[Automatic sleep staging model based on single channel electroencephalogram signal].

Sleep staging is the basis for solving sleep problems. There's an upper limit for the classification accuracy of sleep staging models based on single-channel electroencephalogram (EEG) data and features. To address this problem, this paper proposed an automatic sleep staging model that mixes deep convolutional neural network (DCNN) and bi-directional long short-term memory network (BiLSTM). The model used DCNN to automatically learn the time-frequency domain features of EEG signals, and used BiLSTM to extract the temporal features between the data, fully exploiting the feature information contained in the data to improve the accuracy of automatic sleep staging. At the same time, noise reduction techniques and adaptive synthetic sampling were used to reduce the impact of signal noise and unbalanced data sets on model performance. In this paper, experiments were conducted using the Sleep-European Data Format Database Expanded and the Shanghai Mental Health Center Sleep Database, and achieved an overall accuracy rate of 86.9% and 88.9% respectively. When compared with the basic network model, all the experimental results outperformed the basic network, further demonstrating the validity of this paper's model, which can provide a reference for the construction of a home sleep monitoring system based on single-channel EEG signals.

[Status of Health Economics Research on Cognitive Behavioral Therapy for Insomnia].

Cognitive behavioral therapy for insomnia (CBT-I) is a first-line treatment for insomnia disorder. Herein, we reviewed the currently prevailing forms of application of CBT-I and the corresponding studies on their health economics, comparing them with medication treatment. At present, most of the findings suggest that CBT-I has long-lasting effects and can help reduce future medical costs, thus showing long-term economic advantages. At present, there are no relevant research reports on the economic benefits of CBT-I in China. This review could provide reference for relevant studies to be conducted in the future in China. In addition, it provides reference from an economic perspective for clinicians and patients and facilitates their decision-making concerning using CBT-I as a treatment option for insomnia in the future.

[Study on the method of polysomnography sleep stage staging based on attention mechanism and bidirectional gate recurrent unit].

Polysomnography (PSG) monitoring is an important method for clinical diagnosis of diseases such as insomnia, apnea and so on. In order to solve the problem of time-consuming and energy-consuming sleep stage staging of sleep disorder patients using manual frame-by-frame visual judgment PSG, this study proposed a deep learning algorithm model combining convolutional neural networks (CNN) and bidirectional gate recurrent neural networks (Bi GRU). A dynamic sparse self-attention mechanism was designed to solve the problem that gated recurrent neural networks (GRU) is difficult to obtain accurate vector representation of long-distance information. This study collected 143 overnight PSG data of patients from Shanghai Mental Health Center with sleep disorders, which were combined with 153 overnight PSG data of patients from the open-source dataset, and selected 9 electrophysiological channel signals including 6 electroencephalogram (EEG) signal channels, 2 electrooculogram (EOG) signal channels and a single mandibular electromyogram (EMG) signal channel. These data were used for model training, testing and evaluation. After cross validation, the accuracy was (84.0±2.0)%, and Cohen's kappa value was 0.77±0.50. It showed better performance than the Cohen's kappa value of physician score of 0.75±0.11. The experimental results show that the algorithm model in this paper has a high staging effect in different populations and is widely applicable. It is of great significance to assist clinicians in rapid and large-scale PSG sleep automatic staging.

The Moderating Role of Family Resilience on the Relationship between COVID-19-Related Psychological Distress and Mental Health among Caregivers of Individuals with Eating Disorders in Post-Pandemic China.

COVID-19 has amplified long-standing emotional distress for vulnerable families. While abundant research highlights the importance of resilience under adverse circumstances, little has been undertaken to understand its effectiveness in helping caregivers of individuals with eating disorders (ED) navigate pandemic-related challenges. This paper presents findings of a cross-sectional study investigating the effects of COVID-19-related life disruptions (COLD) and COVID-19-related psychological distress (CORPD) on caregivers' depression, anxiety and stress, as well as the moderation role of individual resilience (IR) and family resilience (FR) during the post-pandemic period in China. A total of 201 caregivers of individuals experiencing ED participated in our online survey from May 2022 to June 2022. The association between pandemic-related stressors (i.e., COLD and CORPD) and mental health conditions were confirmed. FR moderated the relationship between CORPD and mental health outcomes, while IR independently contributed to low emotional distress. We call for intervention programs strengthening caregivers' FR and IR, which might benefit both patients and caregivers' well-being in the post-pandemic period.

