% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Bruin:279183,
author = {Bruin, Willem B. and Zhutovsky, Paul and van Wingen, Guido
A. and Bas-Hoogendam, Janna Marie and Groenewold, Nynke A.
and Hilbert, Kevin and Winkler, Anderson M. and Zugman,
Andre and Agosta, Federica and Åhs, Fredrik and Andreescu,
Carmen and Antonacci, Chase and Asami, Takeshi and Assaf,
Michal and Barber, Jacques P. and Bauer, Jochen and
Bavdekar, Shreya Y. and Beesdo-Baum, Katja and Benedetti,
Francesco and Bernstein, Rachel and Björkstrand, Johannes
and Blair, Robert J. and Blair, Karina S. and Blanco-Hinojo,
Laura and Böhnlein, Joscha and Brambilla, Paolo and
Bressan, Rodrigo A. and Breuer, Fabian and Cano, Marta and
Canu, Elisa and Cardinale, Elise M. and Cardoner, Narcís
and Cividini, Camilla and Cremers, Henk and Dannlowski, Udo
and Diefenbach, Gretchen J. and Domschke, Katharina and
Doruyter, Alexander G. G. and Dresler, Thomas and Erhardt,
Angelika and Filippi, Massimo and Fonzo, Gregory A. and
Freitag, Gabrielle F. and Furmark, Tomas and Ge, Tian and
Gerber, Andrew J. and Gosnell, Savannah N. and Grabe, Hans
and Grotegerd, Dominik and Gur, Ruben C. and Gur, Raquel E.
and Hamm, Alfons O. and Han, Laura K. M. and Harper,
Jennifer C. and Harrewijn, Anita and Heeren, Alexandre and
Hofmann, David and Jackowski, Andrea P. and Jahanshad, Neda
and Jett, Laura and Kaczkurkin, Antonia N. and Khosravi,
Parmis and Kingsley, Ellen N. and Kircher, Tilo and Kostic,
Milutin and Larsen, Bart and Lee, Sang-Hyuk and Leehr,
Elisabeth J. and Leibenluft, Ellen and Lochner, Christine
and Lui, Su and Maggioni, Eleonora and Manfro, Gisele G. and
Månsson, Kristoffer N. T. and Marino, Claire E. and Meeten,
Frances and Milrod, Barbara and Jovanovic, Ana Munjiza and
Mwangi, Benson and Myers, Michael J. and Neufang, Susanne
and Nielsen, Jared A. and Ohrmann, Patricia A. and
Ottaviani, Cristina and Paulus, Martin P. and Perino,
Michael T. and Phan, K. Luan and Poletti, Sara and
Porta-Casteràs, Daniel and Pujol, Jesus and Reinecke,
Andrea and Ringlein, Grace V. and Rjabtsenkov, Pavel and
Roelofs, Karin and Salas, Ramiro and Salum, Giovanni A. and
Satterthwaite, Theodore D. and Schrammen, Elisabeth and
Sindermann, Lisa and Smoller, Jordan W. and Soares, Jair C.
and Stark, Rudolf and Stein, Frederike and Straube, Thomas
and Straube, Benjamin and Strawn, Jeffrey R. and
Suarez-Jimenez, Benjamin and Sylvester, Chad M. and Talati,
Ardesheer and Thomopoulos, Sophia I. and Tükel, Raşit and
van Nieuwenhuizen, Helena and Werwath, Kathryn and Wittfeld,
Katharina and Wright, Barry and Wu, Mon-Ju and Yang, Yunbo
and Zilverstand, Anna and Zwanzger, Peter and Blackford,
Jennifer U. and Avery, Suzanne N. and Clauss, Jacqueline A.
and Lueken, Ulrike and Thompson, Paul M. and Pine, Daniel S.
and Stein, Dan J. and van der Wee, Nic J. A. and Veltman,
Dick J. and Aghajani, Moji},
title = {{B}rain-based classification of youth with anxiety
disorders: transdiagnostic examinations within the
{ENIGMA}-{A}nxiety database using machine learning},
journal = {Nature Mental Health},
volume = {2},
number = {1},
issn = {2731-6076},
address = {London},
publisher = {Nature Publishing Group UK},
reportid = {DZNE-2025-00711},
pages = {104 - 118},
year = {2024},
abstract = {Neuroanatomical findings on youth anxiety disorders are
notoriously difficult to replicate, small in effect size and
have limited clinical relevance. These concerns have
prompted a paradigm shift toward highly powered (that is,
big data) individual-level inferences, which are data
driven, transdiagnostic and neurobiologically informed. Here
we built and validated supervised neuroanatomical machine
learning models for individual-level inferences, using a
case–control design and the largest known neuroimaging
database on youth anxiety disorders: the ENIGMA-Anxiety
Consortium (N = 3,343; age = 10–25 years; global
sites = 32). Modest, yet robust, brain-based
classifications were achieved for specific anxiety disorders
(panic disorder), but also transdiagnostically for all
anxiety disorders when patients were subgrouped according to
their sex, medication status and symptom severity (area
under the receiver operating characteristic curve,
0.59–0.63). Classifications were driven by neuroanatomical
features (cortical thickness, cortical surface area and
subcortical volumes) in fronto-striato-limbic and
temporoparietal regions. This benchmark study within a
large, heterogeneous and multisite sample of youth with
anxiety disorders reveals that only modest classification
performances can be realistically achieved with machine
learning using neuroanatomical data.},
cin = {AG Grabe},
ddc = {610},
cid = {I:(DE-2719)5000001},
pnm = {353 - Clinical and Health Care Research (POF4-353)},
pid = {G:(DE-HGF)POF4-353},
typ = {PUB:(DE-HGF)16},
doi = {10.1038/s44220-023-00173-2},
url = {https://pub.dzne.de/record/279183},
}