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 ToexplorethevalueofMR DKIinevaluationofmicrostructuredamageincervicalspinalcordinjury(CSCI) Methods 32casesofCSCIpatientsconfirmedbyclinicalexaminationand20casesofhealthycontrolgroupwereinvestigatedbyconventional MRIandDKIexamination.AccordingtoT2WIsignal,theinjurygroupweredividedintoA,Bgroup,Agroupofhighsignalgroup(n＝14)andBgroupofnegativegroup (n＝18).A,BgroupsandcontrolgroupweremeasuredbyFA,meandiffusivity(MD)and mean kurtosis(MK)valuesatdifferenttimes (acute,4 weeksafterinjury,2to3 monthsafterinjury)andthedata wereanalyzedby SPSS17.0statisticalsoftware.TheROCcurvewasusedtoevaluatetheabilityofdifferentparametersindiagnosingCSCI.Results In A,BgroupsFAvaluesdecreasedearlyandincreasedgradually,butwerealwayslowerthanthecontrolgroup,andthedifferencewas statisticallysignificant(P＜0.001).InAgroup MDvalueincreasedearlyanddecreasedgradually,butwashigherthanthecontrol group (P＜0.001).InAgroup MKvaluedecreasedearlyandincreasedsignificantly(P＜0.001).InBgroup MDvalueincreasedand MKvaluedecreasedintheacutephase(P＜0.001),lateron MDand MKvaluesgraduallytendtothecontrolgroup,thedifference wasnotstatisticallysignificant(P＞0.05).Conclusion DKIcannoninvasivelyreflectthemicroGdamageofCSCI,whichcannotbedisplayed byconventionalMRIfortheearlydetectionofspinalcordabnormalities.TheFAvalueisofhighdiagnosticvalue.

Objective To explore the effect of modified meridian breathing training on the lung function of acute stroke patients. Methods Sixty acute stroke patients were randomly divided into an intervention group and a control group, each of 30. In addition to the conventional neurological treatment, the control group received routine breathing training, while the intervention group was given modified meridian breathing training by professional reha-bilitation therapists once a day for 4 weeks. Forced vital capacity ( FVC) and forced expiratory volume in one second ( FEV1) , as well as the rate of pulmonary infection were assessed before and after the treatment. Results After 4 weeks of treatment, a significant increase was observed in the average FEV1 and FVC of both groups, but the im-provement in the intervention group was significantly greater than in the control group. There were 3 lung infections ( 10％) in the intervention group, which was significantly lower than the 7 cases ( 23. 3％) in the control group. Conclusion Modified meridian breathing training can improve the lung function of acute stroke patients and reduce the incidence of lung infection.

Objective:To research the clinical effect of Yi-yuan moxibustion on the bladder dysfunction after incomplete spinal cord injury Method:Forty patients with urinary retention were randomized into treatment group and control group,20 cases in each group.The two groups were treated by rehabilitation training,and the treatment group received Yi-yuan moxibustion,once a day,5d a week,8 weeks in total.Bladder volume and residual urine were tested by B-scan ultrasonography.After 8 week treatment,the curative effect was assessed.Result:One week after all treatments,the results of B-scan ultrasonography showed that bladder volume and residual urine volume of both groups are were improved than before.The curative effect after 6 weeks treatment suggests that the effective rate in control group was 55％ and the treatment group was e 90％.The difference was statistically significant (P＜0.05).Conclusion:Yi-yuan moxibustion is a kind of good therapy to ameliorate urinary retention caused by spinal cord injury.

OBJECTIVETo understand the syphilis infection and its high risk factors among men who have sex with men (MSM) recruited from different channels.

METHODSSupported by the China-Gates Foundation HIV program from July to December 2011, we cooperated with community based organizations to conduct syphilis testing intervention among MSM from 14 cities (Beijing, Shanghai, Tianjin, Chongqing, Harbin, Shenyang, Qingdao, Xi'an, Nanjing, Wuhan, Hangzhou, Changsha, Kunming, and Guangzhou) and one province (Hainan province). Participants were recruited from different channels by the staff of local CBOs, Demographic (e.g. age, marital status, and education) and behavioral (e.g. condom use and sexual partners) data were collected using anonymous questionnaires. Blood samples were also collected to test for syphilis. A total of 34 100 MSM participated in the survey. Participants were excluded from data analysis (1 399, 4.1%) if they did not receive syphilis tests or they completed less than 80.00% of the key questions in the survey. Chi-square tests were used to understand the socio-demographic and behavioral differences between each group. Results of syphilis tests were also compared. Logistic regression models were used to test the statistical significance of these differences.

