Schizophrenia is a complex and heterogeneous syndrome with high clinical and biological stratification. Identifying distinctive subtypes can improve diagnostic accuracy and help precise therapy. A key challenge for schizophrenia subtyping is understanding the subtype-specific biological underpinnings of clinical heterogeneity. This study aimed to investigate if the machine learning (ML)-based neuroanatomical and symptomatic subtypes of schizophrenia are associated.

A total of 314 schizophrenia patients and 257 healthy controls from four sites were recruited. Gray matter volume (GMV) and Positive and Negative Syndrome Scale (PANSS) scores were employed to recognize schizophrenia neuroanatomical and symptomatic subtypes using K-means and hierarchical methods, respectively.

Patients with ML-based neuroanatomical subtype-1 had focally increased GMV, and subtype-2 had widespread reduced GMV than the healthy controls based on either K-means or Hierarchical methods. In contrast, patients with symptomatic subtype-1 had severe PANSS scores than subtype-2. No differences in PANSS scores were shown between the two neuroanatomical subtypes; similarly, no GMV differences were found between the two symptomatic subtypes. Cohen’s Kappa test further demonstrated an apparent dissociation between the ML-based neuroanatomical and symptomatic subtypes (P > 0.05). The dissociation patterns were validated in four independent sites with diverse disease progressions (chronic vs. first episodes) and ancestors (Chinese vs. Western).

These findings revealed a replicable dissociation between ML-based neuroanatomical and symptomatic subtypes of schizophrenia, which provides a new viewpoint toward understanding the heterogeneity of schizophrenia.

Major depressive disorder (MDD) is a common debilitating disorder characterized by impaired spontaneous brain activity, yet little is known about its alterations in dynamic properties and the molecular mechanisms associated with these changes.

Based on the resting-state functional MRI data of 65 first-episode, treatment-naïve patients with MDD and 66 healthy controls, we compared dynamic regional homogeneity (dReHo) of spontaneous brain activity between the two groups, and we investigated gene expression profiles associated with dReHo alterations in MDD by leveraging transcriptional data from the Allen Human Brain Atlas and weighted gene co-expression network analysis.

Compared with healthy controls, patients with MDD consistently showed reduced dReHo in both fusiform gyri and in the right temporal pole and hippocampus. The expression profiles of 16 gene modules were correlated with dReHo alterations in MDD. These gene modules were enriched for various biological process terms, including immune, synaptic signalling, ion channels, mitochondrial function and protein metabolism, and were preferentially expressed in different cell types.

Patients with MDD have reduced dReHo in brain areas associated with emotional and cognitive regulation, and these changes may be related to complex polygenetic and polypathway mechanisms.