Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2020 Oct 8;10(1):342.
doi: 10.1038/s41398-020-01013-y.

Structural neuroimaging biomarkers for obsessive-compulsive disorder in the ENIGMA-OCD consortium: medication matters

Willem B Bruin  1 , Luke Taylor  2 , Rajat M Thomas  3 , Jonathan P Shock  4 , Paul Zhutovsky  3 , Yoshinari Abe  5 , Pino Alonso  6   7   8 , Stephanie H Ameis  9   10 , Alan Anticevic  11 , Paul D Arnold  12   13 , Francesca Assogna  14 , Francesco Benedetti  15 , Jan C Beucke  16   17 , Premika S W Boedhoe  18   19 , Irene Bollettini  15 , Anushree Bose  20 , Silvia Brem  21   22 , Brian P Brennan  23 , Jan K Buitelaar  24   25 , Rosa Calvo  26   27   28 , Yuqi Cheng  29 , Kang Ik K Cho  30 , Sara Dallaspezia  15 , Damiaan Denys  3   31 , Benjamin A Ely  32 , Jamie D Feusner  33 , Kate D Fitzgerald  34 , Jean-Paul Fouche  35 , Egill A Fridgeirsson  3 , Patricia Gruner  11 , Deniz A Gürsel  36   37 , Tobias U Hauser  21   38   39 , Yoshiyuki Hirano  40 , Marcelo Q Hoexter  41 , Hao Hu  42 , Chaim Huyser  43   44 , Iliyan Ivanov  45 , Anthony James  46 , Fern Jaspers-Fayer  47 , Norbert Kathmann  16 , Christian Kaufmann  16 , Kathrin Koch  36   37 , Masaru Kuno  40 , Gerd Kvale  48   49 , Jun Soo Kwon  50   51 , Yanni Liu  34 , Christine Lochner  52 , Luisa Lázaro  26   27   28   53 , Paulo Marques  54   55   56 , Rachel Marsh  57   58 , Ignacio Martínez-Zalacaín  6   8 , David Mataix-Cols  59 , José M Menchón  6   7   8 , Luciano Minuzzi  60 , Pedro S Moreira  54   55   56 , Astrid Morer  26   27   28   53 , Pedro Morgado  54   55   56 , Akiko Nakagawa  40 , Takashi Nakamae  5 , Tomohiro Nakao  61 , Janardhanan C Narayanaswamy  20 , Erika L Nurmi  33 , Joseph O'Neill  62 , Jose C Pariente  63 , Chris Perriello  23   64 , John Piacentini  33 , Fabrizio Piras  14 , Federica Piras  14 , Y C Janardhan Reddy  20 , Oana G Rus-Oswald  65   66 , Yuki Sakai  5   67 , João R Sato  68 , Lianne Schmaal  69   70 , Eiji Shimizu  40   71 , H Blair Simpson  57   72 , Noam Soreni  73   74 , Carles Soriano-Mas  6   7   75 , Gianfranco Spalletta  14   76 , Emily R Stern  77   78 , Michael C Stevens  79   80 , S Evelyn Stewart  47   81   82 , Philip R Szeszko  83   84 , David F Tolin  85   86 , Ganesan Venkatasubramanian  20 , Zhen Wang  42   87 , Je-Yeon Yun  88   89 , Daan van Rooij  90 ; ENIGMA-OCD Working Group; Paul M Thompson  91 , Odile A van den Heuvel  18   19 , Dan J Stein  92 , Guido A van Wingen  93
Collaborators, Affiliations

Structural neuroimaging biomarkers for obsessive-compulsive disorder in the ENIGMA-OCD consortium: medication matters

Willem B Bruin et al. Transl Psychiatry. .

Abstract

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.

