TY - JOUR
T1 - Neurostructural subgroup in 4291 individuals with schizophrenia identified using the subtype and stage inference algorithm
AU - ENIGMA Schizophrenia Consortium
AU - ZIB Consortium
AU - Jiang, Yuchao
AU - Luo, Cheng
AU - Wang, Jijun
AU - Palaniyappan, Lena
AU - Chang, Xiao
AU - Xiang, Shitong
AU - Zhang, Jie
AU - Duan, Mingjun
AU - Huang, Huan
AU - Gaser, Christian
AU - Nemoto, Kiyotaka
AU - Miura, Kenichiro
AU - Hashimoto, Ryota
AU - Westlye, Lars T.
AU - Richard, Genevieve
AU - Fernandez-Cabello, Sara
AU - Parker, Nadine
AU - Andreassen, Ole A.
AU - Kircher, Tilo
AU - Nenadić, Igor
AU - Stein, Frederike
AU - Thomas-Odenthal, Florian
AU - Teutenberg, Lea
AU - Usemann, Paula
AU - Dannlowski, Udo
AU - Hahn, Tim
AU - Grotegerd, Dominik
AU - Meinert, Susanne
AU - Lencer, Rebekka
AU - Tang, Yingying
AU - Zhang, Tianhong
AU - Li, Chunbo
AU - Yue, Weihua
AU - Zhang, Yuyanan
AU - Yu, Xin
AU - Zhou, Enpeng
AU - Lin, Ching Po
AU - Tsai, Shih Jen
AU - Rodrigue, Amanda L.
AU - Glahn, David
AU - Pearlson, Godfrey
AU - Blangero, John
AU - Karuk, Andriana
AU - Pomarol-Clotet, Edith
AU - Salvador, Raymond
AU - Fuentes-Claramonte, Paola
AU - Garcia-León, María Ángeles
AU - Spalletta, Gianfranco
AU - Piras, Fabrizio
AU - Chung, Young Chul
N1 - Publisher Copyright:
© The Author(s) 2024.
PY - 2024/12
Y1 - 2024/12
N2 - Machine learning can be used to define subtypes of psychiatric conditions based on shared biological foundations of mental disorders. Here we analyzed cross-sectional brain images from 4,222 individuals with schizophrenia and 7038 healthy subjects pooled across 41 international cohorts from the ENIGMA, non-ENIGMA cohorts and public datasets. Using the Subtype and Stage Inference (SuStaIn) algorithm, we identify two distinct neurostructural subgroups by mapping the spatial and temporal ‘trajectory’ of gray matter change in schizophrenia. Subgroup 1 was characterized by an early cortical-predominant loss with enlarged striatum, whereas subgroup 2 displayed an early subcortical-predominant loss in the hippocampus, striatum and other subcortical regions. We confirmed the reproducibility of the two neurostructural subtypes across various sample sites, including Europe, North America and East Asia. This imaging-based taxonomy holds the potential to identify individuals with shared neurobiological attributes, thereby suggesting the viability of redefining existing disorder constructs based on biological factors.
AB - Machine learning can be used to define subtypes of psychiatric conditions based on shared biological foundations of mental disorders. Here we analyzed cross-sectional brain images from 4,222 individuals with schizophrenia and 7038 healthy subjects pooled across 41 international cohorts from the ENIGMA, non-ENIGMA cohorts and public datasets. Using the Subtype and Stage Inference (SuStaIn) algorithm, we identify two distinct neurostructural subgroups by mapping the spatial and temporal ‘trajectory’ of gray matter change in schizophrenia. Subgroup 1 was characterized by an early cortical-predominant loss with enlarged striatum, whereas subgroup 2 displayed an early subcortical-predominant loss in the hippocampus, striatum and other subcortical regions. We confirmed the reproducibility of the two neurostructural subtypes across various sample sites, including Europe, North America and East Asia. This imaging-based taxonomy holds the potential to identify individuals with shared neurobiological attributes, thereby suggesting the viability of redefining existing disorder constructs based on biological factors.
UR - https://www.scopus.com/pages/publications/85199016346
U2 - 10.1038/s41467-024-50267-3
DO - 10.1038/s41467-024-50267-3
M3 - Journal article
C2 - 39013848
AN - SCOPUS:85199016346
SN - 2041-1723
VL - 15
JO - Nature Communications
JF - Nature Communications
IS - 1
M1 - 5996
ER -