Journal Article

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

Perriello, Chris, Nakagawa, Akiko, James, Anthony, Kvale, Gerd, Lochner, Christine, Wang, Zhen, Nurmi, Erika L., Menchón, José M., Ely, Benjamin A., Kaufmann, Christian, van Rooij, Daan, Hoexter, Marcelo Q., Denys, Damiaan, Szeszko, Philip R., Taylor, Luke, Hu, Hao, Koch, Kathrin, Fitzgerald, Kate D., Morgado, Pedro, Stein, Dan J., Alonso, Pino, Sato, João R., Liu, Yanni, Yun, Je-Yeon, Simpson, H. Blair, Sakai, Yuki, Hirano, Yoshiyuki, Gürsel, Deniz A., Dallaspezia, Sara, Calvo, Rosa, Beucke, Jan C., Schmaal, Lianne, van den Heuvel, Odile A., Soriano-Mas, Carles, Stern, Emily R., Bollettini, Irene, Cho, Kang Ik K., Gruner, Patricia, Venkatasubramanian, Ganesan, Kuno, Masaru, Piras, Fabrizio, Jaspers-Fayer, Fern, Nakao, Tomohiro, Stewart, S. Evelyn, Soreni, Noam, Nakamae, Takashi, Narayanaswamy, Janardhanan C., Huyser, Chaim, Stevens, Michael C., Fridgeirsson, Egill A., van Wingen, Guido A., Piacentini, John, Ameis, Stephanie H., Anticevic, Alan, Cheng, Yuqi, Morer, Astrid, Arnold, Paul D., Brennan, Brian P., Mataix-Cols, David, Fouche, Jean-Paul, Benedetti, Francesco, Bruin, Willem B., Hauser, Tobias U., Thom

2020

Overview

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.

• Publisher: Nature Publishing Group UK
• Subject: 59/57 / 631/378 / 692/53/2421 / Behavioral Sciences / Biological Psychology / Biomarkers / Brain - diagnostic imaging / Humans / Magnetic Resonance Imaging / Medicine / Medicine & Public Health / Neuroimaging / Neurosciences / Obsessive-Compulsive Disorder - diagnostic imaging / Obsessive-Compulsive Disorder - drug therapy / Pharmacotherapy / Psychiatry