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.

Major depressive disorder(MDD)is a prevalent con-dition associated with substantial impairment and low remission rates.Traditional antidepressants demonstrate delayed effects,low cure rate,and inadequate therapeutic effectiveness for man-aging treatment-resistant depression(TRD).Several studies have shown that ketamine,a non-selective N-methyl-D-aspartate receptor(NMDAR)antagonist,can produce rapid and sustained antidepressant effects.Ketamine has demonstrated efficacy for reducing suicidality in TRD patients.However,the pharmaco-logical mechanism for ketamine's antidepressant effects remains incompletely understood.Previous research suggests that the an-tidepressant effects of ketamine may involve the monoaminergic,glutamatergic and dopaminergic systems.This paper provides an overview of the pharmacological mechanism for ketamine's anti-depressant effects and discuss the potential directions for future research.

Here,5 important pathogens carried by ticks in Maanshan City,Anhui Province,China were identified.In to-tal,642 ticks were collected from 13 villages around Maanshan City and identified by morphological and mitochondrial COI genes.The 16S rRNA gene of Francisella tularensis,ssrA gene of Bartonella,16S rRNA,ompA and ompB genes of Rickett-sia,16S rRNA and gltA genes of Anaplasma,and groEL and rpoB genes of Coxiella were sequenced.Reference sequences were retrieved from a public database.Phylogenetic trees were constructed with MEG A1 1.0 software.In total,36 Rickettsiae isolates were detected in 640 Haemaphysalis longicornis ticks,which included 20 isolates of Rickettsia heilongjian-gensis,16 of Candidatus Rickettsia jingxinensis,2 of Ana-plasma bovis,and 186 of Coxiella-like endosymbiont.R.hei-longjiangensis HY2 detected in this study and Anhui B8 strain,Ca.R.jingxinensis QL3 and those from Shanxi Prov-ince and Jiangsu Province,A.bovis JX4 and those from Shanxi Province were clustered on the same branch.Overall,17 ticks had combined infections and none of the 5 bacteria were detected in two Amblyomma testudinarium ticks.This is the first report of Ca.R.jingxinensis detected in H.longicornis ticks from Anhui Province.It is recommended that the two types of Rickettsia that cause spotted fever and A.bovis should be reported to local health authorities to initiate appropriate prevention and control measures.

Objective To establish an ideal modeling method for diarrhea predominant irritable bowel syndrome(IBS-D)with anxiely and depression in rats,and to provide a basis for the clinical study of IBS-D.Methods 60 rats were used in this study.(1)At first,20 rats were randomly divided into blank,3%acetic acid enema,4%acetic acid enema,and 5%acetic acid enema groups.After the modeling and observation period,the diarrhea status and the degree of colon injury caused by different modeling concentrations were observed by diarrhea related index and colon histopathology.(2)After the optimal modeling concentration was assessed,40 rats were randomly divided into control(a),acetic acid enema(b),acetic acid+binding(c),and acetic acid+binding+tail clip(d)groups and correspondingly treated for 8 days.After the treatments,the general condition,diarrhea-related index,open field test(OFT)score,and colonic histopathology of rats were evaluated.Results(1)Compared with the blank group,the fecal trait score of 4%acetic acid enema group was increased on days 1 to 3 after intervention(P＜0.001),and gradually decreased on days 4 to 7 after intervention.After 1 week,there was no significant difference between the fecal trait score and that of the blank group(P＞0.05).Body weight was lower(P＜0.01),fecal water content was higher(P＜0.001).Compared with blank group,body weight of the 5%acetic acid enema group was decreased(P＜0.001),the fecal trait score and diarrhea index were increased(P＜0.01).No significant difference was found between 3%acetic acid enema and blank groups.The pathological colon tissue showed that,compared with the blank group,the mucosal structure of the 4%acetic acid enema group was complete with a small amount of inflammatory cell infiltration,and the pathological tissue score showed no significant difference(P＞0.05),whereas the 5%acetic acid enema had a medium to large amount of inflammatory cell infiltration,and the pathological tissue score was increased(P＜0.01).(2)Compared with group a,group b had lower body weight(P＜0.001),and higher fecal trait score,fecal water content and diarrhea index(P＜0.01).Compared with a and b groups,the body weight of c and d groups was lower(P＜0.001),the fecal traits score,fecal water content,and diarrhea index were increased(P＜0.01),and the colon running time was decreased(P＜0.01).Compared with group c,Fecal water content in group D was higher(P＜0.001).In the OFT score,compared with a and b groups,the OFT distance,standing times,and upright times in c and d groups were lower(P＜0.05).Compared with c,the OFT distance,standing times,and upright times in d group were lower(P＜0.05).The pathological tissue of colon showed that the mucosal structure of the four groups was complete,and there were different degrees of inflammatory cell infiltration.The pathological tissue scores of groups c and d were higher than those of groups a and b(P＜0.05).Conclusions The 4%acetic acid concentration is appropriate for IBS-D modeling.After superposition and binding,the IBS-D diarrhea and internal hypersensitivity characteristic state can be better simulated.After superposition of a tail clip,the IBS-D model of liver stagnation and spleen deficiency can be established successfully.

