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.

In the field of dental aesthetics,digital aesthetic design plays a crucial role in helping dentists to predict treatment outcomes vis-ually,as well as in enhancing the consistency of knowledge and understanding of aesthetic goals between dentists and patients.It serves as the foundation for achieving ideal aesthetic effects.However,there is no clear standard for this digital process currently in China and abroad.Many dentists lack of systematic understanding of how to carry out digital aesthetic design for treatment.To establish standardized processes for dental aesthetic design and to improve the homogeneity of treatment outcomes,Chinese Society of Digital Dental Industry(CSD-DI)convened domestic experts in related field to compile this consensus.This article elaborates on the key aspects of digital aesthetic data collection,integration steps,and the digital aesthetic design process.It also formulates a decision tree for dental aesthetics at macro level and outlines corresponding workflows for various clinical scenarios,serving as a reference for clinicians.

Objective To explore the effect of scutellarin on lipopolysaccharide(LPS)induced neuroinflammation in BV-2 microglia cells.Methods BV-2 microglia were cultured and randomly divided into 6 groups:control group(Ctrl),cyclic GMP-AMP synthetase(cGAS)inhibitor RU320521 group(RU.521 group),LPS group,LPS+RU.521 group,LPS+scutellarin pretreatment group(LPS+S)and LPS+S+RU.521 group.The expressions of cGAS,stimulator of interferon gene(STING),nuclear factor kappa B(NF-κB),phosphorylated NF-κB(p-NF-κB),neuroinflammatory factors PYD domains-containing protein 3(NLRP3)and tumor necrosis factor α(TNF-α)in BV-2 microglia were detected by Western blotting and immunofluorescent double staining(n= 3).Results Western blotting and immunofluorescent double staining showed that compared with the control group,the expression of cGAS,STING,p-NF-κB,NLRP3 and TNF-α in BV-2 microglia increased significantly after LPS induction(P<0.05),while the expression of cGAS,STING,p-NF-κB,NLRP3 and TNF-α in LPS+S group were significantly lower than those in LPS group(P<0.05).Treatment with cGAS pathway inhibitor RU.521 showed similar effects as the pre-treatment group with scutellarin.In addition,the change of NF-κB in each group was not statistically significant(P>0.05).Conclusion Scutellarin inhibits the neuroinflammation mediated by BV-2 microglia cells,which may be related to cGAS-STING signaling pathway.

Objective To study the pharmacokinetic characteristics of the test formulation of compound lidocaine cream and reference formulation of lidocaine and prilocaine cream in Chinese healthy subjects and to evaluate whether there is bioequivalence between the two formulations.Methods A single-center,single-dose,randomized,open-label,two-period,two-sequence,crossover design was used.This study included 40 healthy subjects,and in each period,test formulation or reference formulation 60 g was applied to the skin in front of both thighs(200 cm2 each side,a total of 400 cm2)under fasting conditions,and the drug was left on for at least 5 h after application.The concentrations of lidocaine and prilocaine in plasma were determined using liquid chromatography-tandem mass spectrometry(LC-MS/MS)method.Pharmacokinetic parameters were calculated using WinNonlin 8.0 software to evaluate the bioequivalence of the two formulations.Results After the application of the test formulation compound lidocaine cream and the reference formulation lidocaine and prilocaine cream on both thighs of the subjects,the pharmacokinetic parameters of lidocaine in plasma were as follows:Cmax were(167.27±91.33)and(156.13±66.86)ng·mL-1,AUC0-t were(1 651.78±685.09)and(1 636.69±617.23)ng·mL-1·h,AUC0-∞ were(1 669.85±684.65)and(1 654.37±618.30)ng·mL-1·h,the adjusted geometric mean ratios were 104.49％,101.88％and 101.89％,respectively,with 90％confidence intervals of 98.18％-111.20％,97.80％-106.13％and 97.87％-106.07％,all within the range of 80.00％-125.00％.The pharmacokinetic parameters of prilocaine in plasma were as follows:Cmax were(95.66±48.84)and(87.52±39.16)ng·mL-1,AUC0-t were(790.86±263.99)and(774.14±256.42)ng·mL-1·h,AUC0_m were(807.27±264.67)and(792.84±254.06)ng·mL-1 h,the adjusted geometric mean ratios were 107.34％,103.55％and 102.98％,respectively with 90％confidence intervals of 101.69％-113.31％,99.94％-107.30％and 99.65％-106.43％,all within the range of 80.00％-125.00％.Conclusion The test formulation compound lidocaine cream and the reference formulation lidocaine and prilocaine cream are bioequivalent.

