Indexed in

License and use

Citations

Cited 3 times in

Cited 4 times in

Cited 4 times in

Altmetrics

Grant support

Open Access funding enabled and organized by Seoul National University., This work was supported by the National Research Foundation of Korea(NRF) grant funded by the Korean government(MSIT) (No. 2019H1D3A2A01102270, 2021R1C1C1006503, 2021K1A3A1A2103751212, 2021M3E5D2A01022515, RS-2023-00266787, RS-2023-00265406), Creative-Pioneering Researchers Program through Seoul National University (No. 200-20230058), Semi-Supervised Learning Research Grant by SAMSUNG (No.A0426-20220118), Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government(M-SIT) [NO.2021-0-01343, Artificial Intelligence Graduate School Program (Seoul National University)], and the H2O.ai Academic Program at H2O Inc., CA, USA to JC; by Grant No. K01MH122774 and Brain and Behavior Research Foundation Grant 07040 to XZ, Grant No. R01MH116147, P41EB015922 to PMT, funding of Michael Smith Health Research BC to Dr. FJ-F, IOCDF Innovator Award 2021 to CV, AMED Brain/MINDS Beyond Program Grant No. JP22dm0307002, JSPS KAKENHI Grants No. 22H01090, 19K03309 to YH (PI), FAPESP 18/21934-5 and 21/05331-8 to JRS, PI19/01171, 2017 SGR 1247 to CS-M, JP22dm0307008 to YS; SR/S0/HS/0016/2011, BT/PR13334/Med/30/259/2009 to YCJR, DST INSPIRE faculty grant IFA12-LSBM-26, BT/06/IYBA/2012 to JCN by the India government; the Wellcome-DBT India Alliance grant to GV (500236/Z/11/Z); Marato TV3 Foundation Grant 091510 and Carlos III Health Institute PI11/01419 to RC; K24MH121571 from U.S. National Institute of Mental Health to CPittenger; the Japan Society for the Promotion of Science (KAKENHI Grant No. 18K15523) to YA; European Union projects TACTICS (grant 278948) and CANDY (grant 847818) to JKB; Rio Hortega grant (CM21/00278) to SBertolin; Sao Paulo Research Foundation (FAPESP grants #2018/21934-5 and #2021/05332-8); the Wellcome Trust-DBT India Alliance Early Career Fellowship grant (IA/CPHE/18/1/503956) to VS; National Research Foundation of South Africa (Grants No. 78829) to CL; Scientific productivity grant from National Council for Scientific and Technological Development (CNP)#307386/2021-0 to RGS; the British Columbia Children's Hospital to SES.

Analysis of institutional authors

Share

White matter diffusion estimates in obsessive-compulsive disorder across 1653 individuals: machine learning findings from the ENIGMA OCD Working Group

Publicated to:Molecular Psychiatry. 29 (4): 1063-1074 - 2024-02-07 29(4), DOI: 10.1038/s41380-023-02392-6

