Neurostructural subgroup in 4291 individuals with schizophrenia identified using the subtype and stage inference algorithm

Abstract

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.

Fig. 1. Two pathophysiological progression trajectories in schizophrenia.

a Dice coefficient indicates that K = 2 is the optimal number (marked by asterisk) of subtypes with best consistency of the subtype labeling between two independent schizophrenia populations using non-overlap 2-folds cross-validation procedure. This procedure was repeated ten times (n = 10) to avoid the occasionality of one split. Data are presented as median values +/- standard deviation (SD). b The proportion of individuals whose subtype labels keep consistent by a non-overlap cross-validation procedure. c Sequences of regional volume loss across seventeen brain regions for each ‘trajectory’ via SuStaIn are shown in y-axis. The heatmap shows regional volume loss in which biomarker (y-axis) in a particular ‘temporal’ stage (T0-T16) in the ‘trajectory’ (x-axis). The Color bar represents the degree of gray matter volume (GMV) loss in schizophrenia relative to healthy controls (i.e., z score). d Spatiotemporal pattern of pathophysiological ‘trajectory’. The z-score images are mapped to a glass brain template for visualization. The spatiotemporal pattern of gray matter loss displays a progressive pattern of spatial extension along with later ‘temporal’ stages of pathological progression that are distinct between trajectories. e–f Pathological stages of SuStaIn are correlated with reduced gray matter volume of Broca’s area and hippocampus. g–i Pathological stages of SuStaIn are correlated with longer disease duration, worse negative symptoms and worse cognitive symptoms. Spearman correlation test is conducted for data analysis in figures (e–i). Two-sided p value is reported after multiple comparisons correction by FDR. The error bands in figures (e–i) represent 95% confidence interval. n = 4222 biologically independent samples in figures (e–f). n = 2333 biologically independent samples in figure (g). n = 2651 biologically independent samples in figure (h). n = 1322 biologically independent samples in figure (i).

Fig. 2. Trajectories are reproducibility for samples from different locations of the world.

Two sets of ‘trajectories’ are separately derived from two non-overlapping location cohorts, that are (a) East Asian ancestry (EAS) cohort, and (b) European ancestry (EUR) cohort. The Color bar represents the degree of gray matter volume (GMV) loss in schizophrenia relative to healthy controls (i.e., z-score). c The similarity of the spatiotemporal pattern of each ‘trajectory’ between any two of cohorts is shown by the heatmap. The color bar of the heatmap represents the similarity, which is quantified via the Spearman correlation coefficient between the trajectories from two cohorts. A total of six location cohorts are classified by where the sample locate at, including the EAS, EUR, China, Japan, Europe and North American. The whole sample is labeled as a cross-ancestry cohort.

Fig. 3. Subtype-specific signatures in neuroanatomical pathology.

Brain morphological measures include (a) cortical thickness, (b) cortical surface area, (c) cortical volume, and (d) subcortical volume. For each morphological measure, regional z-scores (i.e., normative deviations from healthy control group) in each subtype are mapped to a brain template for visualization. Effect size of inter-subtype difference is quantified using Cohen’s d.

Fig. 4. Symptomatic trajectories across three stages of disease duration.

Individuals of each subtype are divided into three subgroups according to their illness durations (early stage: ≤2 years; middle stage: 2−10 years; late stage: >10 years). Two sample t test was performed to compare the inter-subtype difference separately within each of the stages after regressing out the effects of age, sex and SuStaIn stage. * two-sided p < 0.05, uncorrected. At the late stage, subtype 1 exhibited worse positive symptom (t = 2.9, p = 0.003), general psychopathology (t = 2.5, p = 0.010) and worse depression/anxiety (t = 2.1, p = 0.033) compared to subtype 2. Data are presented as mean values +/- standard error (se). n = 579 (347), 362 (216), and 400 (282) biologically independent samples in the early stage, middle stage and late stage in subtype 1 (subtype 2) for positive, negative and general subscales. n = 377 (220), 144 (86), and 166 (109) biologically independent samples in the early stage, middle stage and late stage in subtype 1 (subtype 2) for depression & anxiety, cognitive dimension and excitement dimension.