Search

Abstract The automatic classification of electrocardiograms (ECGs) plays a crucial role in the early diagnosis of cardiovascular diseases. In recent research, deep neural network (DNN)-based methods have garnered significant attention due to their exceptional feature extraction capabilities. However, these methods face challenges in dealing with the complex inter- and intra-class dependencies inherent in different arrhythmias. We propose a classification model for electrocardiograms based on the Graph Convolutional Neural Network (EGCNet) to address this. In our EGCNet framework, we first employ the row and column 1-dimensional residual convolution to learn intra-class dependency. Then, we construct a hierarchical graph structure to model the inter-class dependency. In such a graph, each node represents one type of disease, and the edges describe the relationship between diseases. To reduce the complexity of inter-class dependency, we build a hierarchical graph structure by treating similar nodes as the same type. Thus, we can learn the discriminant dependency in the higher-level graph space and feed this high-level knowledge back to the lower-level graph space. Finally, we evaluated our method using publicly available datasets from the PhysioNet/Computing Challenge 2020 ECG data. For instance, our model achieved robust performance in the 24-label experiment with a precision of 0.753 and an F1 score of 0.722.

Helicobacter pylori (H. pylori) is one of the globally recognized causative factors of gastric cancer (GC). Currently, no definite therapy and drugs for H. pylori-related GC have been widely acknowledged although H. pylori infection could be eradicated in early stage. Inflammation and immune response are spontaneous essential stages during H. pylori infection. H pylori may mediate immune escape by affecting inflammation and immune response, leading to gastric carcinogenesis. As an important component of transcriptome, non-coding RNAs (ncRNAs) have been proven to play crucial roles in the genesis and development of H. pylori-induced GC. This review briefly described the effects of ncRNAs on H. pylori-related GC from the perspective of inflammation and immune response, as well as their association with inflammatory reaction and immune microenvironment. We aim to explore the potential of ncRNAs as markers for the early diagnosis, prognosis, and treatment of H. pylori-related GC. The ncRNAs involved in H. pylori-related GC may all hold promise as novel therapeutic targets for immunotherapy.

ObjectivesA bibliometric analysis for non-coding RNA and hepatitis B virus (HBV)-related hepatocellular carcinoma (HCC) was performed to describe international research status and visualize the research scope and emerging trends over the last two decades on this topic.Materials and methodsResearch data of non-coding RNA and HBV-related HCC were retrieved and extracted from the Web of Science Core Collection (WoSCC) database from 1 January 2003 to 13 June 2022 and then analyzed by means of bibliometric methods. A total of 1,036 articles published in this field were assessed for specific characteristics, including the year of publication, journal, author, institution, country/region, references, and keywords. VOSviewer was employed to perform co-authorship, co-occurrence, and co-citation analyses accompanied by constructing a visual network.ResultsOverall, 1,036 reports on non-coding RNA and HBV-related HCC from 2003 to 2022 were retrieved from WoSCC. The publication has gradually increased during the last two decades with 324 journals involved. Most research records (748 publications and 23,184 citations) were concentrated in China. A co-occurrence cluster analysis for the top 100 keywords was performed and four clusters were generated: (1) non-coding RNA as a molecular marker for the diagnosis and prognosis of HBV-related HCC; (2) dysregulation of non-coding RNA by hepatitis B virus X protein (HBx); (3) non-coding RNA affecting the biological behaviors of HBV-related HCC; and (4) epidemiological study for the effects of non-coding RNA on the risk of HBV-related HCC.ConclusionThe publications and citations involved in non-coding RNA and HBV-related HCC have increased over the last two decades associated with many countries, institutions, and authors. Our study revealed current development trends, global cooperation models, basic knowledge, research hotspots, and emerging frontiers in this field.

Improving healthy life expectancy by targeting aging-related pathological changes has been the spotlight of geroscience. Scorpions have been used in traditional medicine in Asia and Africa for a long time. We have isolated heat-resistant peptides from scorpion venom of Buthusmartensii Karsch (SVHRP) and found that SVHRP can attenuate microglia activation and protect Caenorhabditis elegans (C. elegans) against β-amyloid toxicity. Based on the amino acid sequence of these peptides, scorpion venom heat–resistant synthesized peptide (SVHRSP) was prepared using polypeptide synthesis technology. In the present study, we used C. elegans as a model organism to assess the longevity-related effects and underlying molecular mechanisms of SVHRSP in vivo. The results showed that SVHRSP could prolong the lifespan of worms and significantly improve the age-related physiological functions of worms. SVHRSP increases the survival rate of larvae under oxidative and heat stress and decreases the level of reactive oxygen species and fat accumulation in vivo. Using gene-specific mutation of C. elegans, we found that SVHRSP-mediated prolongation of life depends on Daf-2, Daf-16, Skn-1, and Hsf-1 genes. These results indicate that the antiaging mechanism of SVHRSP in nematodes might be mediated by the insulin/insulin-like growth factor-1 signaling pathway. Meanwhile, SVHRSP could also up-regulate the expression of stress-inducing genes Hsp-16.2, Sod-3, Gei-7, and Ctl-1 associated with aging. In general, our study may have important implications for SVHRSP to promote healthy aging and provide strategies for research and development of drugs to treat age-related diseases.

Intrusion detection has become a research focus in internet information security, with deep learning algorithms playing a crucial role in its development. Typically, intrusion detection data are transformed into a two-dimensional matrix by segmenting, stacking and padding them with zeros for input into deep learning models. However, this method consumes computational resources and fails to consider the correlation between features. In this paper, we transform the data into images through visualization operations and propose an information entropy weighted scheme to optimize the collision element problem during the transformation process. This method enhances the correlation between pixel frame features, leading to approximately 2% improvement in accuracy of the classification model when using the generated image samples for detection in experiments. To address the issues of insensitivity to target feature locations and incomplete feature extraction in traditional neural networks, this paper introduces a new network model called CBAM-CapsNet, which combines the advantages of the lightweight Convolutional Block Attention Module and capsule networks. Experimental results on the UNSW-NB15 and IDS-2017 datasets demonstrate that the proposed model achieves accuracies of 92.94% and 99.72%, respectively. The F1 scores obtained are 91.83% and 99.56%, indicating a high level of detection. [ABSTRACT FROM AUTHOR]