Background Patients with COVID-19 in the intensive care unit (ICU) have a high mortality rate, and methods to assess patients’ prognosis early and administer precise treatment are of great significance. Objective The aim of this study was to use machine learning to construct a model for the analysis of risk factors and prediction of mortality among ICU patients with COVID-19. Methods In this study, 123 patients with COVID-19 in the ICU of Vulcan Hill Hospital were retrospectively selected from the database, and the data were randomly divided into a training data set (n=98) and test data set (n=25) with a 4:1 ratio. Significance tests, correlation analysis, and factor analysis were used to screen 100 potential risk factors individually. Conventional logistic regression methods and four machine learning algorithms were used to construct the risk prediction model for the prognosis of patients with COVID-19 in the ICU. The performance of these machine learning models was measured by the area under the receiver operating characteristic curve (AUC). Interpretation and evaluation of the risk prediction model were performed using calibration curves, SHapley Additive exPlanations (SHAP), Local Interpretable Model-Agnostic Explanations (LIME), etc, to ensure its stability and reliability. The outcome was based on the ICU deaths recorded from the database. Results Layer-by-layer screening of 100 potential risk factors finally revealed 8 important risk factors that were included in the risk prediction model: lymphocyte percentage, prothrombin time, lactate dehydrogenase, total bilirubin, eosinophil percentage, creatinine, neutrophil percentage, and albumin level. Finally, an eXtreme Gradient Boosting (XGBoost) model established with the 8 important risk factors showed the best recognition ability in the training set of 5-fold cross validation (AUC=0.86) and the verification queue (AUC=0.92). The calibration curve showed that the risk predicted by the model was in good agreement with the actual risk. In addition, using the SHAP and LIME algorithms, feature interpretation and sample prediction interpretation algorithms of the XGBoost black box model were implemented. Additionally, the model was translated into a web-based risk calculator that is freely available for public usage. Conclusions The 8-factor XGBoost model predicts risk of death in ICU patients with COVID-19 well; it initially demonstrates stability and can be used effectively to predict COVID-19 prognosis in ICU patients.
The aim of the present study was to investigate the potential role of microRNA (miRNA or miR) in invasion and metastasis of non-small cell lung cancer (NSCLC). miRNA-microarray analysis was used to detect the differentially expressed miRNAs between various metastatic levels of NSCLC cells. The microarray results were verified by quantitative polymerase chain reaction. The most clearly altered miRNA, miR-339-5p, was transfected into NSCLC cells and cell migration and invasion were investigated. The expression of miR-339-5p was 3.4662-fold higher in the lower metastatic NSCLC cells. miR-339-5p significantly decreased tumor-cell migration and the invasion capacity in vitro. In conclusion, miR-339-5p is important in NSCLC invasion and metastasis, indicating that miR-339-5p could be further evaluated as a biomarker for predicting the survival time of patients with NSCLC.
Background The rapid outbreak of coronavirus disease 2019 (COVID-19) is a major health concern, in response to which widespread risk factor research is being carried out. Objective To discover how physical activity and lifestyle affect the epidemic as well as the disease severity and prognosis of COVID-19 patients. Methods This multicenter, retrospective cohort study included 203 adults infected with COVID-19 and 228 uninfected adults in three Chinese provinces, with 164 (80.7%) of the infected participants and 188 (82.5%) of the uninfected participants answering a doctor-administered telephone questionnaire on lifestyle. The binary logistic regression model and the ordinal logit model were used to observe relevance. Results Comparing sick and non-sick patients, we found that irregular exercise ( P =0.004), sedentary lifestyle ( P =0.010), and overexertion ( P <0.001) may be associated with the susceptibility to COVID-19. In symptomatic patients, using the recommended status as a reference, risk of severe infection increased with decreased sleep status, being 6.729 (95% CI=2.138–21.181) times higher for potentially appropriate sleep ( P =0.001) and peaking at 8.612 (95% CI=1.913–38.760) times higher for lack of sleep ( P =0.005). Reduction in average daily sleep time significantly increased the likely severity ( P =0.002). Discussion Through further examination of damage of external lung organs, we found that lack of sleep affected not only disease severity but also prognosis. Based on these findings, the public should prioritize a healthy lifestyle and get adequate sleep in response to the outbreak. The study of life habits may bring new ideas for the prevention and treatment of COVID-19.
A four-year-old boy developed recurrent fever and severe pneumonia in April, 2022. High-throughput sequencing revealed a reassortant avian influenza A-H3N8 virus (A/Henan/ZMD-22-2/2022(H3N8) with avian-origin HA and NA genes. The six internal genes were acquired from Eurasian lineage H9N2 viruses. Molecular substitutions analysis revealed the haemagglutin retained avian-like receptor binding specificity but that PB2 genes possessed sequence changes (E627K) associated with increased virulence and transmissibility in mammalian animal models. The patient developed respiratory failure, liver, renal, coagulation dysfunction and sepsis. Endotracheal intubation and extracorporeal membrane oxygenation were administered. H3N8 RNA was detected from nasopharyngeal swab of a dog, anal swab of a cat, and environmental samples collected in the patient’s house. The full-length HA sequences from the dog and cat were identical to the sequence from the patient. No influenza-like illness was developed and no H3N8 RNA was identified in family members. Serological testing revealed neutralizing antibody response against ZMD-22-2 virus in the patient and three family members. Our results suggest that a triple reassortant H3N8 caused severe human disease. There is some evidence of mammalian adaptation, possible via an intermediary mammalian species, but no evidence of person-to-person transmission. The potential threat from avian influenza viruses warrants continuous evaluation and mitigation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.