This study aimed to establish a model for predicting the three-year survival status of patients with hypopharyngeal squamous cell carcinoma using artificial intelligence algorithms.

Data from 295 patients with hypopharyngeal squamous cell carcinoma were analysed retrospectively. Training sets comprised 70 per cent of the data and test sets the remaining 30 per cent. A total of 22 clinical parameters were included as training features. In total, 12 different types of machine learning algorithms were used for model construction. Accuracy, sensitivity, specificity, area under the receiver operating characteristic curve and Cohen's kappa co-efficient were used to evaluate model performance.

The XGBoost algorithm achieved the best model performance. Accuracy, sensitivity, specificity, area under the receiver operating characteristic curve and kappa value of the model were 80.9 per cent, 92.6 per cent, 62.9 per cent, 77.7 per cent and 58.1 per cent, respectively.

This study successfully identified a machine learning model for predicting three-year survival status for patients with hypopharyngeal squamous cell carcinoma that can offer a new prognostic evaluation method for the clinical treatment of these patients.

Brain-derived neurotrophic factor (BDNF) gene may be involved in the pathogenesis of schizophrenia by virtue of its effects on neurotransmitter systems that are dysregulated in psychiatric disorder. The common functional polymorphism Val66Met (or rs6265) within the BDNF gene has been reported to be associated with age of onset in schizophrenia. We investigated the relationship between BDNF polymorphisms rs6265 and rs11030101 and early-onset schizophrenia in the Chinese population.

The tag single nucleotide polymorphisms (tag SNPs) rs11030101 and rs6265 in the BDNF gene were genotyped in 360 early-onset schizophrenics and 399 controls subjects. Single nucleotide polymorphism association and haplotype analysis were performed.

There were significant differences in allele and genotype frequencies between patient and normal control subjects for rs11030101 (χ2 = 5.130407, df = 1, p = 0.023553; χ2 = 6.121, df = 2, p = 0.047). No statistically significant differences were found in allele or genotype between patient and normal control subjects for rs6265. Stratification of the study by gender of the samples yielded significant evidence for an association with the polymorphisms rs11030101 in female population (genotype-wise: χ2 = 7.758, df = 2, p = 0.021).

Our study indicates that the BDNF play major roles in the susceptibility to early-onset and female schizophrenia in the Chinese population.

To explore the factors associated with occurrence of suicidal risk after treatment of Selective Serotonin Reuptake Inhibitor (SSRI) in bipolar disorder with their first depressive episode.

One hundred and seventy seven bipolar patients were enrolled in this retrospective study. Demographic and clinic features between non-occurrence of suicidal risk group and occurrence of suicidal risk group were compared. Stepwise Logistic regression model was used to identify the associated factors. Concordance statistics (i.e. the area under the ROC curve) was used to compute the discrimination of the associated factors, and Hosmer-Lemeshow goodness-of-fit statistic was used to measure the goodness-of-fit.

One hundred and fifty four patients were included in non-occurrence of suicidal risk group, while twenty three were included in occurrence of suicidal risk group. Clinical features associated with occurrence of suicidal risk after treatment of SSRI in bipolar disorder were as follows: symptom of irritability (OR=4.04, 95 CI:1.40-11.67) and psychotic symptom (OR=6.23, 95 CI:1.40-27.56).

This study demonstrated indicated that psychotic symptom and symptom of irritability were associated with occurrence of suicidal risk after treatment of SSRI in bipolar disorder, and it suggested that these two symptoms might be potential to be the predictors of occurrence of suicidal risk after treatment of SSRI in bipolar disorder.

Multiple neurotrophic factors, including vascular endothelial growth factor (VEGF), fibroblast growth factor (FGF)-2, nerve growth factor (NGF) and insulin-like growth factor(IGF)-1, have been shown to play important roles in the pathophysiology of mood disorders. However, insufficient clinical data supporting the importance of these neurotrophic factors in mood disorders, especially manic episode, have made inconclusive to make a connection between these factors and the disorder.

