English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Predicting alcohol dependence from multi‐sitebrain structural measures

Hahn, S., Mackey, S., Cousijn, J., Foxe, J. J., Heinz, A., Hester, R., et al. (2020). Predicting alcohol dependence from multi‐sitebrain structural measures. Human Brain Mapping. doi:10.1002/hbm.25248.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/21.11116/0000-0007-4D33-A Version Permalink: http://hdl.handle.net/21.11116/0000-0007-60AD-A
Genre: Journal Article

Files

show Files
hide Files
:
Hahn_2020.pdf (Publisher version), 2MB
Name:
Hahn_2020.pdf
Description:
-
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
Copyright Date:
-
Copyright Info:
-
License:
-

Locators

show

Creators

show
hide
 Creators:
Hahn, Sage, Author
Mackey, Scott, Author
Cousijn, Janna, Author
Foxe, John J., Author
Heinz, Andreas, Author
Hester, Robert, Author
Hutchinson, Kent, Author
Kiefer, Falk, Author
Korucuoglu, Ozlem, Author
Lett, Tristram, Author
Li, Chiang‐Shan R., Author
London, Edythe, Author
Lorenzetti, Valentina, Author
Maartje, Luijten, Author
Momenan, Reza, Author
Orr, Catherine, Author
Paulus, Martin, Author
Schmaal, Lianne, Author
Sinha, Rajita, Author
Sjoerds, Zsuzsika1, Author              
Stein, Dan J., AuthorStein, Elliot, AuthorHolst, Ruth J., AuthorVeltman, Dick, AuthorWalter, Henrik, AuthorWiers, Reinout W., AuthorYucel, Murat, AuthorThompson, Paul M., AuthorConrod, Patricia, AuthorAllgaier, Nicholas, AuthorGaravan, Hugh, Author more..
Affiliations:
1Department Neurology, MPI for Human Cognitive and Brain Sciences, Max Planck Society, ou_634549              

Content

show
hide
Free keywords: Addiction; Alcohol dependence; Genetic algorithm; Machine learning; Multi‐site; Prediction; Structural MRI
 Abstract: To identify neuroimaging biomarkers of alcohol dependence (AD) from structural magnetic resonance imaging, it may be useful to develop classification models that are explicitly generalizable to unseen sites and populations. This problem was explored in a mega‐analysis of previously published datasets from 2,034 AD and comparison participants spanning 27 sites curated by the ENIGMA Addiction Working Group. Data were grouped into a training set used for internal validation including 1,652 participants (692 AD, 24 sites), and a test set used for external validation with 382 participants (146 AD, 3 sites). An exploratory data analysis was first conducted, followed by an evolutionary search based feature selection to site generalizable and high performing subsets of brain measurements. Exploratory data analysis revealed that inclusion of case‐ and control‐only sites led to the inadvertent learning of site‐effects. Cross validation methods that do not properly account for site can drastically overestimate results. Evolutionary‐based feature selection leveraging leave‐one‐site‐out cross‐validation, to combat unintentional learning, identified cortical thickness in the left superior frontal gyrus and right lateral orbitofrontal cortex, cortical surface area in the right transverse temporal gyrus, and left putamen volume as final features. Ridge regression restricted to these features yielded a test‐set area under the receiver operating characteristic curve of 0.768. These findings evaluate strategies for handling multi‐site data with varied underlying class distributions and identify potential biomarkers for individuals with current AD.

Details

show
hide
Language(s): eng - English
 Dates: 2020-09-212020-06-122020-10-062020-10-16
 Publication Status: Published online
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1002/hbm.25248
Other: online ahead of print
PMID: 33064342
 Degree: -

Event

show

Legal Case

show

Project information

show hide
Project name : -
Grant ID : OAC‐1827314
Funding program : -
Funding organization : Division of Advanced Cyberinfrastructure
Project name : -
Grant ID : R01 DA018307
Funding program : -
Funding organization : National Institute of Mental Health
Project name : -
Grant ID : R01‐AA013892, ZIA AA000125‐04 DICB
Funding program : -
Funding organization : National Institute on Alcohol Abuse and Alcoholism
Project name : -
Grant ID : PL30‐1DA024859‐01, R01‐DA014100, R01‐DA020726, R01DA047119, T32DA043593, UL1‐RR24925‐01
Funding program : -
Funding organization : National Institute on Drug Abuse
Project name : -
Grant ID : U54 EB020403
Funding program : -
Funding organization : National Institutes of Health
Project name : -
Grant ID : VICI grant 453.08.01, VIDI grant 016.08.322, ZonMW grant 31160003, ZonMW grant 31160004, ZonMW grant 31180002, ZonMW grant 91676084
Funding program : -
Funding organization : Nederlandse Organisatie voor Wetenschappelijk Onderzoek

Source 1

show
hide
Title: Human Brain Mapping
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: New York : Wiley-Liss
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: - Identifier: ISSN: 1065-9471
CoNE: https://pure.mpg.de/cone/journals/resource/954925601686