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.
Bipolar Disorder ; diagnosis ; Humans ; Neural Networks (Computer)

Background Permethrin is a commonly used pyrethroid insecticide and has been found to be potentially neurotoxic. Microglia are innate immune cells in the central nervous system and are involved in the development of a range of neurodegenerative diseases. Objective To observe possible toxic effects of permethrin on human microglia clone 3 (HMC3) in vitro and explore associated mechanism. Methods HMC3 were treated with 0, 10, 25, and 55 μmol·L⁻¹ permethrin for 72 h. Cell cycle and apoptosis were measured using flow cytometry. Cyclin-dependent kinase 1 (CDK1), cyclin-dependent kinase inhibitor 1A (CDKN1A), cyclin B2 (CCNB2), cellular tumor antigen p53 (p53), factor-related apoptosis (FAS), caspase 3 (CASP3), and H2A histone family member X (H2AX) were detected by quantitative real-time PCR (qPCR). The differential genes and enrichment pathways of HMC3 after 0 and 25 μmol·L⁻¹ permethrin treatment was analyzed by RNA sequencing. HMC3 was treated by 0, 10, 25, and 55 μmol· L⁻¹ permethrin for 72 h. The content of nitric oxide (NO) in the supernatant was detected using Griess reagent. The secretion level of interleukin-6 (IL-6) was detected by enzyme linked immunosorbent assay (ELISA). The mRNA expression levels of mitogen-activated protein kinase (MAPK) pathway (including MAPK1, MAPK8, and MAPK14), interleukin-1β (IL-1β), IL-6, and matrix metalloproteinase (MMP) families (including MMP1, MMP2, MMP3, and MMP9) were detected by qPCR. The protein expressions of phosphorylated p38 mitogen-activated protein kinase (p-p38), phosphorylated extracellular signal-regulated kinase (p-ERK), IL-1β, IL-6, and MMP1 were detected by Western blot. Results HMC3 was arrested in G2/M phase after 0, 10, 25, and 55 μmol·L⁻¹ permethrin treatment for 72 h, of which there was a statistically significant difference between the 55 μmol·L⁻¹ permethrin treatment group and the control group (P<0.01), and the mRNA expression of CDKN1A was up-regulated according to the qPCR (P<0.05). There was no statistically significant difference in the proportions of apoptosis between the groups (P＞0.05). The RNA sequencing showed that the differential genes were enriched in the MAPK pathway, and the mRNA expressions of MAPK1, MAPK8, and MAPK14 were up-regulated after the permethrin treatment at 55 μmol·L⁻¹ compared to the control group by qPCR (P<0.05). The Western blot revealed that, compared to the control group, the levels of p-p38 and p-ERK were increased after the 10 μmol·L⁻¹ permetrin treatment (P<0.05), the p-ERK level was increased after the 25 μmol·L⁻¹ permetrin treatment (P<0.05), and the p-p38 level was up-regulated after the 55 μmol·L⁻¹ permetrin treatment (P<0.05). The secretion of NO in the supernatant of HMC3 increased after permetrin treatment compared to the control group (P<0.05), the mRNA and protein expressions and the secretion of IL-6 showed an upward trend, the mRNA and protein expressions of IL-1β were up-regulated (P<0.05), and the mRNA and protein expressions of MMP1 were up-regulated in the 25 and 55 μmol·L⁻¹ permethrin groups (P<0.05). Conclusion Permethrin inhibits HMC3 cell proliferation in vitro, induces cell cycle arrest, activates MAPK pathway, and promotes the expression of inflammatory factors IL-1β and MMP1, which may be one of the mechanism of neurotoxicity induced by permethrin.

OBJECTIVETo explore the molecular basis for three pedigrees affected with hypophosphatemia vitamin D resistant rickets (X-linked hypophosphatemia, XLH).

METHODSPeripheral blood samples from the three pedigrees were collected. Following DNA extraction, the 11 exons and flanking regions of the PHEX gene were subjected to PCR amplification and direct sequencing. Pathogenicity of identified mutations was evaluated through genotype-phenotype correlation.

RESULTSFor pedigrees 1 and 2, pathogenic mutations were respectively identified in exon 8 (c.871C>T, p.R291X) and exon 15 (c.1601C>T, p.P534L) of the PHEX gene. For pedigree 3, a novel mutation (c.1234delA, p.S412Vfs*12) was found in exon 11 of the PHEX gene, which caused shift the reading frame and premature termination of protein translation.

CONCLUSIONThe three mutations probably account for the XLH in the affected pedigrees. The discovery of novel mutations has enriched the spectrum of PHEX gene mutations.

