A lack of a sufficiently large sample at single sites causes poor generalizability in automatic diagnosis classification of heterogeneous psychiatric disorders such as schizophrenia based on brain imaging scans. Advanced deep learning methods may be capable of learning subtle hidden patterns from high dimensional imaging data, overcome potential site-related variation, and achieve reproducible cross-site classification. However, deep learning-based cross-site transfer classification, despite less imaging site-specificity and more generalizability of diagnostic models, has not been investigated in schizophrenia. A large multi-site functional MRI sample (n = 734, including 357 schizophrenic patients from seven imaging resources) was collected, and a deep discriminant autoencoder network, aimed at learning imaging site-shared functional connectivity features, was developed to discriminate schizophrenic individuals from healthy controls. Accuracies of approximately 85·0% and 81·0% were obtained in multi-site pooling classification and leave-site-out transfer classification, respectively. The learned functional connectivity features revealed dysregulation of the cortical-striatal-cerebellar circuit in schizophrenia, and the most discriminating functional connections were primarily located within and across the default, salience, and control networks. The findings imply that dysfunctional integration of the cortical-striatal-cerebellar circuit across the default, salience, and control networks may play an important role in the "disconnectivity" model underlying the pathophysiology of schizophrenia. The proposed discriminant deep learning method may be capable of learning reliable connectome patterns and help in understanding the pathophysiology and achieving accurate prediction of schizophrenia across multiple independent imaging sites.

Aims: The burden of mental disorders is increasing worldwide, thus, affecting society and healthcare systems. This study investigated the independent influences of age, period and cohort on the global prevalence of mental disorders from 1990 to 2019; compared them by sex; and predicted the future burden of mental disorders in the next 25 years. Methods: The age-specific and sex-specific incidence of mental disorders worldwide was analysed according to the general analysis strategy used in the Global Burden of Disease Study in 2019. The incidence and mortality trends of mental disorders from 1990 to 2019 were evaluated through joinpoint regression analysis. The influences of age, period and cohort on the incidence of mental disorders were evaluated with an age–period–cohort model. Results: From 1990 to 2019, the sex-specific age-standardized incidence and disability-adjusted life years (DALY) rate decreased slightly. Joinpoint regression analysis from 1990 to 2019 indicated four turning points in the male DALY rate and five turning points in the female DALY rate. In analysis of age effects, the relative risk (RR) of incidence and the DALY rate in mental disorders in men and women generally showed an inverted U-shaped pattern with increasing age. In analysis of period effects, the incidence of mental disorders increased gradually over time, and showed a sub-peak in 2004 (RR, 1.006 for males; 95% CI, 1.000–1.012; 1.002 for women, 0.997–1.008). Analysis of cohort effects showed that the incidence and DALY rate decreased in successive birth cohorts. The incidence of mental disorders is expected to decline slightly over the next 25 years, but the number of cases is expected to increase. Conclusions: Although the age-standardized burden of mental disorders has declined in the past 30 years, the number of new cases and deaths of mental disorders worldwide has increased, and will continue to increase in the near future. Therefore, relevant policies should be used to promote the prevention and management of known risk factors and strengthen the understanding of risk profiles and incidence modes of mental disorders, to help guide future research on control and prevention strategies.

Objective This study aimed to conduct a meta-analysis to explore and summarise the evidence regarding the association between obstructive sleep apnoea (OSA) and the subsequent risk of vascular outcomes and all-cause mortality. Methods Electronic databases PubMed, Embase and the Cochrane Library were searched to identify studies conducted through May 2016. Prospective cohort studies that reported effect estimates with 95% CIs of major adverse cardiac events (MACEs), coronary heart disease (CHD), stroke, cardiac death, all-cause mortality and heart failure for different levels versus the lowest level of OSA were included. Results A total of 16 cohort studies reporting data on 24 308 individuals were included. Of these, 11 studies reported healthy participants, and the remaining five studies reported participants with different diseases. Severe OSA was associated with an increased risk of MACEs (relative risk (RR): 2.04; 95% CI 1.56 to 2.66; P<0.001), CHD (RR: 1.63; 95% CI 1.18 to 2.26; P=0.003), stroke (RR: 2.15; 95% CI 1.42 to 3.24; P<0.001), cardiac death (RR: 2.96; 95% CI 1.45 to 6.01; P=0.003) and all-cause mortality (RR: 1.54; 95% CI 1.21 to 1.97; P0.05). Finally, no evidence of a factor-specific difference in the risk ratio for MACEs among participants with different levels of OSA compared with those with the lowest level of OSA was found. Conclusions Severe and moderate OSAs were associated with an increased risk of vascular outcomes and all-cause mortality. This relationship might differ between genders. Therefore, further large-scale prospective studies are needed to verify this difference.

The Coronavirus Disease 2019 (COVID-19) pandemic has had an adverse impact on the physical and mental health of the public worldwide. In addition to illness in patients with COVID-19, isolated people and the general population have experienced mental health problems due to social distancing policies, mandatory lockdown, and other psychosocial factors, and the prevalence of depression and anxiety significantly increased during the pandemic. The purpose of this review is to elucidate the epidemiology, contributing factors, and pathogenesis of depression and anxiety. during the pandemic. These findings indicate that physicians and psychiatrists should pay more attention to and identify those with a high risk for mental problems, such as females, younger people, unmarried people, and those with a low educational level. In addition, researchers should focus on identifying the neural and neuroimmune mechanisms involved in depression and anxiety, and assess the intestinal microbiome to identify effective biomarkers. We also provide an overview of various intervention methods, including pharmacological treatment, psychological therapy, and physiotherapy, to provide a reference for different populations to guide the development of optimized intervention methods.