An exploration on the machine-learning-based stroke prediction model.

Introduction: With the rapid development of artificial intelligence technology, machine learning algorithms have been widely applied at various stages of stroke diagnosis, treatment, and prognosis, demonstrating significant potential. A correlation between stroke and cytokine levels in the human body has recently been reported. Our study aimed to establish machine-learning models based on cytokine features to enhance the decision-making capabilities of clinical physicians. Methods: This study recruited 2346 stroke patients and 2128 healthy control subjects from Chongqing University Central Hospital. A predictive model was established through clinical experiments and collection of clinical laboratory tests and demographic variables at admission. Three classification algorithms, namely Random Forest, Gradient Boosting, and Support Vector Machine, were employed. The models were evaluated using methods such as ROC curves, AUC values, and calibration curves. Results: Through univariate feature selection, we selected 14 features and constructed three machine-learning models: Support Vector Machine (SVM), Random Forest (RF), and Gradient Boosting Machine (GBM). Our results indicated that in the training set, the RF model outperformed the GBM and SVM models in terms of both the AUC value and sensitivity. We ranked the features using the RF algorithm, and the results showed that IL-6, IL-5, IL-10, and IL-2 had high importance scores and ranked at the top. In the test set, the stroke model demonstrated a good generalization ability, as evidenced by the ROC curve, confusion matrix, and calibration curve, confirming its reliability as a predictive model for stroke. Discussion: We focused on utilizing cytokines as features to establish stroke prediction models. Analyses of the ROC curve, confusion matrix, and calibration curve of the test set demonstrated that our models exhibited a strong generalization ability, which could be applied in stroke prediction.

Development of rapid nucleic acid testing techniques for common respiratory infectious diseases in the Chinese population.

Background: Most respiratory viruses can cause serious lower respiratory diseases at any age. Therefore, timely and accurate identification of respiratory viruses has become even more important. This study focused on the development of rapid nucleic acid testing techniques for common respiratory infectious diseases in the Chinese population. Methods: Multiplex fluorescent quantitative polymerase chain reaction (PCR) assays were developed and validated for the detection of respiratory pathogens including the novel coronavirus (SARS-CoV-2), influenza A virus (FluA), parainfluenza virus (PIV), and respiratory syncytial virus (RSV). Results: The assays demonstrated high specificity and sensitivity, allowing for the simultaneous detection of multiple pathogens in a single reaction. These techniques offer a rapid and reliable method for screening, diagnosis, and monitoring of respiratory pathogens. Conclusion: The implementation of these techniques might contribute to effective control and prevention measures, leading to improved patient care and public health outcomes in China. Further research and validation are needed to optimize and expand the application of these techniques to a wider range of respiratory pathogens and to enhance their utility in clinical and public health settings.

Application Value of Combined Detection of miR-208 and miR-92a in Early Diagnosis of Myocardial Infarction.

Objective: Myocardial infarction (MI) is a common and serious cardiovascular disease with increasing incidence and mortality rates, making it a major global public health issue. Molecular biology research has shown that the cleavage products miR-208 and miR-92a are microRNAs (miRNAs) associated with myocardial injury. Therefore, this study aims to establish a predictive model and explore the application value of the combined detection of miR-208 and miR-92a in the early diagnosis of MI in microRNA. Methods: Plasma samples were collected from 231 volunteers divided into 30 healthy and 201 diseased subjects From January 1st, 2021 to December 30th, 2021. Plasma RNA was extracted using a TRIZOL kit, and levels of miR-208 and miR-92a were determined using a real-time polymerase chain reaction (PCR) assay. Subsequently, the logistic regression model, decision tree model analysis, and receiver operating characteristic (ROC) curve were used to evaluate whether miR-208 combined with miR-92a could be used as a biomarker for MI early diagnosis. Results: In this study, the ROC curve evaluation of the logistic regression model and pruned decision tree model found that age, miR-208, and miR-92a had high early diagnostic accuracy for MI, and the area under the curve (AUC) reached 0.928, showing good predictive value. It was also found that the AUC, optimal threshold, sensitivity, and specificity of age, miR-208, and miR-92a were higher than those of age and miR-208. This indicates that the combination of age, miR-208, and miR-92a has more value in the early diagnosis of MI. Conclusion: The combined diagnosis of miR-208 and miR-92a is helpful for the early diagnosis of myocardial infarction, which might serve as a new marker of MI benefiting from its early diagnosis.

MIP From Legionella pneumophila Influences the Phagocytosis and Chemotaxis of RAW264.7 Macrophages by Regulating the lncRNA GAS5/miR-21/SOCS6 Axis.

