Myocardial Infarction Detection Based on Multi-lead Ensemble Neural Network

Automatic myocardial infarction (MI) detection using an electrocardiogram (ECG) is of great significance for improving the survival rate of patients. In this study, we propose a multi-lead ensemble neural network (MENN) to distinguish anterior myocardial infarction (AMI) and inferior myocardial infarction (IMI) from healthy control (HC) respectively. In the study, three kinds of sub-networks and multi-lead ECG signals are combined, which fully explores the information of ECG signals and improves the classification performance. The algorithm is evaluated on the PTB database by 5-fold inter-subject cross-validation and the sensitivity (Se), specificity (Sp) and area under the curve (AUC) of AMI detection are 98.35%, 97.49%, 97.92%; The Se, Sp, and AUC of IMI detection are 93.17%, 92.02%, 92.60%. The proposed method achieves the state of the art results on both tasks and outperforms the baseline methods. Hence, the proposed method is potential for automatic MI diagnosis.

[Protective effect of Angelica sinensis polysaccharide against liver injury induced by D-galactose in aging mice and its mechanisms]

OBJECTIVE

To investigate the protective effect of Angelica sinensis polysaccharide (ASP) against liver injury induced by D-galactose in aging mice and its mechanisms.

METHODS

Male C57BL/6J were randomly divided into three groups with 10 mice in each group. In the D-galactose model group, the mice were subcutaneously injected with D-galactose (120 mg/kg) qd×42; in the ASP+D-galactose group, from the 8th day of the establishment of D-galactose model, the mice were subcutaneously injected with ASP (120 mg/kg) qd×35. In the normal control group, the mice were subcutaneously injected with isotonic saline of the same volume at the same time point. On the 2nd day after the injection was finished, the ocular blood was collected to prepare serum and measure the content of alanine aminotransferase (ALT), aspartate aminotransferase (AST), and total bilirubin (TBil). The liver tissue homogenate was prepared to measure the content of superoxide dismutase (SOD), glutathione peroxidase (GSH-Px), malondialdehyde (MDA), and advanced glycation end products (AGEs). A paraffin section of liver tissue was prepared; HE staining was performed to observe the pathomorphological changes of the liver, periodic acid-Schiff staining (PAS) was used to observe the changes in glycogen in the liver, and a transmission electron microscope was used to observe the hepatocyte ultrastructure.

RESULTS

The D-galactose model group had increased content of ALT, AST, and TBil, reduced activities of SOD and GSH-Px, an increased content of MDA, and severe liver injuries; the hepatocytes showed degenerative changes, the amount of glycogen in the liver decreased, and the accumulation of AGEs increased. The ASP+D-galactose group had reduced content of ALT, AST, and TBil, increased activities of SOD and GSH-Px, and reduced content of MDA and AGEs; the amount of glycogen in the liver increased, and liver injury and hepatocyte injury were alleviated.

CONCLUSION

ASP can antagonize the liver injury induced by D-galactose in aging mice, and its mechanism may be related to the inhibition of oxidative stress.