Search

Abstract Loss to follow-up (LTFU) in tuberculosis (TB) management increases morbidity and mortality, challenging effective control strategies. This study aims to develop and evaluate machine learning models to predict loss to follow-up in TB patients, improving treatment adherence and outcomes. Retrospective data encompassing tuberculosis patients who underwent treatment or registration at the National Center for Clinical Medical Research on Infectious Diseases from January 2017 to December 2021 were compiled. Employing machine learning techniques, namely SVM, RF, XGBoost, and logistic regression, the study aimed to prognosticate LTFU. A comprehensive cohort of 24,265 tuberculosis patients underwent scrutiny, revealing a LTFU prevalence of 12.51% (n = 3036). Education level, history of hospitalization, alcohol consumption, outpatient admission, and prior tuberculosis history emerged as precursors for pre-treatment LTFU. Employment status, outpatient admission, presence of chronic hepatitis/cirrhosis, drug adverse reactions, alternative contact availability, and health insurance coverage exerted substantial influence on treatment-phase LTFU. XGBoost consistently surpassed alternative models, boasting superior discriminative ability with an average AUC of 0.921 for pre-treatment LTFU and 0.825 for in-treatment LTFU. Our study demonstrates that the XGBoost model provides superior predictive performance in identifying LTFU risk among tuberculosis patients. The identification of key risk factors highlights the importance of targeted interventions, which could lead to significant improvements in treatment adherence and patient outcomes.

Purpose: Osteoarthritis (OA) is a prevalent cause of disability in older adults. Identifying diagnostic markers for OA is essential for elucidating its mechanisms and facilitating early diagnosis. Methods: We analyzed 53 synovial tissue samples (n = 30 for OA, n = 23 for the control group) from two datasets in the Gene Express Omnibus (GEO) database. We identified differentially expressed genes (DEGs) between the groups and applied dimensionality reduction using six machine learning algorithms to pinpoint characteristic genes (key genes). We classified the OA samples into subtypes based on these key genes and explored the differences in biological functions and immune characteristics among subtypes, as well as the roles of the key genes. Additionally, we constructed a protein-protein interaction network to predict small molecules that target these genes. Further, we accessed synovial tissue sample data from the single-cell RNA dataset GSE152805, categorized the cells into various types, and examined variations in gene expression and their correlation with OA progression. Validation of key gene expression was conducted in cellular experiments using the qPCR method. Results: Four genes AGMAT, MAP3K8, PER1, and XIST, were identified as characteristic genes of OA. All can independently predict the occurrence of OA. With these genes, the OA samples can be clustered into two subtypes, which showed significant differences in functional pathways and immune infiltration. Eight cell types were obtained by analyzing the single-cell RNA data, with synovial intimal fibroblasts (SIF) accounting for the highest proportion in each sample. The key genes were found over-expressed in SIF and significantly correlated with OA progression and the content of immune cells (ICs). We validated the relative levels of key genes in OA and normal cartilage tissue cells, which showed an expression trend consistency with the bioinformatics result except for XIST. Conclusion: Four genes, AGMAT, MAP3K8, PER1, and XIST are closely related to the progression of OA, and play as diagnostic and predictive markers in early OA.

Purpose: The development of tumor vaccines has become a hot topic in immunotherapy for osteosarcoma (OS); however, more tumor antigens with stronger immunogenicity need to be identified. Methods: We downloaded six sets of gene expression profile data from online databases. The overexpressed genes were analyzed, intersected, and used to calculate the immune infiltration abundance in the TARGET OS dataset based on their expression matrix. Potential tumor antigen genes were identified based on whether they exhibited a high correlation with the antigen-presenting cells (APCs). A total of 1330 immune-related genes (IRGs) from the ImmPort website were retrieved based on their expression, and the Consensus Cluster method was used to obtain immune subtypes of the OS samples. Prognosis, immune microenvironment, and sensitivity to drugs were compared among the immune subtypes. Results: In total, 680 genes were overexpressed in at least two datasets, of which TREM2, TNFRSF12A, and THY1 were positively correlated with different APCs. Based on the expression matrix of 1330 IRGs in TARGET-OS, two immune subtypes, IS1 and IS2, were identified. The prognosis of the IS1 subtype was better than that of IS2, the expression of immune checkpoint (ICP)-related genes was higher in patients with the IS1 subtype, and immune cell infiltration and sensitivity to 16 drugs were generally higher in IS1 subtype patients. Conclusion: We identified three APC-correlated genes that can be considered to code for potential novel tumor antigens for OS vaccines. Two immune subtypes in patients with OS were identified to implement personalized treatments using mRNA vaccines.