Background: The intracellular pathogen Legionella pneumophila (L. pneumophila) is a causative agent of pneumonia and does great harm to human health. These bacteria are phagocytosed by alveolar macrophages and survive to replicate within the macrophages. Despite macrophage infectivity potentiator (MIP) protein serving as an essential virulence factor during the invasion process of L. pneumophila, the regulatory mechanism of MIP protein in the process of bacterial infection to host cells is not yet completely understood. This research thus aims to explore the interaction between MIP and macrophage phagocytosis. Methods: Through the experiment of the co-culture of RAW264.7 macrophages with different concentrations of MIP, the chemotactic activity of macrophages was detected and the phagocytosis was determined by a neutral red uptake assay. The expression of long noncoding RNA (lncRNA) GAS5, microRNA-21 (miR-21), and suppressor of cytokine signaling (SOCS)6 was determined by qRT-PCR. Target genes were detected by dual luciferase assay. Results: MIP could reduce the phagocytosis and improve the chemotaxis of RAW264.7 macrophages. The expression of both lncRNA GAS5 and SOCS6 was increased whereas the expression of miR-21 was decreased when macrophages were treated with MIP. Dual luciferase assay revealed that lncRNA GAS5 could interact with miR-21, and SOCS6 served as the target of miR-21. After GAS5 overexpression, the phagocytosis of RAW264.7 treated with MIP was increased whereas the chemotaxis was decreased. In contrast, the opposite results were found in RAW264.7 following GAS5 interference. Conclusions: The present results revealed that MIP could influence RAW264.7 macrophages on phagocytic and chemotactic activities through the axis of lncRNA GAS5/miR-21/SOCS6.

A Pan-Cancer Analysis on the Systematic Correlation of MutS Homolog 2 (MSH2) to a Malignant Tumor.

MutS homolog 2 (MSH2) is a crucial participant in human DNA repair, and lots of the studies functionally associated with it were begun with hereditary nonpolyposis colorectal cancer (HNPCC). MSH2 has also been reported to take part in the progresses of various tumors' formation. With the help of GTEx, CCLE, and TCGA pan-cancer databases, the analysis of MSH2 gene distribution in both tumor tissues and normal control tissues was carried out. Kaplan-Meyer survival plots and COX regression analysis were conducted for the assessment into the MSH2's impact on tumor patients' clinical prognosis. In an investigation to the association of MSH2 expression with immune infiltration level of various tumors and a similar study on tumor immune neoantigens, microsatellite instability was subsequently taken. It was found that high expression of MSH2 is prevalent in most cancers. MSH2's efficacy on clinical prognosis as well as immune infiltration in tumor patients revealed a fact that expression of MSH2 in prostate adenocarcinoma (PRAD), brain lower-grade glioma (LGG), breast-invasive carcinoma (BRCA), and head and neck squamous cell carcinoma (HNSC) posed a significant correlation with the immune cell infiltration level of patients. Likewise as above, MSH2's expression comes in a similar trend with tumor immune neoantigens and microsatellite instability. MSH2's expression in the majority of tumors is a direct factor to the activation of tumor-associated pathways as well as immune-associated pathways. MSH2's early screening or even therapeutic target role for sarcoma (SARC) diagnosis is contributing to the efficiency of early screening and overall survival in SARC patients.

Heat inactivation decreases the qualitative real-time RT-PCR detection rates of clinical samples with high cycle threshold values in COVID-19.

SARS-CoV-2 has caused COVID-19 pandemic globally in the beginning of 2020, and qualitative real-time RT-PCR has become the gold standard in diagnosis. As SARSCoV-2 with strong transmissibility and pathogenicity, it has become a professional consensus that clinical samples from suspected patients should be heat inactivated at 56°C for 30 min before further processing. However, previous studies on the effect of inactivation on qualitative real-time RT-PCR were conducted with diluted samples rather than clinical samples. The aim of this study was to investigate whether heat inactivation on clinical samples before detection will affect the accuracy of qualitative real-time RT-PCR detection. All 46 throat swab samples from 46 confirmed inpatients were detected by qualitative real-time RT-PCR directly, as well as after heat inactivation. Heat-Inactivation has significantly influenced the qualitative detection results on clinical samples, especially weakly positive samples. The results indicate the urgency to establish a more suitable protocol for COVID-19 clinical sample's inactivation.

Islet-1 promotes the cardiac-specific differentiation of mesenchymal stem cells through the regulation of histone acetylation.

The aim of the present study was to investigate the effects of Islet-1 on the process of mesenchymal stem cell (MSC) differentiation into cardiomyocyte-like cells and to elucidate the possible mechanisms involved. Lentiviral vectors expressing Islet-1 (Lenti-Islet-1) were constructed and used for C3H10T1/2 cell transfection. Cell morphology was observed. Cardiac-related genes and proteins were detected by qPCR and western blot analysis. Epigallocatechin gallate (EGCG) was used as an inhibitor of acetylated histone H3 (AcH3). AcH3 was detected by chromatin immunoprecipitation. Cells overexpressing Islet-1 tended to change into fibroblast-like cells and were arranged in the same direction. The enhanced expression of GATA binding protein 4 (Gata4), NK2 homeobox 5 (Nkx2.5), myocyte enhancer factor 2C (Mef2c) and cardiac troponin T (cTnT) was observed in the cells overexpressing Islet-1 following transfection with Lenti-Islet-1. However, the expression of hepatocyte-, bone- and neuronal-specific markers was not affected by Islet-1. The AcH3 relative amount increased following transfection with Lenti-Islet-1, which was associated with the enhanced expression of Gata4, Nkx2.5 and Mef2c in these cells. The expression of Gata4, Nkx2.5 and Mef2c in the C3H10T1/2 cells transfected with Lenti-Islet-1 and treated with EGCG was reduced following treatment with EGCG. The data presented in this study indicate that Islet-1 specifically induces the differentiation of C3H10T1/2 cells into cardiomyocyte-like cells, and one of the mechanisms involved is the regulation of histone acetylation.