Impact of adverse childhood experiences on the symptom severity of different mental disorders: a cross-diagnostic study.

Background: Adverse childhood experiences have a significant impact on different mental disorders. Objective: To compare differences in adverse childhood experiences among those with different mental disorders and their relationships in a cross-disorder manner. Methods: The study included 1513 individuals aged ≥18 years : 339 patients with substance use disorders, 125 patients with schizophrenia, 342 patients with depression, 136 patients with bipolar disorder, 431 patients with obsessive-compulsive disorder (OCD), and 140 healthy controls. The Early Trauma Inventory Self Report-Short Form was used to investigate childhood traumatic experiences, and the Addiction Severity Index, Positive and Negative Syndrome Scale, Hamilton Depression Scale, Young Mania Rating Scale, and Yale-Brown Obsessive-Compulsive Scale were used to assess mental disorder severity. Correlation and multivariate logistic regression were analysed between adverse childhood experiences and clinical features. Results: Levels of adverse childhood experiences were significantly different among different mental disorders. Moreover, 25.8% of patients with substance use disorders reported childhood trauma, which was significantly higher than found in the other four psychiatric disorder groups. Emotional abuse scores were positively correlated with disease severity: the higher the total trauma score, the more severe the mental disorder. Conclusions: Adverse childhood experiences are a common phenomenon in those with mental disorders, and the level of trauma affects mental disorder severity. Emotional abuse is closely related to many mental disorders. The incidence or severity of mental disorders can be reduced in the future by reducing the incidence of adverse childhood experiences or by timely intervention in childhood trauma.

Gene expression signatures differentiating major depressive disorder from subsyndromal symptomatic depression.

Subsyndromal symptomatic depression (SSD) and major depressive disorder (MDD) have been classified as distinct diseases, due to their dissimilar gene expression profiles and responses to venlafaxine. To identify specific biomarkers of these two diseases, we conducted a secondary analysis of the gene expression signatures of SSD patients, MDD patients and healthy controls (n=8/group) from the study of Yi et al. Global, individual, specific, enrichment and co-expression analyses were used to compare the transcriptomic profiles of peripheral blood lymphocytes from the three groups. The global and individual analyses revealed that different genes were up- and downregulated in the SSD and MDD groups. Through our specific analysis, we identified 1719 and 3278 differentially expressed genes specifically associated with MDD and SSD, respectively. Enrichment and co-expression analyses demonstrated that the genes specific to MDD were enriched in pathways associated with hormone levels and immune responses, while those specific to SSD were associated with immune function. The specific hub gene for the MDD co-expression network was transmembrane protein 132B (TMEM132B), while the hub genes for SSD were actin-related protein 2/3 complex (ARPC2) and solute carrier family 5 member 5 (SLC5A5). This bioinformatic analysis has provided potential biomarkers that can distinguish SSD from MDD.

Neural biomarker of functional disability in major depressive disorder: A structural neuroimaging study.

BACKGROUND: Most patients with the major depressive disorder (MDD) have varying degrees of impaired social functioning, and functional improvement often lags behind symptomatic improvement. However, it is still unclear if certain neurobiological factors underlie the deficits of social function in MDD. The aim of this study was to investigate the biomarkers of social function in MDD using structural magnetic resonance imaging (MRI). METHODS: 3T anatomical MRI was obtained from 272 subjects including 46 high-functioning (high-SF, Sheehan Disability Scale (SDS) rating < 18) and 63 low-functioning (low-SF, SDS score ≥ 18) patients with MDD and 163 healthy controls (HC). Voxel-based morphometry (VBM) was employed to locate brain regions with grey matter (GM) volume differences in relation to social function in MDD. Regions showing GM differences in relation to social function at baseline were followed up longitudinally in a subset of 38 patients scanned after 12-week treatment. RESULTS: Volume of right parahippocampal gyrus (rPHG) was significantly reduced in low-SF patients with MDD when compared to high-SF ones (FDR-corrected p < 0.05). Over 12 weeks of follow-up, though SF improved overall, the high and low-SF subgroups continued to differ in their SF, but had no progressive changes in PHG volume. LIMITATIONS: Limited functional assessment, high drop-out rate and median-based grouping method. CONCLUSIONS: Greater GM volume (GMV) of the rPHG may mark better social function in patients with MDD.

