OBJECTIVE: To train convolutional networks using multi-lead ECG data and classify new data accurately to provide reliable information for clinical diagnosis. METHODS: The data were pre-processed with a bandpass filter, and signal framing was adopted to adjust the data of different lengths to the same size to facilitate network training and prediction. The dataset was expanded by increasing the sample size to improve the detection rate of abnormal samples. A depth-wise separable convolution structure was used for more specific feature extraction for different channels of twelve-lead ECG data. We trained the two classifiers for each label using the improved DenseNet to classify different labels. RESULTS: The propose model showed an accuracy of 80.13% for distinguishing between normal and abnormal ECG with a sensitivity of 80.38%, a specificity of 79.91% and a F1 score of 79.35%. CONCLUSIONS The model proposed herein can rapidly and effectively classify the ECG data. The running time of a single dataset on GPU is 33.59 ms, which allows real-time prediction to meet the clinical requirements.
Algorithms ; Arrhythmias, Cardiac ; diagnosis ; Databases as Topic ; Electrocardiography ; classification ; methods ; Humans ; Neural Networks (Computer) ; Sensitivity and Specificity

OBJECTIVE: To predict the sensitizing potency and optimal sensitization dose of trichloroethylene( TCE) by an in vitro skin sensitization test on a human acute monocytosis cell line( THP-1).METHODS: THP-1 cells were cultured in vitro and exposed to 2,4-dinitrochlorobenzene( DNCB),sodium dodecyl sulfate( SDS),tert-butylhydroquinone( tBHQ)and TCE for 24 hours.Flow cytometry was used to detect the expression of cell surface marker such as cluster of differentiation( CD) 86 and CD54,and the optimal dose range for sensitization detection was determined.With the relative fluorescence intensity( RFI),CD86 ≥ 150 and CD54 ≥ 200 as the standard,the sensitizing potency and optimal sensitization dose of TCE were predicted.RESULTS: The concentration range of reagents for sensitization test on THP-1 cells was the dose range at which the relative cell survival rate reached 75.0%-100.0%.DNCB at the doses of 20.83,25.00 and 30.00 μmol/L,tBHQ at the dose of 5.80 μmol/L,TCE at the doses of 8.33,10.00 and 12.00 mmol/L,can cause sensitivity.SDS was recognized as a negative sensitizer.The expression of CD86 and CD54 was the highest when the concentration of TCE was 8.33 mmol/L,which was considered as the best sensitization dose.CONCLUSION: The optimum sensitization dose of TCE is 8.33 mmol/L,which can provide the basis for dose design in future study of TCE sensitization pathways.

OBJECTIVE: To explore the molecular mechanism underlying 1,2-dichloroethane(1,2-DCE) induced apoptosis by screening differentially expressed proteins in human astrocytes( HAs). METHODS: HAs were cultured in complete medium with 1,2-DCE at various concentrations of 0-80 or 0-40 mmol/L. After 24 hours,apoptosis of HAs was evaluated using flow cytometry and staining with annexin Ⅴ-fluoresce in isothiocyanate and propidium iodide. An AAH-APO-1-2 protein chip was used to screen differentially expressed proteins and quantitative real-time polymease chain reaction(qRT-PCR) was used to verify related differentially expressed genes(DEGs). RESULTS: At 1,2-DCE concentrations of0-80 mmol/L,the total apoptosis rate of HAs increased with 1,2-DCE concentrations in a dose-dependent manner( P <0. 01). Seven different kinds of proteins were screened out by apoptotic protein chip. Among them,the expression of insulin-like growth factor-binding protein( IGFBP)-1,IGFBP-4 and cytochrome C( Cyto C) were up-regulated,while the expression of P27,cysteine aspartic acid specific protease-3( Caspase-3),B-cell lymphoma-2 interacting mediator of cell death( BIM) and BH3 interacting domain death agonist( BID) were down-regulated compared with the control group. The result of DEGs verified by qRT-PCR showed that the expression of mRNA of IGFBP-1,IGFBP-4 and Cyto C at 1,2-DCE concentrations of 40 mmol/L was up-regulated. This result was in consistent with the trend of target expression in the protein chip. The mRNA expression of Caspase-3,BIM and BID was also up-regulated. CONCLUSION: 1,2-DCE induces apoptosis of HAs through mitochondrial pathway.