{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Hahn S"],"funding":["Intramural NIH HHS","National Institute on Alcohol Abuse and Alcoholism","NIBIB NIH HHS","NCATS NIH HHS","NIDA NIH HHS","NCRR NIH HHS","NIAAA NIH HHS","ZonMw","National Institutes of Health","Philip Morris International","Division of Advanced Cyberinfrastructure","Dutch Research Council (NWO)","National Institute of Mental Health","National Institute on Drug Abuse","NIH HHS"],"pagination":["555-565"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC8675424"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["43(1)"],"pubmed_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. Explorat"],"journal":["Human brain mapping"],"pubmed_title":["Predicting alcohol dependence from multi-site brain structural measures."],"pmcid":["PMC8675424"],"funding_grant_id":["OAC‐1827314","ZonMW grant 31160003","VICI grant 453.08.01","U54 EB020403","UL1 TR001863","ZonMW grant 31160004","PL30-1DA024859-01","R01DA047119","ZIA AA000125-04 DICB","T32DA043593","31160003","31160004","R01 DA020726","UL1‐RR24925‐01","R01-DA014100","R01‐DA020726","PL30‐1DA024859‐01","R01-DA020726","T32 DA043593","ZonMW grant 31180002","R01-AA013892","UL1-RR24925-01","R01‐AA013892","R01‐DA014100","UL1 RR024925","ZIA AA000125","31180002","R01 DA018307","VIDI grant 016.08.322","91676084","R01 DA014100","R01 AA013892","ZonMW grant 91676084","R01 DA047119","PL1 DA024859","ZIA AA000125‐04 DICB"],"pubmed_authors":["Sjoerds Z","Garavan H","London E","Heinz A","Hutchinson K","Korucuoglu O","van Holst RJ","Li CR","Veltman D","Cousijn J","Maartje L","Stein E","Paulus M","Hester R","Conrod P","Momenan R","Walter H","Allgaier N","Foxe JJ","Yucel M","Schmaal L","Sinha R","Stein DJ","Hahn S","Wiers RW","Mackey S","Lorenzetti V","Lett T","Thompson PM","Orr C","Kiefer F"],"additional_accession":[]},"is_claimable":false,"name":"Predicting alcohol dependence from multi-site brain structural measures.","description":"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. Explorat","dates":{"release":"2022-01-01T00:00:00Z","publication":"2022 Jan","modification":"2025-04-22T22:03:09.023Z","creation":"2025-04-06T03:54:02.643Z"},"accession":"S-EPMC8675424","cross_references":{"pubmed":["33064342"],"doi":["10.1002/hbm.25248"]}}