Altered resting-state fMRI signals and network topological properties of bipolar depression patients with anxiety symptoms.

BACKGROUND: This study aims to explore the changes in functional neuroimaging in bipolar depression patients with anxiety symptoms (BDP-A). METHODS: Forty-five BDP-A patients, 22 bipolar depression patients without anxiety symptoms (BDP-NA), and 48 healthy controls (HC) were finally involved. The low-frequency oscillation characteristics, functional connectivity (FC), and network properties among the three groups of participants were analyzed. RESULTS: Compared with the BDP-NA group, BDP-A patients exhibited significantly decreased amplitude of low-frequency fluctuation (ALFF) in the left middle frontal gyrus (MFG), superior occipital gyrus, and inferior parietal, but supramarginal and angular gyri (IPL). Enhanced FC from left IPL to middle temporal gyrus, from left precentral gyrus (PreCG) to bilateral angular gyri, medial superior frontal gyrus, and left superior frontal gyrus (SFG)/MFG were also revealed. Compared with HC, the BDP-A group showed remarkably increased ALFF in the left MFG/PreCG, right superior parietal gyrus, while decreased ALFF in the left inferior frontal gyrus, opercular part, and SFG. In addition, higher regional homogeneity in the left MFG/PreCG was found. LIMITATIONS: The limitations are as follows: (1) relatively small sample size; (2) not all the patients were drug-naive; (3) lack of pure anxiety disorder patients as a controlled group; (4) mental health conditions of HC were not systemic evaluated. CONCLUSIONS: BDP-A patients showed significant differences in resting-state fMRI properties when compared with BDP-NA or HC group. These results may infer the dysfunction of the dorsal attention network, the default network, and the fronto-limbic system as well as disrupted brain network efficiency in BDP-A patients.

Weighted gene co-expression network analysis identifies specific modules and hub genes related to subsyndromal symptomatic depression.

Objectives: The identification of the potential molecule targets for subsyndromal symptomatic depression (SSD) is critical for improving the effective clinical treatment on the mental illness. In the current study, we mined the genome-wide expression profiling and investigated the novel biological pathways associated with SSD.Methods: Expression of differentially expressed genes (DEGs) were analysed with microarrays of blood tissue cohort of eight SSD patients and eight healthy subjects. The gene co-expression is calculated by WGCNA, an R package software. The function of the genes was annotated by gene ontology and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis.Results: We identified 11 modules from the 9,427 DEGs. Three co-expression modules (blue, cyan and red) showed striking correlation with the phenotypic trait between SSD and healthy controls. Gene ontology and KEGG pathway analysis demonstrated that the function of these three modules was enriched with the pathway of inflammatory response and type II diabetes mellitus. Finally, three hub genes, NT5DC1, SGSM2 and MYCBP, were identified from the blue module as significant genes.Conclusions: This first blood gene expression study in SSD observed distinct patterns between cases and controls which may provide novel insight into understanding the molecular mechanisms of SSD.

Longitudinally Measured Changes in Somnolence Severity With a Visual Analog Scale in a Randomized Lithium Versus Quetiapine-IR Study in Bipolar Disorder.