Objective To systematically evaluate the adult intraoperatively acquired pressure injury risk prediction model.Methods Related study on IAPI risk prediction model in Chinese and English databases such as CBM,CNKI,PubMed and Web of Science were searched.The language is limited to Chinese and English,and the search time is until November 4,2022.Two researchers independently screened the literature and extracted the data,and applied the bias risk assessment tool of prediction model research to analyze the bias risk and applicability of the included literature.Results 13 articles were included,including 17 models(operation time,age,diabetes,BMI and serum albumin are the most commonly used predictors).Among the 17 models,the area under the curve of 14 models was 0.616 to 0.984,and the other study did not report the AUC results.Among the 13 studies,10 had good applicability,while the remaining 3 had unclear applicability.13 studies have a high risk of bias,mainly because the included studies are retrospective studies,the predictive factors are screened based on univariate analysis,and the predictive outcomes are not defined by guidelines or standardization.Conclusions The existing IAPI risk prediction model for adults has good applicability,but the risk of bias is high,and the construction is not perfect.It is necessary to pay attention to the effectiveness of different risk assessment methods in the later construction,so as to get a better and more accurate risk prediction model and provide some reference and basis for formulating relevant prevention strategies.

Objective To use the cognitive reinforcement comprehensive intervention program constructed by our team to intervene in patients with spinal cord injury and evaluate its clinical application effect.Methods A non-randomized trial design was adopted to select 97 patients with spinal cord injury from November 2021 to September 2022.Forty-four patients from March to September 2022 in a Grade A hospital in Hefei City were included in the experimental group,and 53 patients from November 2021 to February 2022 were included in the control group.The cognitive reinforcement comprehensive intervention program was used to intervene in the experimental group,and the conventional rehabilitation nursing was used to intervene in the control group.The intervention lasted for 12 weeks in both groups.The Changsha Montreal Scale,Social Support Rating Scale,Rehabilitation Exercise Self-efficacy Scale,Spinal Cord Injury Independence Rating Scale and Hamilton Anxiety Scale were used to measure the two groups before intervention,1 month after intervention and 3 months after intervention.Results 40 cases in the experimental group and 48 cases in the control group completed the study.Repeated measurement ANOVA showed that the temporal,interactive and intergroup effects of cognitive function scores and anxiety scores were statistically significant(P＜0.05).The time effect and interaction effect of the subjective support dimension score,coping self-efficacy dimension score of the two groups were statistically significant(P＜0.05).One month after the intervention,the cognitive function scores of test group were higher than before intervention and control group,and the anxiety scores were lower than before intervention and control group(P＜0.05).Three months after the intervention,the scores of cognitive function,subjective support dimension and coping self-efficacy dimension of experimental group were higher than those before intervention and control group,and the scores of anxiety level were lower than those before intervention and control group(P＜0.05).Conclusion Comprehensive intervention of cognitive reinforcement can improve the cognitive function of patients with spinal cord injury,delay the process of cognitive impairment,enhance self-confidence,relieve anxiety,and promote physical and mental rehabilitation of patients.

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.
China ; Sleep Stages ; Sleep ; Electroencephalography ; Databases, Factual

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.
Humans ; Polysomnography ; China ; Sleep Stages ; Sleep ; Algorithms

【Objective】 Based on our previously established salt-sensitive hypertension cohort, we conducted chronic salt loading and potassium supplementation interventions, aiming to examine the association between genetic variants in renalase and blood pressure (BP) responses to dietary interventions of salt and potassium intake. 【Methods】 In 2004, 514 subjects from 126 families were recruited in Shaanxi Province to establish the salt-sensitive hypertension study cohort. Among them, 334 non-parent subjects were selected and sequentially maintained on a low-salt diet for 7 days, then a high-salt diet for 7 days and a high-salt diet with potassium supplementation for another 7 days. Ten single nucleotide polymorphisms (SNPs) in the renalase gene were genotyped on the MassARRAY platform. 【Results】 SNP rs2576178 of the renalasegene was significantly associated with systolic BP (SBP) and mean arterial pressure (MAP) responses to low-salt intervention (SBP: β=-2.730, P<0.05; MAP: β=-1.718, P<0.05). In addition, SNP rs12356177 was significantly associated with diastolic BP response to low-salt diet (β=-1.608, P<0.05). However, we did not find any association for the renalase SNPs with BP response to high-salt diet with potassium supplementation reached nominal statistical significance. 【Conclusion】 Genetic variants in renalase gene are significantly associated with BP response to low-salt diet, suggesting that renalase may be mechanistically involved in BP salt-sensitivity.