This study intended to investigate possible peripheral biomarkers in serum of manic episode of bipolar disorder.

We aimed to investigate whether or not serum levels of VEGF, FGF-2, NGF and IGF-1 varied in manic state.

Serum levels of VEGF, FGF-2, NGF and IGF-1 were examined in 70 drug-naïve patients with manic episode of bipolar disorder (BM) as well as 50 healthy controls, using an ELISA method.

The mean serum levels of VEGF, FGF-2, NGF and IGF-1 were 168.13±225.61pg/ml, 279.09±378.62pg/ml, 61.38±171.67pg/ml and 162.01±72.00ng/ml in BM patients, and 140.80±143.71pg/ml, 275.46±235.29pg/ml, 36.34±15.14pg/ml and 138.90±80.11ng/ml in healthy controls, respectively. Serum levels of FGF-2, NGF and IGF-1 in patients were significantly higher than those in healthy controls (Z=−2.896, P=0.004; Z=− 2.050, P=0.040; Z=−2.188, P=0.029; respectively), although there was no statistical difference in the serum levels of VEGF between two groups (Z=-0.468, P=0.639). Moreover, serum levels of NGF in patients correlated with the duration of disorder (rs=−0.241, P=0.044).

The increase in serum levels of FGF-2, NGF and IGF-1 in manic state may reflect a neuroprotective role for these factors, and these factors may be considered biological markers for manic episode.

Increasing evidence supports that 5HTTLPR polymorphism of the serotonin transporter gene(5HTTLPR) might associate to bipolar disorder and affective temperaments as measured by TEMPS-A. But the results are discrepant, furthermore, there are no data from Chinese population.

The present study was designed to investigate association between 5HTTLPR and bipolar disorder and affective temperaments of patients with bipolar disorder in the specific Chinese population and add new evidence to the field.

There hundred and five patients with bipolar disorder and 272 normal controls were included in the present case-control study⌧Temperament Evaluation of Memphis, Pisa, Paris and San Diego -autoquestionnaire version (TEMPS-A) in Chinese was used to assess affective temperament. Chi-square test, T test, Nonparametric test and ANOVA were employed to explore association between 5HTTLPR polymorphism and bipolar disorder and affective temperament of patients with bipolar disorder.

5-HTTLPR L/S polymorphism was associated with bipolar disorder in female (genotype χ2 = 6.769⌧P = 0.034⌧allele χ2 = 6.028⌧P = 0.014) and the S allele was associated with anxious temperament (t = 8.248⌧P = 0.005) in patients with bipolar disorder. the LA allele of 5-HTTLPR rs25531 A/G polymorphism was associated with hyperthymic temperament in patients with bipolar disorder (Z = −2.205⌧P = 0.027).

5-HTTLPR might have an effect on the prevalence of bipolar disorder in female and regulate affective temperaments of patients with bipolar disorder in some degree in Chinese population.

Bioinformatic investigations indicate that has-mir-206 (microRNA-206, miRNA-206) could regulate BDNF protein synthesis by interfering with BDNF mRNA translation, which is disrupted in bipolar disorder (BPD).

This study is to investigate whether miRNA-206 gene variants were associated with BPD susceptibility in a Han Chinese population.

342 patients who met DSM-IV criteria for bipolar disorder type I (BPD-I) or type II (BPD-II) and 386 matched health controls were enrolled into this study. the miRNA-206 gene and +/-500bp were selected for gene sequencing. for the case-control genetic comparisons, differences in the genotype and allele distributions between patients and controls were examined using Pearson's χ2 test.

