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.

Objective To clarify the risk factors of diaphragmatic dysfunction (DD) after cardiac surgery with extracorporeal circulation. Methods A retrospective analysis was conducted on the data of patients who underwent cardiac surgery with extracorporeal circulation in the Department of Cardiovascular Surgery of Peking University People's Hospital from January 2023 to March 2024. Patients were divided into two groups according to the results of bedside diaphragm ultrasound: a DD group and a control group. The preoperative, intraoperative, and postoperative indicators of the patients were compared and analyzed, and independent risk factors for DD were screened using multivariate logistic regression analysis. Results A total of 281 patients were included, with 32 patients in the DD group, including 23 males and 9 females, with an average age of (64.0±13.5) years. There were 249 patients in the control group, including 189 males and 60 females, with an average age of (58.0±11.2) years. The body mass index of the DD group was lower than that of the control group [(18.4±1.5) kg/m2 vs. (21.9±1.8) kg/m2, P=0.004], and the prevalence of hypertension, chronic obstructive pulmonary disease, heart failure, and renal insufficiency was higher in the DD group (P<0.05). There was no statistical difference in intraoperative indicators (operation method, extracorporeal circulation time, aortic clamping time, and intraoperative nasopharyngeal temperature) between the two groups (P>0.05). In terms of postoperative aspects, the peak postoperative blood glucose in the DD group was significantly higher than that in the control group (P=0.001), and the proportion of patients requiring continuous renal replacement therapy was significantly higher than that in the control group (P=0.001). The postoperative reintubation rate, tracheotomy rate, mechanical ventilation time, and intensive care unit stay time in the DD group were higher or longer than those in the control group (P<0.05). Multivariate logistic regression analysis showed that low body mass index [OR=0.72, 95%CI (0.41, 0.88), P=0.011], preoperative dialysis [OR=2.51, 95%CI (1.89, 4.14), P=0.027], low left ventricular ejection fraction [OR=0.88, 95%CI (0.71, 0.93), P=0.046], and postoperative hyperglycemia [OR=3.27, 95%CI (2.58, 5.32), P=0.009] were independent risk factors for DD. Conclusion The incidence of DD is relatively high after cardiac surgery, and low body mass index, preoperative renal insufficiency requiring dialysis, low left ventricular ejection fraction, and postoperative hyperglycemia are risk factors for DD.

ObjectiveTo explore the mechanism of Bushen Huoxue enema in treating the rat model of kidney deficiency and blood stasis-thin endometrium （KDBS-TE） by transcriptome sequencing. MethodThe rat model of KDBS-TE was established by administration of tripterygium polyglycosides tablets combined with subcutaneous injection of adrenaline. The pathological changes of rat endometrium in each group were then observed. Three uterine tissue specimens from each of the blank group， model group， and Bushen Huoxue enema group were randomly selected for transcriptome sequencing. The differentially expressed circRNAs， lncRNAs， and miRNAs were screened， and the disease-related specific competitive endogenous RNA （ceRNA） regulatory network was constructed. Furthermore， the gene ontology （GO） functional annotation and the Kyoto Encyclopedia of Genes and Genomes （KEGG） pathway enrichment were performed for the mRNAs in the network. ResultCompared with the blank group， the model group showed endometrial dysplasia， decreased endometrial thickness and endometrial/total uterine wall thickness ratio （P<0.01）， and differential expression of 18 circRNAs， 410 lncRNAs， and 7 miRNAs. Compared with the model group， the enema and estradiol valerate groups showed improved endometrial morphology and increased endometrial thickness and ratio of endometrial to total uterine wall thickness （P<0.05）. In addition， 21 circRNAs， 518 lncRNAs， and 17 miRNAs were differentially expressed in the enema group. The disease-related specific circRNA-miRNA-mRNA regulatory network composed of 629 nodes and 664 edges contained 2 circRNAs， 34 miRNAs， and 593 mRNAs. The lncRNA-miRNA-mRNA regulatory network composed of 180 nodes and 212 edges contained 5 lncRNAs， 10 miRNAs， and 164 mRNAs. The mNRAs were mainly enriched in Hippo signaling pathway， autophagy-animal， axon guidance， etc. ConclusionBushen Huoxue enema can treat KDBS-TE in rats by regulating specific circRNAs， lncRNAs， and miRNAs in the uterus and the ceRNA network.

