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.

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.

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.

italic>Salmonella has emerged as a promising tumor-targeting strategy in recent years due to its good tumor targeting ability and certain safety. In order to further optimize its therapeutic effect, scientists have tried to modify Salmonella, including its attenuation and drug loading. This paper summarizes the mechanism and research progress of Salmonella-mediated targeted tumor therapy, and introduces the strategies and related progress of its modification and optimization. At the same time, the advantages, current challenges and future development directions of Salmonella-mediated tumor therapy are summarized.

This article discussed the evolution of the traditional preparation process of Pinelliae Rhizoma Fermentata.The production methods for Pinelliae Rhizoma Fermentata in Song Dynasty include cake-making of Pinelliae Rhizoma together with ginger juice and fermentation after cake-making,and the former method of cake-making was the mainstream.The process technology in Jin and Yuan Dynasties inherited from that in Song Dynasty,and the application of Pinelliae Rhizoma Fermentata had certain limitations.The medical practitioners of Ming Dynasty elucidated the mechanism of processing of Pinelliae Rhizoma Fermentata,and proposed the view of"sliced Pinelliae Rhizoma being potent while fermented Pinelliae Rhizoma being mild".In the Ming Dynasty,LI Shi-Zhen defined the cake-making process and fermentation process for Pinelliae Rhizoma,and HAN Mao's Han Shi Yi Tong(Han's Clear View of Medicine)contained five prescriptions for the processing of Pinelliae Rhizoma Fermentata,which had the epoch-making signficance in the expansion of prescriptions for the processing of Pinelliae Rhizoma Fermentata.In the Qing Dynasty,HAN Fei-Xia's ten methods for making Pinelliae Rhizoma Fermentata were summarized on the basis of the methods recorded in Han Shi Yi Tong,and at that time,the processing of Pinelliae Rhizoma Fermentata and the preparation of Massa Medicata Fermentata interacted with each other.After the founding of the People's Republic of China,the local experience in the preparation of Pinelliae Rhizoma Fermentata was deeply influenced by the methods in the Qing Dynasty,and the local preparation technical standards gradually became the same.Moreover,this article also explored the issues of the importance of"Pinelliae Rhizoma"and"ingredients for fermentation",the pre-treatment of Pinelliae Rhizoma,the distinction between cake-making process and fermentation process for Pinelliae Rhizoma,the amount of flour added as well as the timing of adding,the addition of Massa Medicata Fermentata powder,the role of Alum in Pinelliae Rhizoma Fermentata and so on.

Inflammatory bowel disease (IBD) is characterized by chronic relapsing intestinal inflammation and encompasses ulcerative colitis (UC) and Crohn's disease (CD). IBD has emerged as a global healthcare problem. Clinically efficacious therapeutic agents are deficient. This study concentrates on models of ulcerative colitis with the objective of discovering novel therapeutic strategies. Previous investigations have established that schisandrin A demonstrates anti-inflammatory effects in vitro, concurrently enhancing the transcriptional activity of farnesoid X receptor (FXR). FXR inversely modulates the transcriptional activity of NF-κB, which has an important role in regulating inflammatory responses. Consequently, the current study was to explore the safeguarding influence of schisandrin A on ulcerative colitis and delineate the mechanism by which it regulates this effect through the FXR signaling pathway. The effect of schisandrin A on the mRNA levels of inflammatory factors was evaluated in RAW264.7 cells. The dual luciferase reporter gene assay was used to verify the relationship between schisandrin A and FXR targeting. The animal experiments were performed in accordance with the regulations of the Animal Ethics Committee of Shanghai University of Traditional Chinese Medicine (approval No. PZSHUTCM2304250005). Acute ulcerative colitis was induced in wild-type or FXR knockout C57BL/6 mice by drinking 3% dextran sodium sulfate (DSS) for 7 days, and schisandrin A was administered via gavage for a continuous treatment period of 7 days. The body weight and faecal were monitored daily. The mRNA levels of inflammatory factors in colon tissue and FXR target genes were measured by RT-qPCR. The findings revealed that schisandrin A, in vitro, impeded the lipopolysaccharide (LPS)-induced elevation in mRNA levels of inflammatory factors and schisandrin A could augment transcriptional activity of FXR. In wild-type mice, schisandrin A significantly improved weight loss, colon shortening, loose stools and blood in stools in mice with acute ulcerative colitis, and schisandrin A significantly reduced the expression of pro-inflammatory factors genes and significantly increased the expression of FXR target genes in colon tissues. In FXR knockout mice, the administration of schisandrin A failed to yield ameliorative effect on acute ulcerative colitis in mice. In conclusion, schisandrin A can reduce intestinal inflammation through the FXR signaling pathway to alleviate acute ulcerative colitis in mice. Implications arise that Schisandra lignans could serve as lead compounds for drug development aimed at inflammatory bowel disease.