Objective To investigate the relationship between serum autotaxin,copeptin,lipopolysaccharide binding protein(LBP)and prognosis in patients with hepatitis B virus-related decompensated cirrhosis(HBV-DC)complicated with liver failure(LF).Methods 143 patients with HBV-DC complicated with LF who admitted to our hospital from February 2018 to August 2023 were selected as the research objects.Patients were followed up for 90 d,patients were divided into death group(55 cases)and survival group(88 cases)according to the prognosis,the levels of serum Autotaxin,Copeptin and LBP were compared between two groups.The clinical data of patients with HBV-DC complicated with liver failure were collected,the prognostic factors of HBV-DC complicated with LF patients were analyzed by univariate and multivariate Logistic regression models.The clinical value of serum Autotaxin,Copeptin and LBP alone or in combination in predicting the prognosis of patients with HBV-DC complicated with LF were analyzed by receiver operating characteristic(ROC)curve.Results 143 patients with HBV-DC complicated with LF 90 d follow-up,55 died,and 88 survived,with a mortality rate of 38.46％.Compared with survival group,the serum levels of Autotaxin,Copeptin and LBP in death group were significantly increased(P＜0.05).Compared with survival group,the proportion of hospitalization time ≥14 d,the proportion of ascites,the proportion of hepatic encephalopathy,alanine aminotransferase,total bilirubin and model for end-stage liver disease(MELD)score in death group were significantly increased(P＜0.05),and albumin was significantly decreased(P＜0.05),there was no significant difference in age,gender,diabetes mellitus,hypertension,serum creatinine,platelet count and fibrinogen(P＞0.05).Elevated total bilirubin,concurrent hepatic encephalopathy,elevated MELD score,and elevated serum Autotaxin,Copeptin,and LBP levels were risk factors for poor prognosis in patients with HBV-DC complicated with LF(P＜0.05).ROC curve results showed that,the area under the curve(AUC),sensitivity and specificity of combined detection of serum Autotaxin,LBP and Copeptin in predicting poor prognosis of patients with HBV-DC complicated with LF were 0.930,85.45％and 88.64％,respectively,which were significantly better than those of single index detection.Conclusion The high expression of serum Autotaxin,Copeptin and LBP are related to the risk of short-term death in patients with HBV-DC complicated with LF,and the combined detection has a high clinical predictive value for the occurrence of short-term death in patients with HBV-DC complicated with LF.

Relevant literature on TCM diagnostic and treatment equipment from January 1994 to May 2023 was collected with three Chinese databases,namely,China National Knowledge Infrastructure,Wanfang and Wipu.CiteSpace software was used for the analyses of the trend of annual publication volume,co-occurrence of publication institutions,co-occurrence of keywords,cluster and burst and the generation of corresponding knowledge graphs.It's pointed out TCM diagnostic and treatment equipment had problems in low publication volume and collaboration between research institutions,hotspots of Chinese medicine diagnosis and treatment,diagnosis and treatment equipment,diagnosis device,Chinese medicine diagnosis,diagnosis and treatment technology and traditional Chinese medicine,and research frontiers of artificial intelligence,medical alliance,curriculum design and innovation and entrepreneurship.References were provided for relevant research in China.[Chinese Medical Equipment Journal,2024,45(3):76-80]