AIM: To investigate the efficacy of lacrimal duct laser dacryoplasty combined with intubation and postoperative meibomian gland treatment in patients with chronic dacryocystitis complicated by meibomian gland dysfunction.METHODS: Data were collected from 128 patients with chronic dacryocystitis complicated by meibomian gland dysfunction treated at Xi'an No.1 Hospital from March 2021 to December 2022. All patients underwent lacrimal duct laser dacryoplasty combined with intubation. Postoperatively, those patients were randomly divided into two groups: group A(64 cases, without meibomian gland treatment)and group B(64 cases, with meibomian gland treatment). The lacrimal intubation was removed at 3 mo after surgery to evaluate the patency rate of lacrimal irrigation. Additionally, changes in the ocular surface disease index(OSDI)score, non-invasive tear film break-up time, tear meniscus height, conjunctival hyperemia analysis, meibomian gland analysis, tear lipid layer thickness, tear ferning test, and conjunctival impression cytology were compared between the two groups.RESULTS: The lacrimal irrigation patency rates in the group A and group B were 78.1% and 81.2% respectively, with no statistically significant difference between the two groups(P>0.05); compared with the group A, group B showed a significant extension in non-invasive tear breakup time at 3 mo after surgery, and the OSDI score, conjunctival hyperemia analysis, tear ferning test and conjunctival impression cytology grading were all significantly decreased(all P<0.05), while there was no significant difference in tear meniscus height, tear lipid layer thickness and meibomian gland loss score between the two groups(all P>0.05).CONCLUSION: Comprehensive treatment for patients with chronic dacryocystitis combined with meibomian gland dysfunction have improved patients' comfort, tear film stability, and reduces local inflammatory response. It is important to simultaneously address ocular surface microenvironment abnormalities during surgical treatment to achieve satisfactory efficacy.

ObjectiveTo study the bioactive secondary metabolites of Talaromyces sp. TP21 and their bioactivities. MethodThe secondary metabolites of Talaromyces sp. TP21 were isolated by high performance liquid chromatography （HPLC）， normal phase and reversed phase column chromatography combined with molecular networking and bioassay-guided fractionation， and their structures were determined by nuclear magnetic resonance （NMR） and high resolution mass spectrometry （HR MS）. The inhibitory effects of the compounds on the growth of the lung cancer cell line A549 and the liver cancer cell line Hep G2 were measured by themethyl thiazolyl tetrazolium （MTT） method. The antimicrobial activities of the compounds were measured with Staphylococcus aureus and human oral cavity-derived Saccharomyces cerevisiae as the indicator microorganisms. ResultSeventeen compounds were isolated from the secondary metabolites of Talaromyces sp. TP21 and identified as ergochrome C （1）， daldiniaeschsone A （2）， seco-blennolide B （3）， penitholabene （4）， penicichrysogene A （5）， orsellinic acid （6）， griseofulvin （7）， isorhodoptilometrin （8）， （+）-5-chloromitorubrinic acid （9）， penicillixanthone A （10）， pentacecilide B （11）， pentacecilide C （12）， chrodrimanin C （13）， chrodrimanin E （14）， chrodrimanin H （15）， chrodrimanin F （16）， and 3-hydroxypentacecilide A （17）. ConclusionCompounds 1-5， 11-12， and 17 were isolated from Talaromyces for the first time. Among them， compounds 4， 7， and 10-12 exhibited inhibitory activities against the growth of A549 and Hep G2 cells， with the median inhibitory concentration below 50 μmol·L^-1. Furthermore， compounds 9 and 10 showed inhibitory activities against S. aureus and human oral cavity-derived S. cerevisiae， with the minimum inhibitory concentration of 8-128 mg·L^-1.

Pulmonary fibrosis is a chronic and progressive lung disease that poses a threat to human health. Current treatment options are limited, highlighting the urgent need for more effective therapeutic strategies. Tetrandrine (TET), a bis-benzylisoquinoline alkaloid extracted from Stephania tetrandra, has been known for its anti-inflammatory and anti-fibrotic effects, but its specific mechanisms remain unclear. This study investigated the anti-fibrotic effects of TET in a chronic model of pulmonary fibrosis, aiming to delineate the molecular mechanisms underlying TET-mediated inhibition of fibroblast activation. The results showed that TET significantly alleviated the pathological changes in a murine model of multiple bleomycin-induced pulmonary fibrosis and effectively inhibited TGF-β1-induced fibroblast activation. Mechanistically, TET predominantly inhibited the TGF-β/SMAD signaling pathway and diminished intracellular reactive oxygen species (ROS) levels. Utilizing CRISPR-Cas9 library screening, we identified that angiotensin II type 1 receptor associated protein (AGTRAP) and membrane palmitoylated protein 6 (MPP6) played important roles in TET's suppressive impact of ROS levels, with the knockout of two genes attenuating TET's antifibrotic activity. All animal treatment procedures were approved according to the Committee on the Ethics of Animal Experiments of the Institute of Medicinal Biotechnology, Chinese Academy of Medical Sciences (IMB-20230406D507). This research not only elucidates the pharmacological mechanism of TET but also provides a novel therapeutic avenue for the treatment of pulmonary fibrosis.