Authors: Kim, Bo-Gyeom; Kim, Gakyung; Abe, Yoshinari; Alonso, Pino; Ameis, Stephanie; Anticevic, Alan; Arnold, Paul D; Balachander, Srinivas; Banaj, Nerisa; Bargallo, Nuria; Batistuzzo, Marcelo C; Benedetti, Francesco; Bertolin, Sara; Beucke, Jan Carl; Bollettini, Irene; Brem, Silvia; Brennan, Brian P; Buitelaar, Jan K; Calvo, Rosa; Castelo-Branco, Miguel; Cheng, Yuqi; Chhatkuli, Ritu Bhusal; Ciullo, Valentina; Coelho, Ana; Couto, Beatriz; Dallaspezia, Sara; Ely, Benjamin A; Ferreira, Sonia; Fontaine, Martine; Fouche, Jean-Paul; Grazioplene, Rachael; Gruner, Patricia; Hagen, Kristen; Hansen, Bjarne; Hanna, Gregory L; Hirano, Yoshiyuki; Hoxter, Marcelo Q; Hough, Morgan; Hu, Hao; Huyser, Chaim; Ikuta, Toshikazu; Jahanshad, Neda; James, Anthony; Jaspers-Fayer, Fern; Kasprzak, Selina; Kathmann, Norbert; Kaufmann, Christian; Kim, Minah; Koch, Kathrin; Kvale, Gerd; Kwon, Jun Soo; Lazaro, Luisa; Lee, Junhee; Lochner, Christine; Lu, Jin; Manrique, Daniela Rodriguez; Martinez-Zalacain, Ignacio; Masuda, Yoshitada; Matsumoto, Koji; Maziero, Maria Paula; Menchon, Jose M; Minuzzi, Luciano; Moreira, Pedro Silva; Morgado, Pedro; Narayanaswamy, Janardhanan C; Narumoto, Jin; Ortiz, Ana E; Ota, Junko; Pariente, Jose C; Perriello, Chris; Pico-Perez, Maria; Pittenger, Christopher; Poletti, Sara; Real, Eva; Reddy, Y C Janardhan; van Rooij, Daan; Sakai, Yuki; Sato, Joao Ricardo; Segalas, Cinto; Shavitt, Roseli G; Shen, Zonglin; Shimizu, Eiji; Shivakumar, Venkataram; Soriano-Mas, Carles; Sousa, Nuno; Sousa, Mafalda Machado; Spalletta, Gianfranco; Stern, Emily R; Stewart, S Evelyn; Szeszko, Philip R; Thomas, Rajat; Thomopoulos, Sophia I; Vecchio, Daniela; Venkatasubramanian, Ganesan; Vriend, Chris; Walitza, Susanne; Wang, Zhen; Watanabe, Anri; Wolters, Lidewij; Xu, Jian; Yamada, Kei; Yun, Je-Yeon; Zarei, Mojtaba; Zhao, Qing; Zhu, Xi; Thompson, Paul M; Bruin, Willem B; van Wingen, Guido A; Piras, Federica; Piras, Fabrizio; Stein, Dan J; van den Heuvel, Odile A; Simpson, Helen Blair; Marsh, Rachel; Cha, Jiook

Affiliations

Abstract

White matter pathways, typically studied with diffusion tensor imaging (DTI), have been implicated in the neurobiology of obsessive-compulsive disorder (OCD). However, due to limited sample sizes and the predominance of single-site studies, the generalizability of OCD classification based on diffusion white matter estimates remains unclear. Here, we tested classification accuracy using the largest OCD DTI dataset to date, involving 1336 adult participants (690 OCD patients and 646 healthy controls) and 317 pediatric participants (175 OCD patients and 142 healthy controls) from 18 international sites within the ENIGMA OCD Working Group. We used an automatic machine learning pipeline (with feature engineering and selection, and model optimization) and examined the cross-site generalizability of the OCD classification models using leave-one-site-out cross-validation. Our models showed low-to-moderate accuracy in classifying (1) "OCD vs. healthy controls" (Adults, receiver operator characteristic-area under the curve = 57.19 +/- 3.47 in the replication set; Children, 59.8 +/- 7.39), (2) "unmedicated OCD vs. healthy controls" (Adults, 62.67 +/- 3.84; Children, 48.51 +/- 10.14), and (3) "medicated OCD vs. unmedicated OCD" (Adults, 76.72 +/- 3.97; Children, 72.45 +/- 8.87). There was significant site variability in model performance (cross-validated ROC AUC ranges 51.6-79.1 in adults; 35.9-63.2 in children). Machine learning interpretation showed that diffusivity measures of the corpus callosum, internal capsule, and posterior thalamic radiation contributed to the classification of OCD from HC. The classification performance appeared greater than the model trained on grey matter morphometry in the prior ENIGMA OCD study (our study includes subsamples from the morphometry study). Taken together, this study points to the meaningful multivariate patterns of white matter features relevant to the neurobiology of OCD, but with low-to-moderate classification accuracy. The OCD classification performance may be constrained by site variability and medication effects on the white matter integrity, indicating room for improvement for future research.

Keywords