At present, a large number of rumors are mixed in with various kinds of news, such as current affairs, politics, social economy, and military activities, which seriously reduces the credibility of Internet information and hinders the positive development of various fields. In previous research on rumors, most scholars have focused their attention on the textual features, contextual semantic features, or single-emotion features of rumors but have not paid attention to the chain reaction caused by the hidden emotions in comments in social groups. Therefore, this paper comprehensively uses the emotional signals in rumor texts and comments to extract emotional features and determines the relationship between them to establish dual-emotion features. The main research achievements include the following aspects: (1) this study verifies that, in the field of affective characteristics, the combination of rumor-text emotion and comment emotion is superior to other baseline affective characteristics, and the detection performance of each component is outstanding; (2) the results prove that the combination of dual-emotion features and a semantic-feature-based detector (BiGRU and CNN) can improve the effectiveness of the detector; (3) this paper proposes reconstructing the dataset according to time series to verify the generalization ability of dual affective features; (4) the attention mechanism is used to combine domain features and semantic features to extract more fine-grained features. A large number of data experiments show that the dual-emotion features can be effectively compatible with an existing rumor detector, enhance the detector’s performance, and improve the detection accuracy.

ObjectiveThe purpose of this review is to identify the impact of virtual reality (VR) technology on student engagement, specifically cognitive engagement, behavioral engagement, and affective engagement.MethodsA comprehensive search of databases such as Google, Scopus, and Elsevier was conducted to identify English-language articles related to VR and classroom engagement for the period from 2014 to 2023. After systematic screening, 33 articles were finally reviewed.ResultsThe use of VR in the classroom is expected to improve student engagement and learning outcomes, and is particularly effective for students with learning disabilities. However, introducing VR into middle school education poses several challenges, including difficulties in the education system to keep up with VR developments, increased demands on students’ digital literacy, and insufficient proficiency of teachers in using VR.ConclusionTo effectively utilize VR to increase student engagement, we advocate for educational policymakers to provide training and technical support to teachers to ensure that they can fully master and integrate VR to increase student engagement and instructional effectiveness.

BackgroundIn recent years, the attitudes of middle school principals toward virtual reality (VR) have received much attention from the educational technology community. As VR continues to gain popularity in education, researchers have begun to explore middle school principals’ perceptions of VR using the Technology Acceptance Model (TAM) (perceived usefulness, and perceived ease of use) and Technology Readiness Index (TRI) (optimism, innovativeness, discomfort, and insecurity) models to explore middle school principals’ perceptions of VR. This helps to reveal the influencing factors of middle school principals’ acceptance of VR, which in turn provides theoretical support and guidance for promoting the application of VR in education.MethodsTo explore the factors influencing the acceptance of VR by middle school principals. We searched several databases such as Google, Scopus, and Elsevier. We focused on peer-reviewed English-language publications on VR, TAM, TRI, and middle school education from 2013 to 2023.ResultsThrough the literature review, we found that middle school principals’ intention to use VR was significantly influenced by the TAM (perceived usefulness, perceived ease of use) and TRI (optimism, innovation, discomfort, and insecurity) models. In addition, there was some degree of intersection between the dimensions of the TRI and TAM models.ConclusionVR has been widely recognized by middle school principals as an educational tool. By providing an immersive and interactive experience, VR can be effective in improving the efficiency of school operations to a great extent.

