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.

Biomolecular condensates are formed through phase separation of biomacromolecules such as proteins and RNAs. These condensates exhibit liquid-like properties that can futher transition into more stable material states. They form complex internal structures via multivalent weak interactions, enabling precise spatiotemporal regulations. However, the use of inconsistent and non-standardized terminology has become increasingly problematic, hindering academic exchange and the dissemination of scientific knowledge. Therefore, it is necessary to discuss the terminology related to biomolecular condensates in order to clarify concepts, promote interdisciplinary cooperation, enhance research efficiency, and support the healthy development of this field.

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 To study the traditional Chinese medicine(TCM)syndromes of patients with chronic heart failure(CHF)combined with diuretic resistance by using the Wenyang Huayin Yangxin Prescription,and to observe its therapeutic efficacy.Methods A total of 68 CHF patients complicated with diuretic resistance and who had Yangqi deficiency and presenting blood stasis syndrome combined with Tanyin were randomly assigned to a control group and an observation group.The control group was given intravenous furosemide(≥ 80 mg/d)via infusion pump in addition to standard Western medical treatment,while the observation group was given intravenous furosemide(＜80 mg/d)via infusion pump along with the Wenyang Huayin Yangxin Prescription(30 g Astragalus,15 g Poria,15 g Baizhu,15 g Chuanxiong,10 g Danfu tablet,10 g Cassia,10 g Alisma,and 10 g Zhimu).The quantitative index of diuretic resistance was used as the primary outcome measure.In addition,the differences between the two groups in TCM syndromes,cardiac function-related indicators,incidence of endpoint events,and readmission rate were compared.Results After 2 weeks of treatment,the filtration sodium excretion fraction(FENa)in the observation group was(0.18±0.04)％,while that of the control group was(0.16±0.03)％,showing a statistically significant difference(P=0.037).The 24-hour urine volume and urine Na+/K+ratio in the observation group increased significantly from baseline levels and were higher than those in the control group(P＜0.05).The differences in the changes of 24-hour urine volume,urine sodium,FENa,and urine Na+/K+ratio between the two groups were statistically significant(P＜0.05).The TCM syndrome scores decreased in both groups after 2 weeks of treatment,with the observation group showing a significantly greater reduction compared with the control group(P＜0.001).The differences in the changes of TCM syndrome scores between the two groups were statistically significant(P＜0.001).After 2 weeks of treatment,the observation group showed significant improvements in palpitations,shortness of breath,facial and limb edema,spontaneous sweating,chest tightness(pain),asthma,and oliguria compared with the baseline data(P＜0.05),while the control group showed improvements only in facial and limb edema,asthma,and oliguria(P＜0.05).Except for the asthma syndrome after 2 weeks of treatment,the observation group showed better outcomes in spontaneous sweating,chest tightness(pain),asthma,and oliguria at various time points after treatment compared with the control group(P＜0.05).After 2 weeks of treatment,the observation group had significantly better cardiac output(CO)and stroke volume(SV)compared with those of the control group(P＜0.05).The differences in the changes in N-terminal pro-brain natriuretic peptide(NT-proBNP),left ventricular ejection fraction(LVEF),SV,and CO between the two groups were statistically significant(P＜0.05).After 24 weeks of follow-up,no significant differences in the incidence of end-point events or readmission rates between the two groups were observed.Conclusion The Wenyang Huayin Yangxin Prescription,combined with low-dose intravenous furosemide administered through an infusion pump,can improve the TCM syndromes of patients with Yangqi deficiency and blood stasis syndrome combined with Tanyin in addition to CHF complicated by diuretic resistance.This treatment improves the patients'heart function and diuretic resistance,reduces the intravenous dosage of diuretic,and enhances clinical efficacy.This approach should be more widely applied in clinical settings.

Objective To explore the application and effectiveness of the apprenticeship education model in Chinese herbal medicine teaching at Western medical college.Methods By comparing classic lecture-based teaching with a combined approach integrating apprenticeship education,the study assesses the impact on student learning outcomes.Participants included students from the 2018 cohort of the eight-year clinical medicine program and the 2022 cohort of the"4+4"pilot program at Peking Union Medical College,who received classic teaching methods and apprenticeship case-based teaching methods,respectively.Upon course completion,students completed a 14-item multiple-choice questionnaire covering essential theory of Chinese medicine,as well as specific categories such as qi-regulating,blood-activating herbs,among others.Results The overall accuracy rate in the apprenticeship case-based teaching group was significantly higher than that in the classic teaching group(P＜0.01).Conclusions The apprenticeship education model of Traditional Chinese Medicine has a positive effect on teaching of Chinese herbal medicine at West-ern medical college and warrants further promotion and application.

Objective To explore the effectiveness of the"apprenticeship case-based teaching"method in the in-struction of traditional Chinese medicine(TCM)formulas for nursing students.Methods A quasi-experimental study was conducted with 135 undergraduate nursing students from the 2023 cohort at Peking Union Medical Col-lege.Participants were randomly assigned to an experimental group(receiving apprenticeship case-based teaching)or a control group(receiving conventional teaching).Teaching effectiveness was evaluated through classroom in-struction followed by a routine test.The test covered the indications and key diagnostic points of eight representative TCM formulas.Results The experimental group overruns the control group on most test items.Statistically signifi-cant differences(P＜0.05)were observed in questions related to Ma Huang Tang,Xiao Chai Hu Tang,Da Cheng Qi Tang,Liu Wei Di Huang Wan,and Ba Zheng San.Conclusions The apprenticeship case-based teaching meth-od significantly enhances students'learning gain about key diagnostic principles in TCM formulas and improves ca-pacity building of clinical reasoning.This method should be shared by schools of nursing in the teaching reformation of TCM curriculum.

Spinal cord injury(SCI)is a central nervous system disease that can lead to motor,sensory,and autonomic dysfunction.Depending on the state of immune microenvironment,macrophage polarization can differentiate into M1/M2 phenotypes.The regulation of macrophage polarization by stem cells in many pathophysiological processes of SCI has become a hot topic of research in recent years.This review summarizes the relationship between macrophage polarization and SCI,and how mesenchymal stem cells(MSCs)and neural stem cells(NSCs)regulate macrophage polarization to improve SCI through paracrine secretion,delivery molecules,derived exosomes,and metabolic reprogramming pathways.It also summarizes the mechanism by which stem cells regulate the macrophage polarization phenotypes to promote SCI recovery through signaling pathways such as Janus tyrosine kinase/signal transducer and activator of transcription(JAK/STAT),Notch,Toll-like receptor 4/nuclear factor kappa-B(TLR4/NF-κB),phosphatidylinositol 3 kinase/protein kinase B(PI3K/Akt).The aim is to provide theoretical support for the treatment of SCI by regulating macrophage polarization with stem cells and to offer new perspectives for exploring the mechanism of stem cell therapy for SCI.