Gene sequencing showed that there are two polymorphisms rs16882131(C/T) and rs62408583 (A/C) located at the upstream of miRNA-206 gene, which are complete linkage disequilibrium. the association analysis showed that there was no significant difference for genotype frequencies (χ2 = 2.075, df = 2, P = 0.354) or for allele frequencies (χ2 = 0.041, df = 1, P = 0.839) between BPD patients and controls. Similarly, no significant difference was found between BPD-I patients and controls (genotype χ2 = 1.411, df = 2, P = 0.494; allele χ2 = 0.380, df = 1, P = 0.538). However, there was significant difference between BPD-II patients and controls (genotype χ2 = 7.933, df = 2, P = 0.019; allele χ2 = 5.403, df = 1, P = 0.020).

Our findings do not support that BPD susceptibility was associated with miRNA-206 gene polymorphisms in the studied Han Chinese population. the association between miRNA-206 gene polymorphisms and bipolar disorder type II is needed to be carefully interpreted. Further studies are necessary to elucidate the involvement miRNA-206 in the pathophysiology of BPD.

To explore the difference in the clinical features between bipolar disorder and unipolar depression from the clinical phenomenology.

Two hundred bipolar patients with their current depressive episode and five hundred and sixty three recurrent depression were involved in the study. Clinical features of these two groups were compared and stepwise Logistic regression was used to identify the relationship between clinical features and bipolar disorder.

Clinical features of depressive episode which was different between two groups and were associated with bipolar disorder were as follows: age at onset of bipolar was earlier than that of unipolar depression; Bipolar patients whose age at onset before 25 years were more than unipolar depression; Sexual appetites which was one of atypical depressive symptoms were more common in bipolar depression than in unipolar depression; with psychiatric symptoms, psychomotor retardation, mood instability and duration of every depressive episode < 3 months, were more common in bipolar depression group than in unipolar depression group; Cognitive impairment factor, one of factors of HAMD-17 score, was significantly higher in bipolar depression group than in unipolar depression group. The odd ratio were 1.54, 1.50, 3.25, 1.99, 1.89, 1.48, 1.63, 1.63, and 1.42 separately.

The founding suggested that unipolar depression and bipolar depression might be distinct disorder, and age at onset, age at onset < 25, sexual appetites, psychiatric symptoms, psychomotor retardation, mood instability and duration of every depressive episode < 3 months might be potential to be the predictors of bipolar disorder.

To explore the factors associated with occurrence of suicidal risk after treatment of SSRI in bipolar disorder with their first depressive episode.

One hundred and seventy seven bipolar patients were enrolled in this retrospective study. One hundred fifty four patients were included in non-occurrence of suicidal risk group, while twenty three were included in occurrence of suicidal risk group. To compare the demographic and clinic features between these two groups. Stepwise Logistic regression model was used to identify the associated factors. Concordance statistics (i.e. the area under the ROC curve) was used to compute the discrimination of the associated factors, and Hosmer-Lemeshow goodness-of-fit statistic was used to measure the goodness-of-fit.

Clinical features associated with occurrence of suicidal risk after treatment of SSRI in bipolar disorder were as follows: psychotic symptom and symptom of irritability. The odd ratio was 6.23 and 4.04 separately.

This study demonstrated indicated that psychotic symptom and symptom of irritability were associated with occurrence of suicidal risk after treatment of SSRI in bipolar disorder, and it suggested that these two symptoms might be potential to be the predictors of occurrence of suicidal risk after treatment of SSRI in bipolar disorder.

To explore the relationship between brain-derived neurotrophic factor (BDNF) and B-cell lymphoma Leukemia-2 (Bcl-2) plasma levels in subsyndromal symptomatic depression (SSD) patients.

In this case-control study, Enzyme-Linked Immunosorbnent Assay (ELISA) method was used to analysed the differences of BDNF plasma levels between SSD group (n=42) and healthy controls (n=51). At the same time Hamilton Depression Rating Scale-17(HAMD17) were assessed the patients'severity.