BackgroundOsteoarthritis (OA) progression involves multiple factors, including cartilage erosion as the basic pathological mechanism of degeneration, and is closely related to chondrocyte apoptosis. To analyze the correlation between apoptosis and OA development, we selected apoptosis genes from the differentially expressed genes (DEGs) between OA and normal samples from the Gene Expression Omnibus (GEO) database, used lasso regression analysis to identify characteristic genes, and performed consensus cluster analysis to further explore the pathogenesis of this disease.MethodsThe Gene expression profile datasets of OA samples, GSE12021 and GSE55235, were downloaded from GEO. The datasets were combined and analyzed for DEGs. Apoptosis-related genes (ARGs) were collected from the GeneCards database and intersected with DEGs for apoptosis-related DEGs (ARDEGs). Least absolute shrinkage and selection operator (LASSO) regression analysis was performed to obtain characteristic genes, and a nomogram was constructed based on these genes. A consensus cluster analysis was performed to divide the patients into clusters. The immune characteristics, functional enrichment, and immune infiltration statuses of the clusters were compared. In addition, a protein–protein interaction network of mRNA drugs, mRNA-transcription factors (TFs), and mRNA-miRNAs was constructed.ResultsA total of 95 DEGs were identified, of which 47 were upregulated and 48 were downregulated, and 31 hub genes were selected as ARDEGs. LASSO regression analysis revealed nine characteristic genes: growth differentiation factor 15 (GDF15), NAMPT, TLR7, CXCL2, KLF2, REV3L, KLF9, THBD, and MTHFD2. Clusters A and B were identified, and neutrophil activation and neutrophil activation involved in the immune response were highly enriched in Cluster B, whereas protein repair and purine salvage signal pathways were enriched in Cluster A. The number of activated natural killer cells in Cluster B was significantly higher than that in Cluster A. GDF15 and KLF9 interacted with 193 and 32 TFs, respectively, and CXCL2 and REV3L interacted with 48 and 82 miRNAs, respectively.ConclusionARGs could predict the occurrence of OA and may be related to different degrees of OA progression.

Flavobacterium columnare is the causative agent of columnaris disease in freshwater fish. Columnaris disease can cause heavy economic losses in aquaculture. In this study, whole-genome sequencing was used to characterize this pathogen. F. columnare isolate AH-01 had a circular chromosome and plasmid that encoded a total of 3,022 genes. Isolate GX-01 only had a circular chromosome and encoded 2,965 genes. Genomic islands, prophage regions, and CRISPR/Cas systems were identified in both genomes. Both genomes presented evidence of gene variation and horizontal transfer, both of which are the essential components of genetic diversity, genome plasticity, and functional evolution. Single-gene phylogeny and comparative genome analyses were performed to investigate the variation and evolution of this pathogen. Genetic analysis of 16S rRNA and housekeeping gene sequences significantly clustered 55 F. columnare isolates into four clades. The intragroup identity of the 16S rRNA gene exceeded 99%, while the intergroup identity was below the species delineation threshold. We discovered significant translocation, inversion, and rearrangement events that influenced local synteny within each group. Notably, the observed alignments varied considerably among all the studied groups. The core genomes of all strains with available sequences comprised 747 genes, corresponding to approximately 25% of the genome. Core genome multilocus sequence typing, genome-wide orthology and phylogenetic analyses, and average nucleotide identity suggested that the currently existing F. columnare was an assemblage of several distinct species, with levels of divergence at least equivalent to those between recognized bacterial species. The present investigation provided genomic evidence of gene variation and horizontal transfer, which were the basis of genetic diversity, genome plasticity, and functional evolution. The findings supported a proposed new taxonomic perspective on F. columnare.

Microorganisms play very important roles in carcinogenesis, tumor progression, and resistance upon treatment. Due to the challenge of accurately acquiring samples and quantifying low-biomass tissue microorganisms, most studies have focused on the effect of gut microorganisms on cancer treatments, especially the efficacy of immunotherapy. Although recent publications reveal the potential interactions between intratumor microorganisms and the immune microenvironment, whether and to what extent the intratumor microorganism could affect progression and treatment outcome remain controversial. This study is aiming to evaluate the associations among intratumor microorganisms, DNA methylation cancer driver genes, immune response, and clinical outcomes from a pan-cancer perspective, using 6,876 TCGA samples across 21 cancer types. We revealed that tumor microorganism dysbiosis is closely associated with the abnormal tumor methylome and/or tumor microenvironment, which might serve to enhance the proliferation ability and fitness for the therapy of tumors. These findings shed the light on a better understanding of the interactions between tumor cells and carcinogens during and after tumor formation, as well as microorganism-associated methylation alterations that could further serve as biomarkers for clinical outcome assessment.

Label discrimination is challenging in fluorescence microscopy due to broad spectra and narrow lifetime distribution. Here, the authors introduce extra kinetic dimensions by illuminating reversibly photoswitchable fluorophores with different intensities, and discriminate 20 spectrally similar fluorophores.

