RESUMEN
This study aims to develop and validate a machine learning (ML) predictive model for assessing mortality in patients with malignant tumors and hyperkalemia (MTH). We extracted data on patients with MTH from the Medical Information Mart for Intensive Care-IV, version 2.2 (MIMIC-IV v2.2) database. The dataset was split into a training set (75%) and a validation set (25%). We used the Least Absolute Shrinkage and Selection Operator (LASSO) regression to identify potential predictors, which included clinical laboratory indicators and vital signs. Pearson correlation analysis tested the correlation between predictors. In-hospital death was the prediction target. The Area Under the Curve (AUC) and accuracy of the training and validation sets of 7 ML algorithms were compared, and the optimal 1 was selected to develop the model. The calibration curve was used to evaluate the prediction accuracy of the model further. SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) enhanced model interpretability. 496 patients with MTH in the Intensive Care Unit (ICU) were included. After screening, 17 clinical features were included in the construction of the ML model, and the Pearson correlation coefficient was <0.8, indicating that the correlation between the clinical features was small. eXtreme Gradient Boosting (XGBoost) outperformed other algorithms, achieving perfect scores in the training set (accuracy: 1.000, AUC: 1.000) and high scores in the validation set (accuracy: 0.734, AUC: 0.733). The calibration curves indicated good predictive calibration of the model. SHAP analysis identified the top 8 predictive factors: urine output, mean heart rate, maximum urea nitrogen, minimum oxygen saturation, minimum mean blood pressure, maximum total bilirubin, mean respiratory rate, and minimum pH. In addition, SHAP and LIME performed in-depth individual case analyses. This study demonstrates the effectiveness of ML methods in predicting mortality risk in ICU patients with MTH. It highlights the importance of predictors like urine output and mean heart rate. SHAP and LIME significantly enhanced the model's interpretability.
Asunto(s)
Hiperpotasemia , Unidades de Cuidados Intensivos , Aprendizaje Automático , Neoplasias , Humanos , Hiperpotasemia/diagnóstico , Hiperpotasemia/mortalidad , Femenino , Masculino , Unidades de Cuidados Intensivos/estadística & datos numéricos , Persona de Mediana Edad , Pronóstico , Neoplasias/mortalidad , Neoplasias/complicaciones , Anciano , Mortalidad Hospitalaria , AlgoritmosRESUMEN
AIM OF THE STUDY: This study aimed to determine the effect of Epimedium brevicornu Maxim. (EF) on osteoporosis (OP) and its underlying molecular mechanisms, and to explore the existence of the "Gut-Bone Axis". MATERIAL AND METHODS: The impact of EF decoction (EFD) on OP was evaluated using istopathological examination and biochemical assays. Targeted metabolomics was employed to identify key molecules and explore their molecular mechanisms. Alterations in the gut microbiota (GM) were evaluated by 16S rRNA gene sequencing. The role of the GM was clarified using an antibiotic cocktail and faecal microbiota transplantation. RESULTS: EFD significantly increased the weight (14.06%), femur length (4.34%), abdominal fat weight (61.14%), uterine weight (69.86%), and insulin-like growth factor 1 (IGF-1) levels (59.48%), while reducing serum type I collagen cross-linked carboxy-terminal peptide (CTX-I) levels (15.02%) in osteoporotic mice. The mechanism of action may involve the regulation of the NLRP3/cleaved caspase-1/IL-1ß signalling pathway in improving intestinal tight junction proteins and bone metabolism. Additionally, EFD modulated the abundance of related GM communities, such as Lactobacillus, Coriobacteriaceae, bacteria of family S24-7, Clostridiales, and Prevotella, and increased propionate and butyrate levels. Antibiotic-induced dysbiosis of gut bacteria disrupted OP regulation of bone metabolism, which was restored by the recovery of GM. CONCLUSIONS: Our study is the first to demonstrate that EFD works in an OP mouse model by utilising GM and butyric acid. Thus, EF shows promise as a potential remedy for OP in the future.
