Author:
Jiang Yuchao,Luo Cheng,Wang Jijun,Palaniyappan Lena,Chang Xiao,Xiang Shitong,Zhang Jie,Duan Mingjun,Huang Huan,Gaser Christian,Nemoto Kiyotaka,Miura Kenichiro,Hashimoto Ryota,Westlye Lars T.,Richard Genevieve,Fernandez-Cabello Sara,Parker Nadine,Andreassen Ole A.,Kircher Tilo,Nenadić Igor,Stein Frederike,Thomas-Odenthal Florian,Teutenberg Lea,Usemann Paula,Dannlowski Udo,Hahn Tim,Grotegerd Dominik,Meinert Susanne,Lencer Rebekka,Tang Yingying,Zhang Tianhong,Li Chunbo,Yue Weihua,Zhang Yuyanan,Yu Xin,Zhou Enpeng,Lin Ching-Po,Tsai Shih-Jen,Rodrigue Amanda L.,Glahn David,Pearlson Godfrey,Blangero John,Karuk Andriana,Pomarol-Clotet Edith,Salvador Raymond,Fuentes-Claramonte Paola,Garcia-León María Ángeles,Spalletta Gianfranco,Piras Fabrizio,Vecchio Daniela,Banaj Nerisa,Cheng Jingliang,Liu Zhening,Yang Jie,Gonul Ali Saffet,Uslu Ozgul,Burhanoglu Birce Begum,Demir Aslihan Uyar,Rootes-Murdy Kelly,Calhoun Vince D.,Sim Kang,Green Melissa,Quidé Yann,Chung Young Chul,Kim Woo-Sung,Sponheim Scott R.,Demro Caroline,Ramsay Ian S.,Iasevoli Felice,Bartolomeis Andrea de,Barone Annarita,Ciccarelli Mariateresa,Brunetti Arturo,Cocozza Sirio,Pontillo Giuseppe,Tranfa Mario,Park Min Tae M.,Kirschner Matthias,Georgiadis Foivos,Kaiser Stefan,Rheenen Tamsyn E Van,Rossell Susan L,Hughes Matthew,Woods William,Carruthers Sean P,Sumner Philip,Ringin Elysha,Spaniel Filip,Skoch Antonin,Tomecek David,Homan Philipp,Homan Stephanie,Omlor Wolfgang,Cecere Giacomo,Nguyen Dana D,Preda Adrian,Thomopoulos Sophia,Jahanshad Neda,Cui Long-Biao,Yao Dezhong,Thompson Paul M.,Turner Jessica A.,van Erp Theo G.M.,Cheng Wei,Feng Jianfeng, ,
Abstract
AbstractMachine learning can be used to define subtypes of psychiatric conditions based on shared clinical and biological foundations, presenting a crucial step toward establishing biologically based subtypes of mental disorders. With the goal of identifying subtypes of disease progression in schizophrenia, here we analyzed cross-sectional brain structural magnetic resonance imaging (MRI) data from 4,291 individuals with schizophrenia (1,709 females, age=32.5 years±11.9) and 7,078 healthy controls (3,461 females, age=33.0 years±12.7) pooled across 41 international cohorts from the ENIGMA Schizophrenia Working Group, non-ENIGMA cohorts and public datasets. Using a machine learning approach known as Subtype and Stage Inference (SuStaIn), we implemented a brain imaging-driven classification that identifies two distinct neurostructural subgroups by mapping the spatial and temporal trajectory of gray matter (GM) loss in schizophrenia. Subgroup 1 (n=2,622) was characterized by an early cortical-predominant loss (ECL) with enlarged striatum, whereas subgroup 2 (n=1,600) displayed an early subcortical-predominant loss (ESL) in the hippocampus, amygdala, thalamus, brain stem and striatum. These reconstructed trajectories suggest that the GM volume reduction originates in the Broca’s area/adjacent fronto-insular cortex for ECL and in the hippocampus/adjacent medial temporal structures for ESL. With longer disease duration, the ECL subtype exhibited a gradual worsening of negative symptoms and depression/anxiety, and less of a decline in positive symptoms. We confirmed the reproducibility of these imaging-based subtypes across various sample sites, independent of macroeconomic and ethnic factors that differed across these geographic locations, which include Europe, North America and East Asia. These findings underscore the presence of distinct pathobiological foundations underlying schizophrenia. This new imaging-based taxonomy holds the potential to identify a more homogeneous sub-population of individuals with shared neurobiological attributes, thereby suggesting the viability of redefining existing disorder constructs based on biological factors.
Publisher
Cold Spring Harbor Laboratory