As an essential part of the network-based intrusion detection systems (IDS), malicious traffic detection using deep learning methods has become a research focus in network intrusion detection. However, even the most advanced IDS available are challenging to satisfy real-time detection because they usually need to accumulate the packets into particular flows and then extract the features, causing processing delays. In this paper, using the deep learning approach, we propose a deep hierarchical network for malicious traffic detection at the packet-level, capable of learning the features of traffic from raw packet data. It used the one-dimensional convolutional layer to extract the spatial features of raw packets and Gated Recurrent Units (GRU) structure to extract the temporal features. To evaluate the performance of our approach, experiments were conducted to examine the efficiency of the proposed deep hierarchical network based on the ISCX2012 dataset, USTC-TFC2016 dataset and CICIDS2017 dataset, respectively. Accuracy (ACC), detection rate (DR) and false alarm rate (FAR) are the metrics for evaluation. In the ISCX2012 dataset, our approach achieved 99.42%, 99.74%, 1.77% on ACC, DR and FAR, respectively. In USTC-TFC2016, there were 99.94%, 99.99%, 0.99%. In CICIDS2017, there were 100%, 100%, 0%. Furthermore, we discussed the impact of data balanced on classification performance and the time efficiency between the Long Short-Term Memory (LSTM) model and the GRU model. Experiments show that our approach can effectively detect malicious traffic and outperform sout s many other state-of-the-art methods in terms of ACC and DR.

The resistance of Lactobacillus plantarum to vancomycin depends on its peptidoglycan composition. Vancomycin has poor binding affinity with peptidoglycan precursors ending in D-alanyl-D-lactate (D-Ala-D-Lac) but binds strongly to peptidoglycan precursors ending in D-alanyl-D-alanine (D-Ala-D-Ala), resulting in resistance and sensitivity, respectively. The ligase Ddl, which generates D-Ala-D-Lac or D-Ala-D-Ala incorporated into the peptidoglycan precursor chain, is responsible for this specificity. To study the effect of peptidoglycan precursors on immunity, we constructed several strains of L. plantarum expressing the ddl gene of Lactococcus lactis to change their peptidoglycan precursors. The change in the termini of the peptidoglycan precursors was determined by the sensitivity of the strains to vancomycin. The overexpression of ddl increased the susceptibility of the strains to vancomycin. We further explored the regulation of the macrophage inflammatory response pathway by the wild-type and constructed strains, and found that these strains induced the MyD88-dependent TRAF6/MAPK pathway, and the increase in D-Ala L. plantarum peptidoglycan precursors increased the secretion of the inflammatory factors IL-6, IL-1β and TNF-α. These results indicate that D-Ala-ended peptidoglycan precursors play a central role in the variable immunomodulatory ability of L. plantarum.

Social media fake news has become a pervasive and problematic issue today with the development of the internet. Recent studies have utilized different artificial intelligence technologies to verify the truth of the news and provide explanations for the results, which have shown remarkable success in interpretable fake news detection. However, individuals’ judgments of news are usually hierarchical, prioritizing valuable words above essential sentences, which is neglected by existing fake news detection models. In this paper, we propose an interpretable novel neural network-based model, the hierarchical co-attention selection network (HCSN), to predict whether the source post is fake, as well as an explanation that emphasizes important comments and particular words. The key insight of the HCSN model is to incorporate the Gumbel–Max trick in the hierarchical co-attention selection mechanism that captures sentence-level and word-level information from the source post and comments following the sequence of words–sentences–words–event. In addition, HCSN enjoys the additional benefit of interpretability—it provides a conscious explanation of how it reaches certain results by selecting comments and highlighting words. According to the experiments conducted on real-world datasets, our model outperformed state-of-the-art methods and generated reasonable explanations.

This paper proposes an improved method for the prediction of radial vibration in switched reluctance motor (SRM) considering magnetic saturation. In this paper, the basic modeling principle is briefly introduced, it is based on the derivation that the peak acceleration is dependent on the product of phase current and current gradient idi/dt. However, the derivation may cause errors due to saturation effect. Thus in this paper, the discrete sample data are firstly acquired based on DC pulse measurement method, by which electromagnetic, torque and peak acceleration characteristics can all be acquired. Then the entire peak acceleration characteristics are obtained by improved Least Square Support Vector Machine (LSSVM). Based on the obtained static peak acceleration characteristics, the time-varied radial vibration model is established based on superposition of natural oscillations of dominant vibration modes. Finally, a simulation model is built up using MATLAB/Simulink. The good agreement between simulation and experiment shows that the proposed method for modeling is feasible and accurate, even under saturation. In addition, since LSSVM does not need any prior knowledge, it is much easier for modeling compared with other existing literatures.