OBJECTIVE: The aim of this study was to use a visual analog scale (VAS) longitudinally measuring somnolence severity in patients with bipolar disorder. METHODS: A data set of patients with bipolar spectrum disorders who were randomized to lithium or quetiapine-IR for 16 weeks was used. The somnolence severity was measured with a VAS from 0 to 100 (VAS based), and somnolence frequency was recorded according to incident report (incidence based) at each visit. The rates of VAS-based and incidence-based somnolence and changes in somnolence severity from baseline to the end of study were compared between the lithium and quetiapine groups. Longitudinal changes in somnolence severity were analyzed with linear regression analysis. RESULTS: Of 42 patients randomized, only 3 scored 0 on the VAS at baseline. The rates of incidence-based and VAS-based somnolence were similar in the lithium and quetiapine-IR groups. The VAS change scores from baseline to each visit varied in both groups with significant decreases at weeks 6 and 12 in the quetiapine-IR group only. The decrease at week 6 in the quetiapine-IR group was significantly different from that in the lithium group. Patterns of changes in somnolence severity were inconsistent in both groups. A significant interaction between time course and the decrease in VAS scores was observed in the quetiapine-IR group, but not in the lithium group. CONCLUSIONS: Baseline somnolence was highly prevalent in patients with bipolar disorder. The change in somnolence severity was different between lithium-treated and quetiapine-treated patients. Quantifying somnolence longitudinally is important in clinical trials and practice.

A Pilot Study of the Effectiveness of Lithium Versus Quetiapine Immediate Release Monotherapy in Patients With Bipolar Spectrum Disorders.

OBJECTIVE: The aim of this study was to compare the effectiveness of lithium versus quetiapine immediate release (IR) monotherapy in patients with bipolar I, II, or subthreshold bipolar disorder at any phase. METHODS: Eligible patients were randomized to lithium or quetiapine IR for 16 weeks. The difference in the time to discontinuation from study due to "all causes" between lithium and quetiapine IR groups and changes from baseline to 8 and 16 weeks in depression, mania, anxiety, quality of life (QOL), metabolic profiles, and proinflammatory markers were compared. RESULTS: Of the 42 patients randomized to lithium (n = 18) and quetiapine IR (n = 24), the median time to discontinuation due to "all causes" was 6 weeks (95% confidence interval, 2-12 weeks) in the lithium group and 8 weeks (95% confidence interval, 6 weeks to not calculable) in the quetiapine IR group. The mean time to discontinuation due to "all causes" was 7.7 ± 1.1 weeks for lithium versus 8.4 ± 0.8 weeks for quetiapine IR (P = 0.54). There was no significant difference between lithium and quetiapine IR in changes in the severity of depression, mania/hypomania, anxiety, and QOL as a whole or only in patients with depressive index episode. The decrease in total cholesterol was significantly larger with lithium than with quetiapine IR (P = 0.05) as a whole, but not only in patients with depression index episode. There was no other significant difference in changes in metabolic panels and inflammatory markers between the 2 groups. CONCLUSIONS: The difference in effectiveness between lithium and quetiapine IR monotherapy in a real-world bipolar population was minimal. Large-sample studies are needed to support or refute this finding.

The association of duration and severity of disease with executive function: Differences between drug-naïve patients with bipolar and unipolar depression.

BACKGROUND: The aims of this study were to investigate the differences in executive function and the relationship with clinical factors between drug-naïve patients with bipolar depression (BDD) and unipolar depression (UPD). METHODS: Drug-naïve patients with BDD, UPD and healthy controls (HC) were recruited (30 cases in each group). All patients were assessed with Hamilton Rating Scale for Anxiety (HAM-A), Hamilton Rating Scale for Depression-17 (HAM-D), and Young Mania Rating Scale (YMRS). Executive function was evaluated by Stroop color-word test (CWT) and Wisconsin Card Sorting Test (WCST). RESULTS: In the BDD group, only the CWT number of missing was higher than HCs (P = 0.047). In the UDP group, CWT number of correct was lower, CWT number of missing was higher, and the WCST indices were worse than the HC group (P < 0.05). The WCST percentage of errors (PE) and percentage of conceptual level responses (PCLR) in the UPD group were worse than the BDD group (P < 0.05). In the BDD group, no correlations between CWT and WCST indices and clinical features were detected after correcting for multiple comparisons (P > 0.05). In the UDP group, the WCST PE, PCLR, number of categories completed (CC), and the percentage of perseverative responses (PPR) were correlated to the number of mood episodes (P < 0.01). LIMITATION: This was a small-sample cross-sectional study. The possibility of UPD transforming to bipolar disorder (BD) in future could not be ruled out. CONCLUSION: Our results suggested only small differences in executive function between drug-naïve patients with BDD and UPD, but in this sample only the UPD group showed differences with HCs. The executive function of drug-naïve BDD patients may be associated with duration of current depressive episode, while for UDP patients executive function indices were significantly correlated with number of mood episodes.

