Convolutional neural network is a good technique for sleep staging based on HRV: A comparative analysis.

The fluctuation of heart rate is regulated by autonomic nervous system. In human sleep, the autonomic nervous system plays a leading role. Therefore, we can use heart-rate variability (HRV) to stage the sleep process. Based on two independent public datasets, we construct three end-to-end automatic sleep staging models: fully connected neural networks (FCN), convolutional neural networks (CNN) and long short-term memory networks (LSTM). Only the HRV sequence was used to classify and identify the four sleep stages of the subject's sleep process: wake(W), light sleep (LS), slow-wave sleep (SWS) and rapid eye movement (REM), and the confusion matrix was calculated. The three models were compared by performance index (precision, accuracy, F1, Kappa statistic) and Friedman test. Among these models, the CNN has the best classification effect. The precision of W, REM, LS and SWS were 88.31%, 98.07%, 81.16% and 99.36%, respectively. It's the average accuracy, average F1 value and Kappa statistic were 91.72%, 0.8850 and 0.8844 ±â€¯0.0095, respectively. The experimental results show that the convolutional neural network can achieve good sleep staging effect based on the signal of HRV solely, which is suitable for sleep detection in the home.

[A preliminary report of SARS coronavirus specific RNA in SARS convalescents and medical person].

OBJECTIVE: To observe the method of fluorescent-polymerase chain reaction (F-PCR) and gene-hip technique in detecting coronavirus in severe acute respiratory syndrome (SARS) and its value for clinical application. METHODS: Serum of 60 SARS patients, 20 samples of serum and 20 samples of gargling fluid of medical staff of the "Fever Clinic", and one cDNA specimen obtained from one SARS suspect patient were examined with F-PCR diagnosis kit and gene-chip technique for SARS coronavirus. RESULTS: Three methods, including DR Chip and two F-PCR kit from Zhongshan College Da'an gene stock company and Shanghai Fortune industrial joint-stock Co, Ltd, were used, and the results were all negative for all specimens, except one cDNA specimen, which was obtained from one SARS suspect patient, virus could be amplified by F-PCR. CONCLUSION: Special RNA fragment of SARS virus has not been detected in gargling fluid and serum of SARS convalescents and medical staff.

[Comparison of serum biochemical features between SARS and other viral pneumonias].

OBJECTIVE: To identify blood chemistry changes in coronavirus of severe acute respiratory syndrome (SARS). METHODS: Biochemical changes in SARS patients were summarized and compared with other viral pneumonias. Serum total protein (TP), albumin (Alb), total cholesterol (TC), triglyceride (TG), calcium (Ca), ferrum (Fe), lactate dehydrogenase (LDH), creatine kinase (CK), alanine aminotransferase (ALT) and aspartate aminotransferase (AST) between SARS and other viral pneumonias were examined by Roche Diagnostics assay, HITACHI7600 automatic analyzer. Clinically confirmed SARS patients, patients with other viral pneumonias, and healthy controls were included in the study. RESULTS: Compared with healthy person, the levels of serum TC, Fe, Ca, Alb were significantly lowered (P<0.05 or P<0.01), while the activity of LDH, CK, ALT, AST were elevated, the increase of CK and the decrease of Fe were the most significant (P<0.05 or P<0.01), the changes of TP and TG were not obvious. In the other viral pneumonias patients, ALT, AST, LDH were elevated slightly than those of healthy person, while Fe, Ca, Alb, TC, CK were a little reduced, but there was no significant difference between the two groups. In convalescent stage, all the tests were returned to normal ranges except ALT, AST were still elevated in SARS patients. CONCLUSION: The changes in serum biochemistry are more marked in SARS patients compared with patients suffering from other viral pneumonias, the decrease of Fe as well as the inhibition of TC may be caused by the treatment of anti-virus.

[Correlation of polymorphism in IL-6 gene promoter with BMI, inflammatory factors, and pathogenesis and progression of CHD].

This study was aimed to explore the correlation between IL-6 gene promoter polymorphisms and coronary heart disease (CHD) by investigating the polymorphisms (-572G/C, -597G/A) in IL-6 gene promoter area, body mass index (BMI), inflammatory factors and other biochemical parameters in Han nationality of North China. The genotypes of IL-6 gene promoter-572G/C, -597G/A were detected by fluorescent probe hybridization with fluorescent resonance energy transfer and melting curve techniques in 194 CHD patients and 123 healthy people as control. The effects of genotype on plasma lipids, apoproteins, high sensitive C-reactive protein (hsCRP) and BMI were also studied. Logistic regression was performed to observe the risk factors of CHD. The results indicated that genotype of IL-6 gene promoter -597G/A polymorphism in 7 cases were GA and were GG in others, whereas no AA genotype had been found and no associations between polymorphism of IL-6 gene -597G/A, BMI and inflammatory factors were found. No differences had been found between the frequencies of IL-6 gene -572G/C genotypes and alleles in CHD and control group. However, significant difference was found between the G allele carrier (GG+GC) and non-G allele carrier (CC) of CHD and control group (p=0.0425). In the control group, median levels of systolic blood pressure of G allele carrier were significant higher than non-G allele carrier (p=0.02). Among all the subjects, median levels of BMI, hsCRP and systolic blood pressure in the group of G allele carrier were significantly higher than that in the group of non-G allele carrier, p values were 0.026, 0.022, 0.005 respectively. Multivariate logistic regression analysis showed that age, triglyceride, sex, high blood pressure, apoprotein C2, cholesterol and lipoprotein-a) were the risk factors for CHD, and apoprotein A1 was a protective factor. The G allele of IL-6 gene -572G/C has been not found to be a risk factor for CHD. It is concluded IL-6 gene -597G/A polymorphism is not correlated with the susceptibility to CHD; IL-6 gene -572G/C polymorphism may be correlated with the susceptibility to CHD in Han nationality of North China, the mechanisms may be related with the changes of BMI, hsCRP and blood pressure levels resulted from the polymorphism of IL-6 -572G/C.