Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Background: s/Aims: Sarcomatoid hepatocellular carcinoma (HCC) is a rare histological subtype of HCC characterized by extremely poor prognosis; however, its molecular characterization has not been elucidated. Methods: In this study, we conducted an integrated multiomics study of whole-exome sequencing, RNA-seq, spatial transcriptome, and immunohistochemical analyses of 28 paired sarcomatoid tumor components and conventional HCC components from 10 patients with sarcomatoid HCC, in order to identify frequently altered genes, infer the tumor subclonal architectures, track the genomic evolution, and delineate the transcriptional characteristics of sarcomatoid HCCs. Results: Our results showed that the sarcomatoid HCCs had poor prognosis. The sarcomatoid tumor components and the conventional HCC components were derived from common ancestors, mostly accessing similar mutational processes. Clonal phylogenies demonstrated branched tumor evolution during sarcomatoid HCC development and progression. TP53 mutation commonly occurred at tumor initiation, whereas ARID2 mutation often occurred later. Transcriptome analyses revealed the epithelial–mesenchymal transition (EMT) and hypoxic phenotype in sarcomatoid tumor components, which were confirmed by immunohistochemical staining. Moreover, we identified ARID2 mutations in 70% (7/10) of patients with sarcomatoid HCC but only 1–5% of patients with non-sarcomatoid HCC. Biofunctional investigations revealed that inactivating mutation of ARID2 contributes to HCC growth and metastasis and induces EMT in a hypoxic microenvironment. Conclusions We offer a comprehensive description of the molecular basis for sarcomatoid HCC, and identify genomic alteration (ARID2 mutation) together with the tumor microenvironment (hypoxic microenvironment), that may contribute to the formation of the sarcomatoid tumor component through EMT, leading to sarcomatoid HCC development and progression.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Background: s/Aims: Sarcomatoid hepatocellular carcinoma (HCC) is a rare histological subtype of HCC characterized by extremely poor prognosis; however, its molecular characterization has not been elucidated. Methods: In this study, we conducted an integrated multiomics study of whole-exome sequencing, RNA-seq, spatial transcriptome, and immunohistochemical analyses of 28 paired sarcomatoid tumor components and conventional HCC components from 10 patients with sarcomatoid HCC, in order to identify frequently altered genes, infer the tumor subclonal architectures, track the genomic evolution, and delineate the transcriptional characteristics of sarcomatoid HCCs. Results: Our results showed that the sarcomatoid HCCs had poor prognosis. The sarcomatoid tumor components and the conventional HCC components were derived from common ancestors, mostly accessing similar mutational processes. Clonal phylogenies demonstrated branched tumor evolution during sarcomatoid HCC development and progression. TP53 mutation commonly occurred at tumor initiation, whereas ARID2 mutation often occurred later. Transcriptome analyses revealed the epithelial–mesenchymal transition (EMT) and hypoxic phenotype in sarcomatoid tumor components, which were confirmed by immunohistochemical staining. Moreover, we identified ARID2 mutations in 70% (7/10) of patients with sarcomatoid HCC but only 1–5% of patients with non-sarcomatoid HCC. Biofunctional investigations revealed that inactivating mutation of ARID2 contributes to HCC growth and metastasis and induces EMT in a hypoxic microenvironment. Conclusions We offer a comprehensive description of the molecular basis for sarcomatoid HCC, and identify genomic alteration (ARID2 mutation) together with the tumor microenvironment (hypoxic microenvironment), that may contribute to the formation of the sarcomatoid tumor component through EMT, leading to sarcomatoid HCC development and progression.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Background: s/Aims: Sarcomatoid hepatocellular carcinoma (HCC) is a rare histological subtype of HCC characterized by extremely poor prognosis; however, its molecular characterization has not been elucidated. Methods: In this study, we conducted an integrated multiomics study of whole-exome sequencing, RNA-seq, spatial transcriptome, and immunohistochemical analyses of 28 paired sarcomatoid tumor components and conventional HCC components from 10 patients with sarcomatoid HCC, in order to identify frequently altered genes, infer the tumor subclonal architectures, track the genomic evolution, and delineate the transcriptional characteristics of sarcomatoid HCCs. Results: Our results showed that the sarcomatoid HCCs had poor prognosis. The sarcomatoid tumor components and the conventional HCC components were derived from common ancestors, mostly accessing similar mutational processes. Clonal phylogenies demonstrated branched tumor evolution during sarcomatoid HCC development and progression. TP53 mutation commonly occurred at