Effect-Size Estimation Using Semiparametric Hierarchical Mixture Models in Disease-Association Studies with Neuroimaging Data.
Algorithms
Alzheimer Disease
/ diagnostic imaging
Bayes Theorem
Brain
/ diagnostic imaging
Computational Biology
Computer Simulation
Databases, Factual
/ statistics & numerical data
Humans
Magnetic Resonance Imaging
/ statistics & numerical data
Markov Chains
Models, Statistical
Neuroimaging
/ statistics & numerical data
Selection Bias
Statistics, Nonparametric
Journal
Computational and mathematical methods in medicine
ISSN: 1748-6718
Titre abrégé: Comput Math Methods Med
Pays: United States
ID NLM: 101277751
Informations de publication
Date de publication:
2020
2020
Historique:
received:
07
07
2020
revised:
08
10
2020
accepted:
27
11
2020
entrez:
25
1
2021
pubmed:
26
1
2021
medline:
18
9
2021
Statut:
epublish
Résumé
In disease-association studies using neuroimaging data, evaluating the biological or clinical significance of individual associations requires not only detection of disease-associated areas of the brain but also estimation of the magnitudes of the associations or effect sizes for individual brain areas. In this paper, we propose a model-based framework for voxel-based inferences under spatial dependency in neuroimaging data. Specifically, we employ hierarchical mixture models with a hidden Markov random field structure to incorporate the spatial dependency between voxels. A nonparametric specification is proposed for the effect size distribution to flexibly estimate the underlying effect size distribution. Simulation experiments demonstrate that compared with a naive estimation method, the proposed methods can substantially reduce the selection bias in the effect size estimates of the selected voxels with the greatest observed associations. An application to neuroimaging data from an Alzheimer's disease study is provided.
Identifiants
pubmed: 33488762
doi: 10.1155/2020/7482403
pmc: PMC7787870
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
7482403Informations de copyright
Copyright © 2020 Ryo Emoto et al.
Déclaration de conflit d'intérêts
The authors declare that they have no conflicts of interest.
Références
Neuroimage. 2009 Jan 1;44(1):83-98
pubmed: 18501637
Biometrics. 2015 Sep;71(3):741-50
pubmed: 26012881
BMJ Open. 2011 Feb 23;1(1):e000007
pubmed: 22021723
J Am Stat Assoc. 2009 Sep 1;104(487):1015-1028
pubmed: 20333278
Neuroimage. 2002 Jan;15(1):273-89
pubmed: 11771995
JAMA Psychiatry. 2017 Mar 1;74(3):207-208
pubmed: 28099973
Neuroimage. 2014 Jan 1;84:97-112
pubmed: 23981437
Bioinformatics. 2009 Nov 1;25(21):2802-8
pubmed: 19654115
Psychosom Med. 2015 Feb-Mar;77(2):114-25
pubmed: 25647751
Neuroimage. 2007 Oct 15;38(1):95-113
pubmed: 17761438
Ageing Res Rev. 2016 Sep;30:73-84
pubmed: 26876244
Hum Brain Mapp. 2014 Aug;35(8):3701-25
pubmed: 24443091
Bayesian Anal. 2013;8(2):
pubmed: 24368932
J Neurol Neurosurg Psychiatry. 2016 Apr;87(4):425-32
pubmed: 25904810
Biometrics. 2011 Dec;67(4):1225-35
pubmed: 21627629
Front Aging Neurosci. 2016 Aug 17;8:195
pubmed: 27582703
Neuroradiology. 2016 Jan;58(1):59-67
pubmed: 26400852
Neurobiol Aging. 2015 Jan;36 Suppl 1:S23-31
pubmed: 25260851
Biostatistics. 2011 Apr;12(2):223-33
pubmed: 20841334
Neurobiol Aging. 2010 Aug;31(8):1375-85
pubmed: 20447732
AJNR Am J Neuroradiol. 2008 May;29(5):944-9
pubmed: 18296551
J Cogn Neurosci. 2010 Dec;22(12):2677-84
pubmed: 19929323
Neuroimage Clin. 2014 Aug 15;6:9-19
pubmed: 25379412
J Neurosci Methods. 2002 Aug 30;118(2):115-28
pubmed: 12204303
Front Aging Neurosci. 2018 May 24;10:135
pubmed: 29881340