Different levels of pro- and anti-inflammatory cytokines in patients with unipolar and bipolar depression.

BACKGROUND: Immune system dysregulation is critical in the physiopathology of major depressive disorder (MDD) and bipolar disorder (BD). However, it is unclear whether both diseases present the same inflammatory patterns during depressive episodes. We explored the differences in pro- and anti-inflammatory cytokines between unipolar and bipolar depression (BDD) and the trajectory of these cytokines after acute-phase treatment. METHODS: Sixty-four MDD patients, 61 BDD patients, and 62 healthy controls (HCs) were enrolled. We assessed the clinical features and cytokines plasma levels at baseline and week 12. The pro-inflammatory cytokines (IL-6, TNF-α) and anti-inflammatory cytokines (IL-4, IL-13) of all subjects were assessed by multiplexed sandwich ELISA-based quantitative arrays. RESULTS: Before acute-phase treatment, the initial levels of TNF-α and IL-13 were significantly lower in the BDD patients than in the MDD patients. The results demonstrated that there was no relationship between each cytokine level and clinical features of unipolar and bipolar depressions. After 12 weeks, TNF-α, IL-4, and IL-13 levels became lower in MDD patients than in the other two groups regardless of the patients' response to treatment while the levels of TNF-α and IL-4 increased only in the BDD responders. LIMITATIONS: The effects of different drugs on inflammatory cytokines in MDD or BDD could not be explored further due to the relatively small sample size. CONCLUSION: Even within the same depressive states, MDD and BDD patients present different inflammatory features, particularly in regard to pro-inflammatory TNF-α and anti-inflammatory IL-13. In addition, the fluctuations of cytokines induced by medication may provide a hint regarding the prediction of treatment response.

Association analysis between mitogen-activated protein/extracellular signal-regulated kinase (MEK) gene polymorphisms and depressive disorder in the Han Chinese population.

BACKGROUND: Recent research findings suggest that BDNF and BDNF signaling pathways participate in the development of major depressive disorder. Mitogen-activated extracellular signal-regulated kinase (MEK) is the most important kinase in the extracellular signal-regulated kinase pathway, and the extracellular signal-regulated kinase pathway is the key signaling pathway of BDNF, so it may play a role in development of depressive disorder. The aim of this study is to investigate the association between polymorphisms of the MAP2K1 (also known as MEK) gene and depressive disorder. RESULTS: Three single nucleotide polymorphisms (SNPs), were significantly associated with depressive disorder: rs1549854 (p = 0.006), rs1432441 (p = 0.025), and rs7182853 (p = 0.039). When subdividing the sample by gender, two of the SNPs remained statistically associated with depressive disorder in females: rs1549854 (p = 0.013) and rs1432441 (p = 0.04). CONCLUSION: The rs1549854 and rs1432441 polymorphisms of the MAP2K1 gene may be associated with major depressive disorder, especially in females. This study is the first to report that the MAP2K1 gene may be a genetic marker for depressive disorder.

Reduced ENA78 levels as novel biomarker for major depressive disorder and venlafaxine efficiency: Result from a prospective longitudinal study.