tumor initiation, whereas ARID2 mutation often occurred later. Transcriptome analyses revealed the epithelial–mesenchymal transition (EMT) and hypoxic phenotype in sarcomatoid tumor components, which were confirmed by immunohistochemical staining. Moreover, we identified ARID2 mutations in 70% (7/10) of patients with sarcomatoid HCC but only 1–5% of patients with non-sarcomatoid HCC. Biofunctional investigations revealed that inactivating mutation of ARID2 contributes to HCC growth and metastasis and induces EMT in a hypoxic microenvironment. Conclusions We offer a comprehensive description of the molecular basis for sarcomatoid HCC, and identify genomic alteration (ARID2 mutation) together with the tumor microenvironment (hypoxic microenvironment), that may contribute to the formation of the sarcomatoid tumor component through EMT, leading to sarcomatoid HCC development and progression.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective To explore the computed tomography angiography(CTA)and clinical features of Takayasu's arteritis(TA)with peripheral artery involvement.Methods In this retrospective study,CTA scan was performed in a total of 184 TA patients.TA patients were divided into two groups:60 patients within peripheral artery involvement(peripheral artery involvement group)and 124 patients without peripheral artery involvement(peripheral artery non-involvement group).The difference in comparison of clini-cal data and CTA findings were analyzed.Results A total of 194 peripheral arteries were involved in 60 patients.The most suscep-tible peripheral artery were axillary artery(52,26.8％),middle cerebral artery(26,13.4％)and femoral artery(22,11.3％).In the peripheral artery involvement group,the most common CTA manifestation was luminal stenosis(141,72.7％).The lumen dilata-tion,lumen stenosis with dilatation and wall calcification were not easy to be observed.The age and duration of disease in peripheral artery involvement group were significantly greater than those in peripheral artery non-involvement group(P＜0.05).The proportion of the peripheral artery involvement group in the active phase was significantly lower than that of the peripheral artery non-involvement group(P＜0.05).The incidence of pain in the limbs in peripheral artery involvement group was significantly higher than that in peripheral artery non-involvement group(P＜0.05).The utilization rate of tocilizumab in the peripheral artery involvement group was significantly higher than that in the peripheral artery non-involvement group(P＜0.05).Conclusion TA involving peripheral arteries is more common in patients with a long course of disease and in the inactive phase.Patients are prone to pain in their limbs.The CT A manifestations of these patients are also special,that is,the involved peripheral arteries are not prone to lumen dilatation and wall calcification.

Objective To observe the application effect of montelukast sodium combined with terbutaline on cough variant asthma(CVA)in children and its influence on airway remodeling and peripheral blood inflammatory indicators.Methods The children with CVA were randomly classified into control group and treatment group.The control group was given aerosol inhalation of terbutaline(5 mg each time,twice a day),and on the basis of the control group,the treatment group was combined with oral administration of montelukast sodium granules(4 mg each time,once a day,taking before going to bed),and both groups were continuously treated for 3 months.The clinical efficacy,airway cross-section area(AO),airway lumen area(AI),airway wall thickness(T),airway wall area(WA),serum interleukin-5(IL-5),eosinophilic chemotactic factor(Eotaxin),macrophage inflammatory protein-1α(MIP-1α)and T lymphocyte subgroups CD4+,CD8+and CD4+/CD8+were compared between the two groups of children,and the medication safety was assessed.Results Fifty-three cases in control group and 53 cases in treatment group were included.After treatment,the total effective rates in treatment group and control group were 96.23％(51 cases/53 cases)and 83.02％(44 cases/53 cases),respectively(P＜0.05).The AO values in treatment group and control group were(39.42±3.67)and(45.69±4.92)mm2;AI values were(22.36±2.85)and(27.06±3.18)mm2;T values were(1.12±0.28)and(1.44±0.33)mm;WA values were(53.82±4.17)and(60.13±4.66)mm2;serum IL-5 levels were(25.46±5.83)and(41.46±7.64)ng·L-1;Eotaxin levels were(181.24±30.05)and(238.21±39.42)ng·L-1;MIP-1a levels were(15.24±3.67)and(22.43±4.05)ng·L-1;CD4+levels were(37.18±4.06)％and(33.57±3.82)％;CD8+levels were(24.08±3.15)％and(27.31±3.07)％;and CD4+/CD8+levels were 1.54±0.33 and 1.24±0.28,respectively(all P＜0.05).The total incidences of adverse drug reactions in treatment group and control group were 9.43％(5 cases/53 cases)and 3.77％(2 cases/53 cases),respectively(P＞0.05).Conclusion Montelukast sodium combined with terbutaline has an exact efficacy in the treatment of CVA in children,and it can effectively reverse airway remodeling,reduce inflammation level and enhance immune function,and it has good safety.