Open AccessPredicting alcohol dependence from multi‐site brain structural measures
Author(s) -
Hahn Sage,
Mackey Scott,
Cousijn Janna,
Foxe John J.,
Heinz Andreas,
Hester Robert,
Hutchinson Kent,
Kiefer Falk,
Korucuoglu Ozlem,
Lett Tristram,
Li ChiangShan R.,
London Edythe,
Lorenzetti Valentina,
Maartje Luijten,
Momenan Reza,
Orr Catherine,
Paulus Martin,
Schmaal Lianne,
Sinha Rajita,
Sjoerds Zsuzsika,
Stein Dan J.,
Stein Elliot,
Holst Ruth J.,
Veltman Dick,
Walter Henrik,
Wiers Reinout W.,
Yucel Murat,
Thompson Paul M.,
Conrod Patricia,
Allgaier Nicholas,
Garavan Hugh
Publication year - 2022
Publication title -
human brain mapping
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 2.005
H-Index - 191
eISSN - 1097-0193
pISSN - 1065-9471
DOI - 10.1002/hbm.25248
Subject(s) - feature selection , orbitofrontal cortex , cross validation , neuroimaging , putamen , set (abstract data type) , receiver operating characteristic , functional magnetic resonance imaging , artificial intelligence , computer science , psychology , neuroscience , pattern recognition (psychology) , machine learning , prefrontal cortex , cognition , programming language
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.