Objective To explore the difference in the effectiveness between proximal femoral nail anti-rotation(PFNA)and proximal femoral locking compression plate(PFLCP)of intertrochanteric fracture in the elderly patients combined with knee osteoarthritis.Methods The clinical data of 65 intertrochanteric femoral fractures combined with knee osteoarthritis be-tween June 2015 and February 2021 were retrospectively analyze.They were divided into two groups according to the different surgical methods.PFNA group was composed of 36 patients,12 males and 24 females,aged from 61to 88 years old with an av-erage of(77.0±6.4)years old.There were 17 cases of left injury and 19 cases of right injury.According to modified Evans clas-sification,there were 3 cases of type Ⅱ,19 cases of type Ⅲ,10 cases of type Ⅳ,and 4 cases of type Ⅴ.PFLCP group was com-posed of 29 patients,11 males and 18 females,aged from 60 to 92 years old with an average of(78.8±6.5)years old.There were 14 cases of left injury and 15 cases of right injury.According to modified Evans classification,there were 2 cases of typeⅡ,18 cases of type Ⅲ,7 cases of type Ⅳ,and 2 cases of type Ⅴ.Comparison of operation time,intraoperation blood loss,postoperative bed time,incidence of postoperative complications,Harris score at 6 months and 1 year postoperation.Results All 65 patients were followed up ranging from 12 to 24 months with an average of(16.9±3.6)months.In the PFNA and PFLCP groups,the operation time was respectively(57.6±6.8)min and(77.4±6.5)min,the intraoperative blood loss was(128.3±50.3)ml and(156.3±23.9)ml,postoperative bed time was(4.0±2.5)days and(8.1±2.0)days,Harris score at 6 months post-operative was(45.3±8.6)points and(36.3±7.0)points.There were significant differences between two groups(P＜0.05).Inci-dence of postoperative complications was 19.4％(7/36)and 34.5％(10/29),Harris score at 1 year postoperative was(60.8±6.7)points and(59.0±8.1)points.There was no significant difference between the two groups(P＞0.05).Conclusion Compared with PFLCP,PFNA treatment of elderly patients with knee osteoarthritis between the femoral intertrochanteric fractures shorter surgical time,less intraoperative blood loss,bed rest after surgery,short-term hip function recovery better,when the affected knee joint can tolerate traction,can be used as a priority.

Circulating tumor DNA (ctDNA) comes from tumor, reflecting the genetic information of the tumor well, and will change with the progress of tumor. In recent years, the unique capabilities of ctDNA have attracted much attention and been widely studied. In this paper, based on the summary of the source, properties and sample processing of ctDNA, its detection technology and application in cancer diagnosis and treatment are reviewed. The roles and importance of ctDNA reference material in second-generation sequencing are described. The urgency of establishing uniform standards and specifications of ctDNA in various processes, such as samples collection, storage, quantitative testing and data analysis, has been pointed out.