Objective:To investigate the association between hyperuricemia and the risk for stroke occurrence, as well as the mediating effect of hypertension on this association.Methods:In this study, the China Chronic Diseases and Nutrition Surveillance system in 2015 was used as baseline data. We identified hospital admissions for stroke using the electronic homepage of inpatient medical records from 2013-2020, and death data were obtained from the 2015-2020 National Mortality Surveillance System. A retrospective cohort was established after matching and linking the database. The Cox proportional hazard regression model was used to analyze the relationship between hyperuricemia and the risk of stroke and its subtypes. Restricted cubic spline analysis was conducted to examine the dose-response relationship between serum uric acid levels and the risk for stroke. Mediation analysis was performed to investigate the mediating effect of hypertension on the association between hyperuricemia and the risk for stroke and its subtypes. Subgroup analyses were conducted based on gender and age groups.Results:A total of 124 352 study subjects were included, with an accumulative follow-up time of 612 911.36 person-years. During the follow-up period, 4 638 cases of stroke were found, including 3 919 cases of ischemic stroke and 689 cases of hemorrhagic stroke. The incidence density of stroke was 756.72 per 100 000 person-years, 641.37 per 100 000 person-years for ischemic stroke, and 114.60 per 100 000 person-years for hemorrhagic stroke. Multivariable Cox proportional hazards regression models showed that after adjusting for covariates, compared to those without hyperuricemia, individuals with hyperuricemia had a 16% higher risk for stroke [hazard ratio ( HR)=1.16, 95% CI: 1.06-1.27], a 12% higher risk of ischemic stroke ( HR=1.12, 95% CI: 1.01-1.24), and a 39% higher risk of hemorrhagic stroke ( HR=1.39, 95% CI: 1.11-1.75). Mediation analysis showed that hypertension partially mediated the associations between hyperuricemia and the risk for stroke, ischemic stroke, and hemorrhagic stroke, with mediation proportions of 36.07%, 39.98%, and 25.34%, respectively. The mediating effect is pronounced in the male population and individuals below 65. Conclusion:Hyperuricemia is a risk factor for stroke, and hypertension partially mediates the effect of hyperuricemia on stroke.

Objective As primary Sj?gren's syndrome(pSS)primarily affects the salivary glands,saliva can serve as an indicator of the glands'pathophysiology and the disease's status.This study aims to illustrate the salivary proteomic profiles of pSS patients and identify potential candidate biomarkers for diagnosis. Methods The discovery set contained 49 samples(24 from pSS and 25 from age-and gender-matched healthy controls[HCs])and the validation set included 25 samples(12 from pSS and 13 from HCs).Totally 36 pSS patients and 38 HCs were centrally randomized into the discovery set or to the validation set at a 2:1 ratio.Unstimulated whole saliva samples from pSS patients and HCs were analyzed using a data-independent acquisition(DIA)strategy on a 2D LC-HRMS/MS platform to reveal differential proteins.The crucial proteins were verified using DIA analysis and annotated using gene ontology(GO)and International Pharmaceutical Abstracts(IPA)analysis.A prediction model for SS was established using random forests. Results A total of 1,963 proteins were discovered,and 136 proteins exhibited differential representation in pSS patients.The bioinformatic research indicated that these proteins were primarily linked to immunological functions,metabolism,and inflammation.A panel of 19 protein biomarkers was identified by ranking order based on P-value and random forest algorichm,and was validated as the predictive biomarkers exhibiting good performance with area under the curve(AUC)of 0.817 for discovery set and 0.882 for validation set. Conclusions The candidate protein panel discovered may aid in pSS diagnosis.Salivary proteomic analysis is a promising non-invasive method for prognostic evaluation and early and precise treatments for pSS patients.DIA offers the best time efficiency and data dependability and may be a suitable option for future research on the salivary proteome.