Post-embedding correlative light and electron microscopy (CLEM) has the advantage of high-precision registration and enables light and electron microscopy imaging of the same slice. However, its broad application has been hampered by the limited available fluorescent proteins (FPs) and a low signal-to-background ratio (SBR). Here, we developed a green photoswitchable FP, mEosEM-E with substantially high on/off contrast in EM samples embedded in Epon resin, which maximally preserves cellular structures but quenches the fluorescence of FPs. Taking advantage of the photoswitching property of mEosEM-E, the autofluorescence background from the resin was significantly reduced by a subtraction-based CLEM (sCLEM) method. Meanwhile, we identified a red fluorescent protein (RFP) mScarlet-H that exhibited higher brightness and SBR in resin than previously reported RFPs. With mEosEM-E and mScarlet-H, dual-colour post-Epon-embedding CLEM images with high SBR and no cross-talk signal were successfully performed to reveal the organization of nucleolar proteins. Moreover, a dissection of the influences of different EM sample preparation steps on the fluorescence preservation for several RFPs provides useful guidance for further probe development.

In wireless sensor networks, it is a typical threat to source privacy that an attacker performs backtracing strategy to locate source nodes by analyzing transmission paths. With the popularity of the Internet of Things in recent years, source privacy protection has attracted a lot of attentions. In order to mitigate this threat, many proposals show their merits. However, they fail to get the tradeoff between multipath transmission and transmission cost. In this paper, we propose a constrained random routing mechanism, which can constantly change routing next-hop instead of a relative fixed route so that attackers cannot analyze routing and trace back to source nodes. First, we design a specific selection domain which is located around the sending node according to the dangerous distance and the wireless communication range. Then sending nodes calculate the selected weights of the candidate nodes according to their offset angles in this domain. Finally, the selected weights help to decide which node will become the next hop. In this way, attackers would be confused by the constantly changing paths. The simulation results prove that our proposal can achieve high routing efficiency in multi-path transmission, while only introducing a controllable energy consumption, end-to-end delay and redundant paths.

In the past two decades, various super-resolution (SR) microscopy techniques have been developed to break the diffraction limit using subdiffraction excitation to spatially modulate the fluorescence emission. Photomodulatable fluorescent proteins (FPs) can be activated by light of specific wavelengths to produce either stochastic or patterned subdiffraction excitation, resulting in improved optical resolution. In this review, we focus on the recently developed photomodulatable FPs or commonly used SR microscopies and discuss the concepts and strategies for optimizing and selecting the biochemical and photophysical properties of PMFPs to improve the spatiotemporal resolution of SR techniques, especially time-lapse live-cell SR techniques.

The task of cross-target stance detection faces significant challenges due to the lack of additional background information in emerging knowledge domains and the colloquial nature of language patterns. Traditional stance detection methods often struggle with understanding limited context and have insufficient generalization across diverse sentiments and semantic structures. This paper focuses on effectively mining and utilizing sentiment-semantics knowledge for stance knowledge transfer and proposes a sentiment-aware hierarchical attention network (SentiHAN) for cross-target stance detection. SentiHAN introduces an improved hierarchical attention network designed to maximize the use of high-level representations of targets and texts at various fine-grain levels. This model integrates phrase-level combinatorial sentiment knowledge to effectively bridge the knowledge gap between known and unknown targets. By doing so, it enables a comprehensive understanding of stance representations for unknown targets across different sentiments and semantic structures. The model’s ability to leverage sentiment-semantics knowledge enhances its performance in detecting stances that may not be directly observable from the immediate context. Extensive experimental results indicate that SentiHAN significantly outperforms existing benchmark methods in terms of both accuracy and robustness. Moreover, the paper employs ablation studies and visualization techniques to explore the intricate relationship between sentiment and stance. These analyses further confirm the effectiveness of sentence-level combinatorial sentiment knowledge in improving stance detection capabilities. [ABSTRACT FROM AUTHOR]