Although lines of evidence demonstrated that cytokines play an important role in the pathogenesis of major depressive disorder (MDD), none of the them have been established as reliable biomarkers. We use our previous whole-genome cRNA microarray data to identify epithelial cell-derived neutrophil-activating peptide 78 (ENA78), the most differentially expressed cytokine in peripheral blood between MDD patients and healthy controls; and then we confirmed the result by the quantitative reverse transcription-polymerase chain reaction (RT-qPCR) and enzyme-linked immunosorbent assay (ELISA) for mRNA and protein level, respectively, in an independent drug-naïve first-episode sample set. In addition, to replicate the role of plasma ENA 78 in MDD, and determine the role of ENA78 on the venlafaxine efficiency, we further detected the plasma ENA78 in another independent 8- week follow-up sample set. We found that both of mRNA and plasma of ENA78 decreased in MDD patients, and displayed much lower after venlafaxine treatment. We also found that venlafaxine non-responders had lower level of peripheral plasma ENA78 prior to treatment than responders. Our findings for the first time provided strong evidence that the ENA78 may play a key role of mediator in pathogenesis of MDD and in the mechanism of vinlafaxine effects on MDD indicating that reduced ENA78 may be a potential biomarker for diagnosing of MDD and predicting of response to venlafaxine.

Differential gene expression in patients with subsyndromal symptomatic depression and major depressive disorder.

BACKGROUND: Subsyndromal symptomatic depression (SSD) is a subtype of subthreshold depressive and can lead to significant psychosocial functional impairment. Although the pathogenesis of major depressive disorder (MDD) and SSD still remains poorly understood, a set of studies have found that many same genetic factors play important roles in the etiology of these two disorders. Nowadays, the differential gene expression between MDD and SSD is still unknown. In our previous study, we compared the expression profile and made the classification with the leukocytes by using whole-genome cRNA microarrays among drug-free first-episode subjects with SSD, MDD and matched healthy controls (8 subjects in each group), and finally determined 48 gene expression signatures. Based on these findings, we further clarify whether these genes mRNA was different expressed in peripheral blood in patients with SSD, MDD and healthy controls (60 subjects respectively). METHOD: With the help of the quantitative real-time reverse transcription-polymerase chain reaction (RT-qPCR), we gained gene relative expression levels among the three groups. RESULTS: We found that there are three of the forty eight co-regulated genes had differential expression in peripheral blood among the three groups, which are CD84, STRN, CTNS gene (F = 3.528, p = 0.034; F = 3.382, p = 0.039; F = 3.801, p = 0.026, respectively) while there were no significant differences for other genes. CONCLUSION: CD84, STRN, CTNS gene may have significant value for performing diagnostic functions and classifying SSD, MDD and healthy controls.

Ratio of mBDNF to proBDNF for Differential Diagnosis of Major Depressive Disorder and Bipolar Depression.

There is a high rate of misdiagnosis between major depressive disorder (MDD) and bipolar disorder (BD) in clinical practice. Our previous work provided suggestive evidence for brain-derived neurotrophic factor (BDNF) in differentiating BD from MDD. In this study, we aimed to investigate the role of mature BDNF (mBDNF) and its precursor (proBDNF) in distinguishing bipolar depression (BP) from MDD during acute depressive episode. A total of 105 participants, including 44 healthy controls, 37 MDD patients and 24 BP patients, were recruited. Enzyme-linked immunosorbent assay kits were applied to measure plasma mBDNF levels and proBDNF levels of all participants. Plasma mBDNF levels were significantly decreased in BP group than those in MDD group (P = 0.001) and healthy controls (P = 0.002). Significantly higher ratio of mBDNF to proBDNF (M/P) at baseline was showed in MDD group than those in BP group as well as in healthy controls (P = 0.000 and P = 0.000, respectively). The optimal model for discriminating BP was the M/P ratio (area under the ROC curve = 0.858, 95 % CI 0.753-0.963). Furthermore, the M/P ratio was restored to normal levels after antidepressants treatment in MDD group. In summary, our data demonstrated that both plasma mBDNF levels and M/P ratio were lower in BP compared with MDD. These findings further support M/P ratio as a potential differential diagnostic biomarker for BP among patients in depressive episodes.

[Correlation between Expression of Peripheral IL-17 Protein and Aggression of Bipolar Mania].

