Quantifying uncertainty in brain-predicted age using scalar-on-image quantile regression.
Brain age
Prediction intervals
Quantile regression
Scalar-on-image regression
Journal
NeuroImage
ISSN: 1095-9572
Titre abrégé: Neuroimage
Pays: United States
ID NLM: 9215515
Informations de publication
Date de publication:
01 10 2020
01 10 2020
Historique:
received:
05
12
2019
revised:
07
05
2020
accepted:
08
05
2020
pubmed:
6
6
2020
medline:
25
2
2021
entrez:
6
6
2020
Statut:
ppublish
Résumé
Prediction of subject age from brain anatomical MRI has the potential to provide a sensitive summary of brain changes, indicative of different neurodegenerative diseases. However, existing studies typically neglect the uncertainty of these predictions. In this work we take into account this uncertainty by applying methods of functional data analysis. We propose a penalised functional quantile regression model of age on brain structure with cognitively normal (CN) subjects in the Alzheimer's Disease Neuroimaging Initiative (ADNI), and use it to predict brain age in Mild Cognitive Impairment (MCI) and Alzheimer's Disease (AD) subjects. Unlike the machine learning approaches available in the literature of brain age prediction, which provide only point predictions, the outcome of our model is a prediction interval for each subject.
Identifiants
pubmed: 32502669
pii: S1053-8119(20)30424-9
doi: 10.1016/j.neuroimage.2020.116938
pmc: PMC7443707
pii:
doi:
Types de publication
Journal Article
Research Support, N.I.H., Extramural
Research Support, Non-U.S. Gov't
Research Support, U.S. Gov't, Non-P.H.S.
Langues
eng
Sous-ensembles de citation
IM
Pagination
116938Subventions
Organisme : Wellcome Trust
ID : 100309/Z/12/Z
Pays : United Kingdom
Organisme : NIA NIH HHS
ID : U01 AG024904
Pays : United States
Organisme : Medical Research Council
Pays : United Kingdom
Organisme : CIHR
Pays : Canada
Informations de copyright
Copyright © 2020 The Author(s). Published by Elsevier Inc. All rights reserved.
Déclaration de conflit d'intérêts
Declaration of competing interest All authors declare no conflict of interests.
Références
Neuroimage. 2018 Feb 15;167:11-22
pubmed: 29122720
BMC Med Res Methodol. 2012 Jan 25;12:6
pubmed: 22276940
R J. 2015 Jun;7(1):163-175
pubmed: 27330830
Proc Natl Acad Sci U S A. 2019 Oct 15;116(42):21213-21218
pubmed: 31575746
Mol Psychiatry. 2019 Jun 3;:
pubmed: 31160692
Neuroimage. 2019 Jun;193:35-45
pubmed: 30831310
Front Neurol. 2019 Aug 14;10:789
pubmed: 31474922
Neuroimage. 2013 Feb 1;66:648-61
pubmed: 23153970
Neuroimage. 2008 May 15;41(1):19-34
pubmed: 18378167
PLoS Med. 2015 Mar 31;12(3):e1001779
pubmed: 25826379
J Magn Reson Imaging. 2006 Sep;24(3):513-9
pubmed: 16878302
Neuroimage. 2019 Oct 15;200:528-539
pubmed: 31201988
Alzheimer Dis Assoc Disord. 2012 Jan-Mar;26(1):17-27
pubmed: 22343374
Prog Neurobiol. 2014 Jun;117:20-40
pubmed: 24548606
Alzheimers Dement. 2005 Jul;1(1):55-66
pubmed: 17476317
J Am Stat Assoc. 2009 Dec 1;104(488):1550-1561
pubmed: 20625442
Neuroimage. 2017 Dec;163:115-124
pubmed: 28765056
Neural Regen Res. 2018 Oct;13(10):1719-1730
pubmed: 30136683
Neuroimage. 2012 Nov 15;63(3):1305-12
pubmed: 22902922
Int Stat Rev. 2017 Aug;85(2):228-249
pubmed: 28919663
Neurosci Biobehav Rev. 2014 Feb;39:34-50
pubmed: 24374381
Aging (Albany NY). 2017 Aug 30;9(8):1861-1862
pubmed: 28858849
Neuropsychol Rev. 2014 Sep;24(3):271-89
pubmed: 25146995
Sci Rep. 2019 Apr 12;9(1):6012
pubmed: 30979917
Bioinformatics. 2018 Aug 15;34(16):2781-2787
pubmed: 29617937
Biometrics. 2010 Mar;66(1):61-9
pubmed: 19432766
Stat Med. 2018 Dec 10;37(28):4298-4317
pubmed: 30132932
Annu Rev Pathol. 2008;3:41-66
pubmed: 18039130
Biom J. 2018 May;60(3):431-449
pubmed: 29292533