RESULTSA total of 32 701 MSM were enrolled and received syphilis testing. The average age of participates was 30.96 ± 9.57. And among them, 2 284 cases (7.0%) were recruited from gay bathhouses, 4 774 (14.6%) from gay bars, 6 266 (19.2%) from the internet, 1 997 (6.1%) from the parks/toilets and 17 380 (53.1%) from other channels. MSM recruited from the bathhouses had the highest syphilis infection rate than other 4 groups: gaybars (4.5%, 216/4 774), internet (6.7%, 422/6 266), parks/toilets (8.3%, 166/1 997), other channels (6.4%, 1 103/17 380) (χ² = 164.58, P < 0.001). The multivariate logistic regression analysis showed that being > 20 years of age (P < 0.001), having more than 2 homosexual partners in recent 3 months (8.0% (1 408/17 714), OR (95% CI) = 1.44 (1.04-1.98)), having no sex with females in past 3 months (6.8% (1 446/21 276), OR (95% CI) = 1.25 (1.07-1.46)), and not using condom at last anal sex (8.0% (769/9 668), OR (95% CI) = 1.13 (1.03-1.25)) were associated with a higher probability of being infected with syphilis. Whereas MSM married (7.2% (456/6 305), OR (95% CI) = 0.84 (0.73-0.98)), having a college or a higher education (5.3% (829/15 684), OR (95% CI) = 0.60 (0.53-0.67)), being local residents (6.5% (1 843/28 185), OR (95% CI) = 0.73 (0.61-0.87)) and living in the local province of project cities (6.6% (170/2 593), OR (95% CI) = 0.67 (0.53-0.85)) were protective factors.

CONCLUSIONMSM who were recruited from gay bathhouses have a higher rate of syphilis infection than those in channels relatively. They are older, with low education levels and high-risk sexual behaviors. Tailored interventions are required in the future, especially for MSM from gay bathhouses.

Adult ; China ; Condoms ; Demography ; Homosexuality, Male ; Humans ; Logistic Models ; Male ; Risk Factors ; Safe Sex ; Sexual Behavior ; Sexual Partners ; Surveys and Questionnaires ; Syphilis ; Universities

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)

Anesthesiology rotation is an important part in resident standardization training of surgery. However, there are many problems in the teaching process. For example, the key points of teaching is not clear, the process of teaching is not coherent, and teachers and students lack interaction. The Rotation Record is introduced in order to solve those problems. The Rotation Record effectively reflects the fundamental process and major learning point of anesthesiology department which contains three items: the usage and recording of instrument; the communication and the basic knowledge and operating skills of anesthesia. The Rotation Record can initiate learning activity, emphasize important contents, supervise and urge teaching and improve the learning effect. By introducing Rotation Record, the assessment results in the surgical residency in anesthesiology has greatly improved compared to the previous ones, and has effectively improved the teaching quality of anesthesia.

Objective To observe the effect of acupuncture combined with moxibustion on heart rate variability (HRV) in patients with post-stroke depression. Methods 120 patients were divided into control group (n=60) and treatment group (n=60). Both groups took fluoxetine and accepted acupuncture therapy, and the treatment group accepted moxibustion additionally. Hamilton Depression Rating Scale-17 (HAMD-17) and the change of HRV were compared before and after treatment. Results The score of HAMD was lower, and the reductive ratio was higher in the treatment group than in the control group (P<0.05). The standard deviation of the mean of qualified normal sinus interval (SDNN) and standard deviation of sequential five-minute R-R interval means (SDANN) increased in both groups after treatment (P< 0.05), and were higher in the treatment group than in the control group (P<0.05). The root mean square differences of successive R-R intervals (RMSSD) and percentage of differences between adjacent normal sinus intervals greater than 50 ms (PNN50) decreased in both groups after treatment (P<0.05), and were lower in the treatment group than in the control group (P<0.05). The low frequency (LF), high frequency (HF) and LF/HF were higher in both groups after treatment (P<0.05), and were higher in the treatment group than in the control group (P< 0.05). Conclusion Acupuncture combined with moxibustion therapy can better adjust the function of autonomic nerve and reduce depression in patients with post-stroke depression.

Objective To observe the effect of needle warming moxibustion on cognitive dysfunction after stroke. Methods 76 stroke patients with cognitive dysfunction were randomly divided into treatment group (n=38) and control group (n=38). The treatment group received needle warming moxibustion and routine rehabilitation for 4 weeks, while the control group only received routine rehabilitation. They were assessed with Montreal Cognitive Assessment (MoCA) and activities of daily living (ADL) scale before and after treatment. Results The score of MoCA and ADL improved in both groups (P<0.05), and improved more in the treatment group than in the control group (P<0.05) after treatment. Conclusion Needle warming moxibustion could improve cognitive function in patients after stroke and activities of daily living.