TY - JOUR
T1 - Structural neuroimaging biomarkers for obsessive-compulsive disorder in the ENIGMA-OCD consortium
T2 - medication matters
AU - Bruin, Willem B.
AU - Taylor, Luke
AU - Thomas, Rajat M.
AU - Shock, Jonathan P.
AU - Zhutovsky, Paul
AU - Abe, Yoshinari
AU - Alonso, Pino
AU - Ameis, Stephanie H.
AU - Anticevic, Alan
AU - Arnold, Paul D.
AU - Assogna, Francesca
AU - Benedetti, Francesco
AU - Beucke, Jan C.
AU - Boedhoe, Premika S. W.
AU - Bollettini, Irene
AU - Bose, Anushree
AU - Brem, Silvia
AU - Brennan, Brian P.
AU - Buitelaar, Jan K.
AU - Calvo, Rosa
AU - Cheng, Yuqi
AU - Cho, Kang Ik K.
AU - Dallaspezia, Sara
AU - Denys, Damiaan
AU - Ely, Benjamin A.
AU - Feusner, Jamie D.
AU - Fitzgerald, Kate D.
AU - Fouche, Jean-Paul
AU - Fridgeirsson, Egill A.
AU - Gruner, Patricia
AU - Gürsel, Deniz A.
AU - Hauser, Tobias U.
AU - Hirano, Yoshiyuki
AU - Hoexter, Marcelo Q.
AU - Hu, Hao
AU - Huyser, Chaim
AU - Ivanov, Iliyan
AU - James, Anthony
AU - Jaspers-Fayer, Fern
AU - Kathmann, Norbert
AU - Kaufmann, Christian
AU - Koch, Kathrin
AU - Kuno, Masaru
AU - Kvale, Gerd
AU - Kwon, Jun Soo
AU - Liu, Yanni
AU - Schmaal, Lianne
AU - Figee, Martijn
AU - ENIGMA-OCD working group
AU - van Wingen, Guido A.
AU - van Wingen, Guido A.
AU - ENIGMA OCD Working Group
AU - Lochner, Christine
AU - Lázaro, Luisa
AU - van den Heuvel, Odile A
PY - 2020/12/1
Y1 - 2020/12/1
N2 - No diagnostic biomarkers are available for obsessive-compulsive disorder (OCD). Here, we aimed to identify magnetic resonance imaging (MRI) biomarkers for OCD, using 46 data sets with 2304 OCD patients and 2068 healthy controls from the ENIGMA consortium. We performed machine learning analysis of regional measures of cortical thickness, surface area and subcortical volume and tested classification performance using cross-validation. Classification performance for OCD vs. controls using the complete sample with different classifiers and cross-validation strategies was poor. When models were validated on data from other sites, model performance did not exceed chance-level. In contrast, fair classification performance was achieved when patients were grouped according to their medication status. These results indicate that medication use is associated with substantial differences in brain anatomy that are widely distributed, and indicate that clinical heterogeneity contributes to the poor performance of structural MRI as a disease marker.
AB - No diagnostic biomarkers are available for obsessive-compulsive disorder (OCD). Here, we aimed to identify magnetic resonance imaging (MRI) biomarkers for OCD, using 46 data sets with 2304 OCD patients and 2068 healthy controls from the ENIGMA consortium. We performed machine learning analysis of regional measures of cortical thickness, surface area and subcortical volume and tested classification performance using cross-validation. Classification performance for OCD vs. controls using the complete sample with different classifiers and cross-validation strategies was poor. When models were validated on data from other sites, model performance did not exceed chance-level. In contrast, fair classification performance was achieved when patients were grouped according to their medication status. These results indicate that medication use is associated with substantial differences in brain anatomy that are widely distributed, and indicate that clinical heterogeneity contributes to the poor performance of structural MRI as a disease marker.
UR - http://www.scopus.com/inward/record.url?scp=85092536771&partnerID=8YFLogxK
U2 - https://doi.org/10.1038/s41398-020-01013-y
DO - https://doi.org/10.1038/s41398-020-01013-y
M3 - Article
C2 - 33033241
SN - 2158-3188
VL - 10
SP - 342
JO - Translational Psychiatry
JF - Translational Psychiatry
IS - 1
M1 - 342
ER -