PubMed Disclaimer

Conflict of interest statement

Dr. Baker has received research support from the National Institute of Mental Health (NIMH) and Valera Health. Dr. Brennan has received consulting fees from Rugen Therapeutics and Nobilis Therapeutics and research grant support from Eli Lilly, Transcept Pharmaceuticals, and Biohaven Pharmaceuticals. Dr. Walitza has received lecture honoraria Opopharma in the last 3 years. Her work was supported in the last 3 years by the Swiss National Science Foundation (SNF), diverse EU FP7s, HSM Hochspezialisierte Medizin of the Kanton Zurich, Switzerland, Bfarm Germany, Zinep, Hartmann Müller Stiftung, Olga Mayenfisch. Dr. Dan J. Stein has received research grants and/or consultancy honoraria from Lundbeck and Sun in the past 3 years. Dr. Paul M. Thompson has received research grant support from Biogen, Inc., for research unrelated to the topic of this manuscript. Dr. Ivanov has received honoraria from Lundbeck as a member of the Data Safety Monitoring Committee and research grants from the National Institute on Drug Abuse in the last 3 years. Dr. Pittenger has received research support and/or honoraria for consultation from Biohaven Pharmaceuticals, Blackthorn Therapeutics, Abide Therapeutics, and Brainsway, and royalties or honoraria from Oxford University Press and Elsevier in the past 3 years. Dr. Feusner has received an honorarium from Pfizer and consultation fees from NOCD, Inc. Dr. Piacentini has received research support from Pfizer Pharmaceuticals for research unrelated to the topic of this manuscript. Dr. Soreni has received support for Investigator Initiated Clinical Trial from Lundbeck LLC unrelated to the topic of this study. Dr. Buitelaar has been in the past 3 years a consultant to/member of advisory board of/and/or speaker for Shire, Roche, Medice, and Servier. He is not an employee of any of these companies, and not a stock shareholder of any of these companies. He has no other financial or material support, including expert testimony, patents, royalties. Dr. Mataix-Cols receives royalties for contributing articles to UpToDate (Wolters Kluwer Health), and for editorial work from Elsevier, all unrelated to the current work. In the last three years, Dr. Simpson has received research support for an industry-sponsored clinical trial from Biohaven Pharmaceuticals, royalties from UpToDate, Inc, and a stipend from JAMA Psychiatry for her role as Associate Editor. Dr. Tolin has received research support from Biohaven Pharmaceuticals. All other individually-named authors in- and outside of the ENIGMA-OCD working group reported no biomedical financial interests or potential conflicts of interest.

Figures

Fig. 1
Fig. 1. Performance for multi-site classification using different algorithms and cross-validation schemes.
Boxplots summarize AUC scores obtained across CV-folds; dashed line represents chance-level performance and asterisks indicate scores significantly different from chance (Mann–Whitney-U statistic; p < 0.05 Bonferroni corrected (10 classifiers × 3 CV types), see Supplement for details). SVM Support Vector Machine, PCA Principal Component Analysis, RBF Radial Basis Function, LR Logistic Regression, GPC Gaussian Processes Classification, RFC Random Forest Classifier, XGB XGBoost, NN Neural Network.
Fig. 2
Fig. 2. Scatterplot illustrating relationship between number of participants and classification performance across sites.
Only RFC classifier performance averaged across CV-folds and repeats are plotted (Spearman correlation; rS = 0.37, p = 0.014).
Fig. 3
Fig. 3. Performance for classification between subgroups of patients based on medication status.
Only RFC classifier performance for combined (pediatric and adult) data is shown here; Boxplots summarize AUC scores obtained across CV-folds; dashed line represents chance-level performance and asterisks indicate scores significantly different from chance (Mann–Whitney-U statistic; p < 0.05 Bonferroni corrected (10 classifiers × 3 CV types), see Supplement for details). unmed unmedicated, med medicated.
See this image and copyright information in PMC

References

    1. Ruscio AM, et al. The epidemiology of obsessive-compulsive disorder in the National Comorbidity Survey Replication. Psychiatry Res. 2010;15:513–517. - PMC - PubMed
    1. American Psychiatric Association. Diagnostic and statistical manual of mental disorders, 5th edn. (DSM-5). Diagn. Stat. Man. Ment. Disord.280, 10.1176/appi.books.9780890425596.744053. (2013).
    1. Abramowitz JS, Taylor S, McKay D. Obsessive-compulsive disorder. Lancet. 2009;374:491–499. doi: 10.1016/S0140-6736(09)60240-3. - DOI - PubMed
    1. Menzies L, et al. Integrating evidence from neuroimaging and neuropsychological studies of obsessive-compulsive disorder: the orbitofronto-striatal model revisited. Neurosci. Biobehav. Rev. 2008;32:525–549. doi: 10.1016/j.neubiorev.2007.09.005. - DOI - PMC - PubMed
    1. van den Heuvel OA, et al. Brain circuitry of compulsivity. Eur. Neuropsychopharmacol. 2016;26:810–827. doi: 10.1016/j.euroneuro.2015.12.005. - DOI - PubMed

Publication types

MeSH terms