Asunto(s)
Caspasa 1 , Epimedium , Microbioma Gastrointestinal , Interleucina-1beta , Proteína con Dominio Pirina 3 de la Familia NLR , Osteoporosis , Transducción de Señal , Animales , Proteína con Dominio Pirina 3 de la Familia NLR/metabolismo , Microbioma Gastrointestinal/efectos de los fármacos , Osteoporosis/tratamiento farmacológico , Osteoporosis/metabolismo , Transducción de Señal/efectos de los fármacos , Caspasa 1/metabolismo , Ratones , Femenino , Interleucina-1beta/metabolismo , Modelos Animales de Enfermedad , Ratones Endogámicos C57BL , Huesos/efectos de los fármacos , Huesos/metabolismo , Factor I del Crecimiento Similar a la Insulina/metabolismo , Trasplante de Microbiota FecalRESUMEN
At present, China's economic development has entered a "new normal." Exploring industrial ecological efficiency (IEE) in the background of economic transformation is of great significance to promote China's industrial transformation and upgrading and achieving high-quality economic development. Based on the super-efficiency DEA model, this study evaluated the IEE of cities in the Yellow River Basin from 2008 to 2017. Exploratory spatial data analysis methods were used to explore the spatial-temporal evolutionary characteristics, and a panel regression model was established to explore the influencing factors of IEE. The research results showed that the IEE in the Yellow River Basin exhibited an elongated S-shaped evolutionary trend from 2008 to 2017, and the mean IEE of cities presented a trend, whereby Yellow River Basin's regions could be ranked in the following order: lower reaches > middle reaches > upper reaches. There was significant spatial autocorrelation of the IEE in the Yellow River Basin, and the hot and cold spots showed an obvious "spatial clubs" phenomenon. The results of panel regression show that the influence factors of IEE in the Yellow River Basin showed spatial heterogeneity in their effect.
Asunto(s)
Desarrollo Económico , Ríos , China , Ciudades , Eficiencia , IndustriasRESUMEN
In this work, a series of experiments were carried out to study the kinetic inhibition performance of N-butyl-N-methylpyrrolidinium tetrafluoroborate ([BMP][BF4]), poly(N-vinylcaprolactam) (PVCap) and compound inhibitor systems on methane hydrate from both macroscopic and microscopic perspectives. In the macroscopic experiments, the influence of the concentration, the ratio of inhibitors, the subcooling on the induction time and gas consumption rate of methane hydrate were studied. The results indicated that [BMP][BF4] could inhibit the growth rate of CH4 hydrate, but failed to delay the nucleation. An improved inhibitory effect was observed by combining [BMP][BF4] and PVCap, and the optimal ratio of the two inhibitors was obtained to gain the best inhibition performance. Furthermore, the microstructure and morphology of methane hydrate crystals formed in different inhibitor systems were investigated through powder X-ray diffraction (PXRD), Raman spectroscopy and scanning electron cryomicroscopy (Cryo-SEM) methods. It was found that [BMP][BF4] and PVCap had different influences on the large cage occupancy by CH4 and the morphology of methane hydrate.
RESUMEN
In energy-constrained wireless sensor networks (WSNs), the design of an energy-efficient smart strategy is a key to extend the network lifetime, but the unbalance of energy consumption and node load severely restrict the long-term operation of the network. To address these issues, a novel routing algorithm which considers both energy saving and load balancing is proposed in this paper. First of all, the transmission energy consumption, node residual energy and path hops are considered to create the link cost, and then a minimum routing graph is generated based on the link cost. Finally, in order to ensure the balance of traffic and residual energy of each node in the network, an "edge-cutting" strategy is proposed to optimize the minimum routing graph and turn it into a minimum routing tree. The simulation results show that, the proposed algorithm not only can balance the network load and prolong the lifetime of network, but meet the needs of delay and packet loss rate.