OBJECTIVE: To explore the correlation between the interleukin-17 (IL-17) level of peripheral blood and aggression of bipolar mania. METHODS: Thirty-six patients of bipolar mania were selected as experimental group by DSM-IV-TR and received treatment with quetiapine and lithium. Thirty-six healthy volunteers with similar age and gender were selected as control group. The level of IL-17 at baseline in each group and the level of IL-17 in the experimental group after treatment for 2, 4 and 8 weeks were detected by ELISA. RESULTS: The level of IL-17 in experimental group at baseline, after treatment for 2 and 4 weeks were all significantly higher than that in control group. After 8 weeks treatment, there was no significant difference between the two groups (P > 0.05). After 2, 4 and 8 weeks treatment, the total score and aggression score of Young Mania Rating Score (YMRS) were significantly lower than the baseline level (P < 0.05). In experimental group, the level of IL-17 was positively correlated with the two scores of YMRS at baseline (P < 0.05). CONCLUSION: Bipolar mania may be related to the up-regulation of IL-17. The level of IL-17 is related to the severity of manic symptoms at baseline, especially aggression symptom.

[Research on Early Identification of Bipolar Disorder Based on Multi-layer Perceptron Neural Network].

Multi-layer perceptron (MLP) neural network belongs to multi-layer feedforward neural network, and has the ability and characteristics of high intelligence. It can realize the complex nonlinear mapping by its own learning through the network. Bipolar disorder is a serious mental illness with high recurrence rate, high self-harm rate and high suicide rate. Most of the onset of the bipolar disorder starts with depressive episode, which can be easily misdiagnosed as unipolar depression and lead to a delayed treatment so as to influence the prognosis. The early identifica- tion of bipolar disorder is of great importance for patients with bipolar disorder. Due to the fact that the process of early identification of bipolar disorder is nonlinear, we in this paper discuss the MLP neural network application in early identification of bipolar disorder. This study covered 250 cases, including 143 cases with recurrent depression and 107 cases with bipolar disorder, and clinical features were statistically analyzed between the two groups. A total of 42 variables with significant differences were screened as the input variables of the neural network. Part of the samples were randomly selected as the learning sample, and the other as the test sample. By choosing different neu- ral network structures, all results of the identification of bipolar disorder were relatively good, which showed that MLP neural network could be used in the early identification of bipolar disorder.

Down-regulation of PRKCB1 expression in Han Chinese patients with subsyndromal symptomatic depression.

BACKGROUND: Subsyndromal symptomatic depression (SSD) is a common disease with significant social dysfunction. However, SSD is still not well understood and the pathophysiology of it remains unclear. METHODS: We classified 48 candidate genes for SSD according to our previous study into clusters and pathways using DAVID Bioinformatics Functional Annotation Tool. We further replicated the result by using real-time Quantitative PCR (qPCR) studies to examine the expression of identified genes (i.e., STAT5b, PKCB1, ABL1 and NRAS) in another group of Han Chinese patients with SSD (n = 50). We further validated the result by examining PRKCB1 expression collected from MDD patients (n = 20). To test whether a deficit in PRKCB1 expression leads to dysregulation in PRKCB1 dependent transcript networks, we tested mRNA expression levels for the remaining 44 genes out of 48 genes in SSD patients. Finally, the power of discovery was improved by incorporating information from Quantitative Trait (eQTL) analysis. RESULTS: The results showed that the PRCKB1 gene expression in peripheral blood mononuclear cells (PBMC) was 33.3% down-regulated in SSD patients (n = 48, t = 3.202, p = 0.002), and a more dramatic (n = 17, 49%) down-regulation in MDD patients than control (n = 49, t = 2.114, p = 0.001). We also identified 37 genes that displayed a strong correlation with PRKCB1 mRNA expression levels in SSD patients. The expression of PRKCB1 was regulated by multiple single nucleotide polymorphisms (SNPs) both at the transcript level and exon level. CONCLUSIONS: In conclusion, we first found a significant decrease of PRCKB1 mRNA expression in SSD, suggesting PRKCB1 might be the candidate gene and biomarker for SSD.