[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127764-en":3,"doc-seo-127764-105":30,"detail-sidebar-cat-0-en-105":84},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},127764,1099523882182,"Eliana","https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8",8,"Research & Report","White matter diffusion estimates in obsessive-compulsive disorder across 1653 individuals - machine learning findings from the ENIGMA OCD Working Group","White matter pathways assessed with diffusion tensor imaging are implicated in obsessive-compulsive disorder, but generalizability has been limited by small samples and single-site studies. This study evaluates OCD classification using the largest available OCD DTI dataset, covering 1653 participants from 18 international ENIGMA-OCD sites. An automatic machine learning pipeline with feature engineering and leave-one-site-out cross-validation shows low-to-moderate accuracy and significant site variability across adult and pediatric cohorts. Interpretation highlights corpus callosum, internal capsule, and posterior thalamic radiation diffusivity as contributing features, while performance is constrained by site variability and medication effects.","Molecular [Psychiatry](Psychiatry www.nature.com/mp)[ www.nature.com/mp](Psychiatry www.nature.com/mp)  \nARTICLE OPEN   \nWhite matter diffusion estimates in obsessive-compulsive disorder across 1653 individuals: machine learning findings from the ENIGMA OCD Working Group  \nBo-Gyeom Kim 1,148, Gakyung Kim2,148, Yoshinari Abe 3, Pino Alonso 4,5,6, Stephanie Ameis 7,8,9, Alan Anticevic 10, Paul D. Arnold 11,12, Srinivas Balachander 13, Nerisa Banaj 14, Nuria Bargalló15,16, Marcelo C. Batistuzzo 17,18,  \nFrancesco Benedetti 19,20, Sara Bertolín 5,21, Jan Carl Beucke22,23,24, Irene Bollettini 20, Silvia Brem25,26, Brian P. Brennan 27,28, Jan K. Buitelaar 29,30, Rosa Calvo 5,31,32,33, Miguel Castelo-Branco34,35,36, Yuqi Cheng37, Ritu Bhusal Chhatkuli38,39, Valentina Ciullo14, Ana Coelho40,41,42, Beatriz Couto40,41,42, Sara Dallaspezia43, Benjamin A. Ely 44, Sónia Ferreira40,41,42, Martine Fontaine45,  \nJean-Paul Fouche46, Rachael Grazioplene 10, Patricia Gruner10, Kristen Hagen47,48, Bjarne Hansen48,49, Gregory L. Hanna50, Yoshiyuki Hirano 38,39, Marcelo Q. Höxter17, Morgan Hough51, Hao Hu52, Chaim Huyser 53,54, Toshikazu Ikuta 55,  \nNeda Jahanshad56, Anthony James 57, Fern Jaspers-Fayer 58,59, Selina Kasprzak60,61, Norbert Kathmann22, Christian Kaufmann22, Minah Kim 62,63, Kathrin Koch 64,65, Gerd Kvale48,66, Jun Soo Kwon 63,67,68, Luisa Lazaro 5,31,32,33, Junhee Lee 62,69, Christine Lochner 70, Jin Lu71, Daniela Rodriguez Manrique64,65,72, Ignacio Martínez-Zalacaín 4,73, Yoshitada Masuda74,  \nKoji Matsumoto74, Maria Paula Maziero75,76, Jose M. Menchón 4,5,6, Luciano Minuzzi77,78, Pedro Silva Moreira 40,41,79,  \nPedro Morgado40,41,42, Janardhanan C. Narayanaswamy13, Jin Narumoto80, Ana E. Ortiz31,32,33, Junko Ota38,39, Jose C. Pariente 16, Chris Perriello81, Maria Picó-Pérez 40,41,82, Christopher Pittenger 10,83,84,85, Sara Poletti 20, Eva Real5,6, Y. C. Janardhan Reddy13, Daan van Rooij86, Yuki Sakai 80,87, João Ricardo Sato88,89, Cinto Segalas5,6, Roseli G. Shavitt90, Zonglin Shen37, Eiji Shimizu 38,39,91, Venkataram Shivakumar92, Noam Soreni93,94, Carles Soriano-Mas 5,6,95, Nuno Sousa 40,41,42, Mafalda Machado Sousa40,41,42, Gianfranco Spalletta14,96, Emily R. Stern97,98, S. Evelyn Stewart 58,99,100, Philip R. Szeszko 101,102, Rajat Thomas103,  \nSophia I. Thomopoulos56, Daniela Vecchio14, Ganesan Venkatasubramanian 13, Chris Vriend60,61,104, Susanne Walitza25,26, Zhen Wang 105, Anri Watanabe 80, Lidewij Wolters106, Jian Xu107, Kei Yamada 108, Je-Yeon Yun 109,110, Mojtaba Zarei111, Qing Zhao 105, Xi Zhu 112,113 and , ENIGMA-OCD Working Group*, Paul M. Thompson56, Willem B. Bruin104,114,  \nGuido A. van Wingen 104,114, Federica Piras 14, Fabrizio Piras 14, Dan J. Stein 115,116, Odile A. van den Heuvel 60,61, Helen Blair Simpson45, Rachel Marsh 45 and Jiook Cha 1,2 ✉  \n© The Author(s) 2024, corrected publication 2024  \n|  |  |  |\n| --- | --- | --- |\n|  | 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) “unmed","cbCaimczoooxGbDY","https://ap.wps.com/l/cbCaimczoooxGbDY","pdf",5732050,1,12,"English","en",105,"# Introduction\n## Study rationale and background\n# Methods\n## Dataset and participant cohorts\n## Machine learning pipeline and validation\n# Results\n## Cross-site classification performance\n## Feature contributions and interpretation\n## Comparison with prior ENIGMA findings\n# Discussion\n## Site variability, medication effects, and implications","[{\"question\":\"What factors limited classification performance?\",\"answer\":\"Classification accuracy showed low-to-moderate levels and appeared constrained by site variability and medication effects on white matter integrity, leaving room for improvement in future research.\"}]","White matter diffusion estimates in obsessive-compulsive disorder across 1653 individuals - machine learning findings from the ENIGMA OCD Working Group | PDF",1785941481,30,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":79,"head_meta":81,"extra_data":83,"updated_unix":28},"white-matter-diffusion-estimates-in-obsessive-compulsive-disorder-across-1653-individuals-machine-learning-findings-from-the-enigma-ocd-working-group","",{"@graph":36,"@context":78},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/white-matter-diffusion-estimates-in-obsessive-compulsive-disorder-across-1653-individuals-machine-learning-findings-from-the-enigma-ocd-working-group/127764/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-22","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72],{"name":73,"@type":74,"acceptedAnswer":75},"What factors limited classification performance?","Question",{"text":76,"@type":77},"Classification accuracy showed low-to-moderate levels and appeared constrained by site variability and medication effects on white matter integrity, leaving room for improvement in future research.","Answer","https://schema.org",{"og:url":52,"og:type":80,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":82,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":85},[86,90,94,98,103,108,113,115,120,123,127],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":87,"show_sort_weight":88,"slug":89},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":91,"show_sort_weight":92,"slug":93},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Exam",70,"exam",{"id":99,"doc_module":4,"doc_module_name":46,"category_name":100,"show_sort_weight":101,"slug":102},5,"Comic",60,"comic",{"id":104,"doc_module":4,"doc_module_name":46,"category_name":105,"show_sort_weight":106,"slug":107},6,"Technology",50,"technology",{"id":109,"doc_module":4,"doc_module_name":46,"category_name":110,"show_sort_weight":111,"slug":112},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":29,"slug":114},"research-report",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":99,"slug":130},19,"General","general"]