bjornsdottir
    deCODE Genetics/Amgen, Inc., 101, Reykjavik, Iceland.
  • T E Thorgeirsson
    deCODE Genetics/Amgen, Inc., 101, Reykjavik, Iceland.
  • L M Ellingsen
    University of Iceland, 101, Reykjavik, Iceland.
  • G Bragi Walters
    deCODE Genetics/Amgen, Inc., 101, Reykjavik, Iceland.
  • D F Gudbjartsson
    deCODE Genetics/Amgen, Inc., 101, Reykjavik, Iceland.
  • H Stefansson
    deCODE Genetics/Amgen, Inc., 101, Reykjavik, Iceland.
  • K Stefansson
    deCODE Genetics/Amgen, Inc., 101, Reykjavik, Iceland. kstefans@decode.is.
  • M O Ulfarsson
    deCODE Genetics/Amgen, Inc., 101, Reykjavik, Iceland. mou@hi.is.