Predicting alcohol dependence from multi‐site brain structural measures. Issue 1 (16th October 2020)

• Record Type: Journal Article
• Authors: Hahn, Sage; Mackey, Scott; Cousijn, Janna; Foxe, John J.; Heinz, Andreas; Hester, Robert; Hutchinson, Kent; Kiefer, Falk; Korucuoglu, Ozlem; Lett, Tristram; Li, Chiang‐Shan R.; London, Edythe; Lorenzetti, Valentina; Maartje, Luijten; Momenan, Reza; Orr, Catherine; Paulus, Martin; Schmaal, Lianne; Sinha, Rajita; Sjoerds, Zsuzsika; Stein, Dan J.; Stein, Elliot; van Holst, Ruth J.; Veltman, Dick; Walter, Henrik; Wiers, Reinout W.; Yucel, Murat; Thompson, Paul M.; Conrod, Patricia; Allgaier, Nicholas; Garavan, Hugh;
• Other Names: Thompson P.M. guestEditor.; Jahanshad N. guestEditor.; Schmaal L. guestEditor.; Turner J.A. guestEditor.; Winkler A. guestEditor.; Thomopoulos S.I. guestEditor.; Egan G.F. guestEditor.; Kochunov P. guestEditor.
• Is Part Of: Human brain mapping. Volume 43:Issue 1(2022)
• Page Start: 555
• Page End: 565
• Publication Date: 2020-10-16
• Subjects: addiction -- alcohol dependence -- genetic algorithm -- machine learning -- multi‐site -- prediction -- structural MRI; Brain mapping -- Periodicals; 611.81
• DOI: 10.1002/hbm.25248
• Languages: English
• ISSNs: 1065-9471

Abstract

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. Abstract : To identify neuroimaging biomarkers of alcohol dependence (AD) from structural magnetic resonance imaging, we developed classifiers on data collected from multiple sites. Exploratory data analysis revealed that inclusion of case‐ and control‐only sites led to the inadvertent learning of site‐effects. Evolutionary‐based feature selection leveraging leave‐one‐site‐out cross‐validation, to combat unintentional learning, yielded a test‐set area under the receiver operating characteristic curve of 0.768.