There were significant difference of BDNF plasma levels between SSD group (medium 2.97 ng/ml)and healthy group (medium 3.71ng/ml, z=-2.94, P 0.003). Furthermore, BDNF plasma levels in SSD patients were associated with Hamilton score (r -0.53, P < 0.001). Plasma Bcl-2 levels were not different between SSD group (medium 4951 U/ml) and health controls (medium 5574 U/ml) (z = -1.71, P =0.09); and plasma Bcl-2 levels in SSD group were not associated with Hamilton score (r -0.10, P 0.34).

The study suggested that the decreased BDNF plasma levels were related with the pathophysiology of SSD and it might reflect the severity of disorder.

We investigated the relationship between tyrosine hydroxylase (TH) polymorphisms rs11042978, rs2070762 and rs6356 and early-onset schizophrenia in the Chinese Han population.

The tag single nucleotide polymorphisms (tag SNPs) rs11042978, rs2070762 and rs6356 in the TH gene were genotyped in 315 early-onset schizophrenics (188 male patients,127 female patients)and 391 controls subjects (219 males,172 females). Single nucleotide polymorphism association and haplotype analysis were performed.

There were significant differences in allele and genotype frequencies between patients and normal control subjects for rs11042978 allele (χ2 = 4.47, df = 1, P = 0.034) and genotype (χ2 = 6.35, df = 2, P = 0.042). No statistically significant differences were found in allele or genotype between patients and normal control subjects for rs2070762 and rs6356. The haplotype analysis revealed that there were significant differences between patients and normal control subjects for haplotypes GAC (χ2 = 6.35, P = 0.012).

Our study indicates that the TH gene may play major roles in the susceptibility to early-onset schizophrenia in the Chinese population.

The present study compared the expression profile and made the classification with the leukocytes by using whole-genome cRNA microarrays among patients with SSD, major depressive disorder (MDD) and healthy controls.

Gene expression profiling was conducted in peripheral blood leucocytes from drug-free first-episode subjects with SSD, MDD, and matched controls (8 subjects in each group) using global mRNA expression arrays. Support vector machines (SVMs) were utilized for training and testing on candidate signature expression profiles from signature selection step.

We identified SSD and MDD gene signatures from blood-based gene expression profile and build a SSD- MDD disorder model with higher predictive power. Firstly, we identified 63 differentially expressed SSD signatures in contrast to control (P <= 5.0E-4) and 30 differentially expressed MDD signatures in contrast to control, respectively. Then, 123 gene signatures were identified with significantly differential expression level between SSD and MDD. Secondly, in order to conduct priority selection for biomarkers for SSD and MDD together, we selected top gene signatures from each group of pair-wise comparison results, and merged the signatures together to generate better profiles used for clearly classify SSD and MDD sets in the same time. In details, we tried different combination of signatures from the three pair-wise compartmental results and finally determined 48 gene expression signatures with 100% accuracy.

Blood cell-derived RNA may have significant value for performing diagnostic functions and identifying disease biomarkers in SSD and MDD. These 48 gene model could classify SSD, MDD, and healthy controls.

To study the relationship between insulin-like growth factor 1 receptor (IGF1R)and subsyndromal symptomatic depression (SSD).

In this case-control study, real-time quantitative reverse transcriptase polymerase chain reaction (RT-qPCR) with TaqMan MGB was used to analyzing the differences of IGF1R gene mRNA expression in peripheral leukocytes between subsyndromal symptomatic depression group(n = 47) and healthy controls(n = 52). At the same time Hamilton Depression Rating Scale -17(HAMD17) were assessed.

IGF1R gene mRNA expression was 0.21 ± 0.11 in SSD group, 0.56 ± 0.37 in healthy group, and there was significant difference between both groups on IGF1R expression(z = 39.54, P < 0.001). the expression levels of IGF1R in SSD patients was not correlated with Hamilton score(r = −0.292, p = 0.275).

This study suggested that the decreased expression of IGF1R were related with the pathophysiology of SSD.