Neuroimaging- and machine-learning-based brain-age prediction of schizophrenia is well established. However, the diagnostic significance and the effect of early medication on first-episode schizophrenia remains unclear.

To explore whether predicted brain age can be used as a biomarker for schizophrenia diagnosis, and the relationship between clinical characteristics and brain-predicted age difference (PAD), and the effects of early medication on predicted brain age.

The predicted model was built on 523 diffusion tensor imaging magnetic resonance imaging scans from healthy controls. First, the brain-PAD of 60 patients with first-episode schizophrenia, 60 healthy controls and 21 follow-up patients from the principal data-set and 40 pairs of individuals in the replication data-set were calculated. Next, the brain-PAD between groups were compared and the correlations between brain-PAD and clinical measurements were analysed.

The patients showed a significant increase in brain-PAD compared with healthy controls. After early medication, the brain-PAD of patients decreased significantly compared with baseline (P < 0.001). The fractional anisotropy value of 31/33 white matter tract features, which related to the brain-PAD scores, had significantly statistical differences before and after measurements (P < 0.05, false discovery rate corrected). Correlation analysis showed that the age gap was negatively associated with the positive score on the Positive and Negative Syndrome Scale in the principal data-set (r = −0.326, P = 0.014).

The brain age of patients with first-episode schizophrenia may be older than their chronological age. Early medication holds promise for improving the patient's brain ageing. Neuroimaging-based brain-age prediction can provide novel insights into the understanding of schizophrenia.

Based on hubs of neural circuits associated with addiction and their degree centrality (DC), this study aimed to construct the addiction-related brain networks for patients diagnosed with heroin dependence undertaking stable methadone maintenance treatment (MMT) and further prospectively identify the ones at high risk for relapse with cluster analysis.

Sixty-two male MMT patients and 30 matched healthy controls (HC) underwent brain resting-state functional MRI data acquisition. The patients received 26-month follow-up for the monthly illegal-drug-use information. Ten addiction-related hubs were chosen to construct a user-defined network for the patients. Then the networks were discriminated with K-means-clustering-algorithm into different groups and followed by comparative analysis to the groups and HC. Regression analysis was used to investigate the brain regions significantly contributed to relapse.

Sixty MMT patients were classified into two groups according to their brain-network patterns calculated by the best clustering-number-K. The two groups had no difference in the demographic, psychological indicators and clinical information except relapse rate and total heroin consumption. The group with high-relapse had a wider range of DC changes in the cortical−striatal−thalamic circuit relative to HC and a reduced DC in the mesocorticolimbic circuit relative to the low-relapse group. DC activity in NAc, vACC, hippocampus and amygdala were closely related with relapse.

MMT patients can be identified and classified into two subgroups with significantly different relapse rates by defining distinct brain-network patterns even if we are blind to their relapse outcomes in advance. This may provide a new strategy to optimize MMT.