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: 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 The affinity between placental transporters and perfluoroalkyl substances (PFAS) could affect the placental transport and toxicity of PFAS, while the study on the interaction between PFAS and placental transporters is limited. Objective To explore interactions between PFAS and placental transporters using molecular docking, and to provide a theoretical basis for PFAS toxicity prediction and fetal health risk assessment. Methods Fifteen PFAS compounds, each conformationally sampled and energy-minimized, and 16 placental transporters, represented by their 3D structures, were imported into a molecular docking software (MOE 20140901). For each PFAS, 30 distinct conformations were generated and docked into the active pockets of the transporters using a semi-flexible docking mode. Docking poses were primarily scored and ranked based on their calculated binding free energy (ΔG, kcal·mol⁻¹), with additional consideration given to hydrogen bonding interactions and the ligand's root mean square deviation (RMSD) at the binding site; the top 20 poses for each complex were subsequently output. Optimal binding configurations were identified as those exhibiting a relatively low binding free energy (ΔG ranging from −3 to −10 kcal·mol⁻¹), well-defined hydrogen bonds, and an RMSD ≤ 2.0 Å. The binding capabilities of the PFAS to the placental transporters were then evaluated based on these optimal docking results. Results The PFAS could bind to the placental transporters, with structural specificity. For example, the binding capabilities increased as the carbon chain length of PFAS increased, and it was also higher for PFOS alternatives than for PFOS. Besides, the binding capabilities of sulfonic PFAS with the same carbon chain length was also stronger than that of carboxylic PFAS. For example, the binding capabilities of PFOS (C8) to 15 placental transporters was higher than that of PFOA (C8), except for glucose transporter 1 (PFOS vs. PFOA: −4.14 vs. −4.14). Further, PFAS might be bound to the placental transporter through hydrogen, ionic, and hydrophobic interactions. Conclusion PFAS are able to bind the placental transporters, and its toxicity and exposure risk can’t be ignored.

The apprenticeship education of Traditional Chinese medicine(TCM)is an important pathway for the cultivation of talents in TCM education.The combination of institutional education and apprenticeship education is considered to be the most suitable educational model that aligns with the inherent characteristics of TCM education.The current status of TCM education in western medical institutions and the main challenges include the difficulty in transitioning between western and Chinese medical reasoning and limited clinical internship hours for TCM.The strengths and features of TCM apprenticeship education lie in cultural heritage,classical teachings,mentorship,practice orientation and personalized education.Therefore,integration of TCM apprenticeship education and clinical internships for western medical students represents a new educational model for medical undergraduates.

Objective To explore the relationship and internal path between activities of daily living(ADL),sleep quality and mental health of community elderly people in Shanghai.Methods A questionnaire survey was conducted among community residents aged 60 years and older seeing doctors in community health care center of five streets in Shanghai during Sept to Dec,2021 using convenience sampling.Activities of Daily Living(ADL),Pittsburgh Sleep Quality Index(PSQI)and 10-item Kessler Psychological Distress Scale(K10)were adopted in the survey.Single factor analysis,correlation analysis and multiple linear regression were used to analyze the data.The effect relationship between the variables was tested using Bootstrap's mediated effects test.Results A total of 1 864 participants were included in the study.The average score was 15.53±4.47 for ADL,5.60±3.71 for PSQI and 15.50±6.28 for K10.The rate of ADL impairment,poor sleep quality,poor and very poor mental health of the elderly were 23.6%,27.3%,11.9%and 4.9%,respectively.ADL and sleep quality were all positively correlated with mental health(r=0.321,P＜0.001;r=0.466,P＜0.001);ADL was positively correlated with sleep quality(r=0.294,P＜0.001).Multiple linear results of factors influencing mental health showed that ADL(β= 0.457,95%CI:0.341-0.573),sleep quality(β =0.667,95%CI:0.598-0.737)and mental health were positively correlated(P＜0.001).Sleep quality partially mediated the relationship between ADL and mental health(95%CI:0.078-0.124)with an effect size of 33.0%.Conclusion Sleep quality is a mediator between ADL and mental health among community elderly people.Improving ADL and sleep quality may improve mental health in the population.

Objective To prepare a nano drug(PFOB@Lip-MMC)with liposome as the carrier,liquid perfluorooc-tyl bromide(PFOB)as core and mitomycin C(MMC)loading on the liposome shell and study its inhibitory effect on the proliferation of human pterygium fibroblasts(HPFs).Methods The thin film dispersion-hydration ultrasonic method was used to prepare PFOB@Lip-MMC and detect its physical and chemical properties.Cell Counting Kit-8,Cam-PI cell viability staining and flow cytometry were employed to detect the impact of different concentrations of PFOB@Lip-MMC on the via-bility of HPFs.DiI fluorescence labeled PFOB@Lip-MMC was used to observe the permeability of the nano drug to HPFs under a laser confocal microscope.After establishing HPF inflammatory cell models,they were divided into the control group(with sterile phosphate-buffered saline solution added),PFOB@Lip group(with PFOB@Lip added),MMC group(with MMC added),PFOB@Lip-MMC group(with PFOB@Lip-MMC added)and normal group(with fresh culture medi-um added)according to the experimental requirements.After co-incubation for 24 h,flow cytometer was used to detect the apoptosis rate of inflammatory cells,and the gene expression levels of interleukin(IL)-1β,prostaglandin E2(PGE2),tumor necrosis factor(TNF)-α and vascular endothelial growth factor(VEGF)in cells were analyzed by PCR.Results The average particle size and Zeta potential of PFOB@Lip-MMC were(103.45±2.17)nm and(27.34±1.03)mV,respec-tively,and its entrapped efficiency and drug loading rate were(72.85±3.28)％and(34.27±2.04)％,respectively.The sustained-release MMC of drug-loaded nanospheres reached(78.34±2.92)％in vitro in a 24-hour ocular surface environ-ment.The biological safety of PFOB@Lip-MMC significantly improved compared to MMC.In terms of the DiI fluorescence labeled PFOB@Lip-MMC,after co-incubation with inflammatory HPFs for 2 h,DiI fluorescence labeling was diffusely dis-tributed in the cytoplasm of inflammatory HPFs.The apoptosis rate of inflammatory HPFs in the PFOB@Lip-MMC group[(77.23±4.93)％]was significantly higher than that in the MMC group[(51.62±3.28)％].The PCR examination results showed that the gene transcription levels of IL-1 β,PGE2,TNF-α and VEGF in other groups were significantly reduced com-pared to the control group and PFOB@Lip group,with the most significant decrease in the PFOB@Lip-MMC group(all P＜0.05).Conclusion In this study,a novel nano drug(PFOB@LIP-MMC)that inhibited the proliferation of HPFs was successfully synthesized,and its cytotoxicity was significantly reduced compared to the original drugs.It has good bio-compatibility and anti-inflammatory effects,providing a new treatment approach for reducing the recurrence rate after pte-rygium surgery.