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.

Aim To investigate the effect of quercetin on the aging model of bone marrow mesenchymal stem cells established under microgravity. Methods Using 3D gyroscope, a aging model of bone marrow mesenchymal stem cells was constructed, and after receiving quercetin and microgravity treatment, the anti-aging effect of the quercetin was evaluated by detecting related proteins and oxidation indexes. Results Compared to the control group, the expressions of age-related proteins p21, pi6, p53 and RB in the microgravity group significantly increased, while the expressions of cyclin D1 and lamin B1 significantly decreased, with statistical significance (P<0.05). In the microgravity group, mitochondrial membrane potential significantly decreased (P<0.05), ROS accumulation significantly increased (P <0.05), SOD content significantly decreased and MDA content significantly increased (P<0.05). Compared to the microgravity group, the expressions of age-related proteins p21, pi6, p53 and RB in the quercetin group significantly decreased, while the expressions of cyclin D1 and lamin B1 significantly increased, with statistical significance (P<0.05). In the quercetin group, mitochondrial membrane potential significantly increased (P<0.05), ROS accumulation significantly decreased (P<0.05), SOD content significantly increased and MDA content significantly decreased (P<0.05). Conclusions Quercetin can resist oxidation, protect mitochondrial function and normal cell cycle, thus delaying the aging of bone marrow mesenchymal stem cells induced by microgravity.

Cryoablation therapy with explicit anti-tumor mechanisms and histopathological manifestations has a long history.A large number of clinical practice has shown that cryoablation therapy is safe and effective,making it an ideal tumor treatment method in theory.Previously,its efficacy and clinical application were constrained by the limitations of refrigerants and refrigeration equipment.With the development of the new generation of cryoablation equipment represented by argon helium knives,significant progress has been made in refrigeration efficien-cy,ablation range,and precise temperature measurement,greatly promoting the progression of tumor cryoablation technology.This consensus systematically summarizes the mechanism of cryoablation technology,indications for oral mucosal melanoma(OMM)cryotherapy,clinical treatment process,adverse reactions and management,cryotherapy combination therapy,etc.,aiming to provide reference for carrying out the standardized cryoablation therapy of OMM.

BACKGROUND:Many clinical research observations have indicated a close association between rheumatoid arthritis and osteoporosis as well as bone mineral density(BMD).However,it remains unclear whether there is a causal genetic relationship between rheumatoid arthritis and the development of osteoporosis and alterations of BMD. OBJECTIVE:To assess the potential causal relationship between rheumatoid arthritis and osteoporosis as well as BMD using a two-sample Mendelian randomization approach,provide meaningful insights from a genetic perspective into the underlying mechanisms and offer a reference for early prevention of osteoporosis and improvement in the progression of the disease. METHODS:We conducted a study using data from publicly available genome-wide association studies databases to identify single nucleotide polymorphisms associated with rheumatoid arthritis as instrumental variables(P＜5×10-8).The main outcomes of the study included osteoporosis and BMD at five different sites,including total body BMD,lumbar spine BMD,femoral neck BMD,heel BMD,and forearm BMD.The inverse variance-weighted method was used as the primary analysis method to evaluate causal effects.Weighted median,simple median,weighted mode and MR-Egger regression were used as supplementary analyses.Causal relationships between rheumatoid arthritis and the risk of osteoporosis and BMD were assessed using odds ratios(OR)and 95%confidence intervals(CI).Heterogeneity was assessed using Cochran's Q test and horizontal pleiotropy was evaluated using MR-Egger intercept tests. RESULTS AND CONCLUSION:The inverse variance-weighted analysis demonstrated a positive association between genetically predicted rheumatoid arthritis and osteoporosis(OR=1.123,95%CI:1.077-1.171;P=4.02×10-8).Heterogeneity test(P=0.388)indicated no significant heterogeneity among the single nucleotide polymorphisms.MR-Egger intercept(P=0.571)tests did not detect horizontal pleiotropy,and sensitivity analysis showed no evidence of bias in the study results.There was no causal relationship between rheumatoid arthritis and BMD at the five different sites.The total body BMD(OR=1.000,95%CI:0.988-1.012;P=0.925),lumbar spine BMD(OR=0.999,95%CI:0.982-1.016;P=0.937),femoral neck BMD(OR=1.001,95%CI:0.986-1.016;P=0.866),heel BMD(OR=0.996,95%CI:0.989-1.004;P=0.419),and forearm BMD(OR=1.063,95%CI:0.970-1.031;P=0.996)indicated no significant association.MR-Egger intercept analysis did not detect potential horizontal pleiotropy(total body BMD:P=0.253;lumbar spine BMD:P=0.638;femoral neck BMD:P=0.553;heel BMD:P=0.444;forearm BMD:P=0.079).Rheumatoid arthritis may contribute to the development of osteoporosis through the interaction between chronic inflammation and bone formation,resorption,and absorption.Additionally,the use of glucocorticoids and the presence of autoantibodies(such as anti-citrullinated protein antibody)in patients with rheumatoid arthritis showed associations with osteoporosis.Future research should focus on monitoring systemic inflammatory markers,standardized use of glucocorticoids,and regular screening for osteoporosis risk in patients with rheumatoid arthritis.

BACKGROUND:Observational studies have suggested that statins may have a protective effect against osteoarthritis,including knee osteoarthritis and hip osteoarthritis.However,the association between statins and the risk of osteoarthritis remains unclear. OBJECTIVE:To investigate the association between statins and the risk of osteoarthritis through Mendelian randomization analysis using summary data from large-scale population-based genome-wide association studies(GWAS). METHODS:Firstly,single nucleotide polymorphism data related to statins were obtained from the latest 9th edition of the FinnGen database,while data of osteoarthritis,knee osteoarthritis and hip osteoarthritis were obtained from the IEU Open GWAS,UK Biobank,and ArcOGEN(Genetics of Osteoarthritis)databases,respectively.The inverse variance weighted method was used as the primary analysis approach to evaluate the causal effects.The weighted median method,simple median method,weighted mode-based method,and MR-Egger regression were used as supplementary analyses.The causal relationship between statins and the risk of osteoarthritis,knee osteoarthritis and hip osteoarthritis was assessed using odds ratios(OR)with 95%confidence intervals(CI).Sensitivity analyses were conducted to validate the reliability of the results,including the Cochran's Q test for heterogeneity and the MR-Egger-intercept test for horizontal pleiotropy,as well as leave-one-out analysis to identify potentially influential single nucleotide polymorphisms. RESULTS AND CONCLUSION:The inverse variance weighted analysis demonstrated a negative causal relationship between genetically predicted statins and the risk of osteoarthritis(OR=0.998,95%CI:0.996-0.999,P=0.01),knee osteoarthritis(OR=0.964,95%CI:0.940-0.989,P=0.005),and hip osteoarthritis(OR=0.928,95%CI:0.901-0.955,P=4.28×10-7).MR-Egger intercept analysis did not detect potential horizontal pleiotropy(osteoarthritis:P=0.658;knee osteoarthritis:P=0.600;hip osteoarthritis:P=0.141).The results of this study provide evidence that statins reduce the risks of osteoarthritis,knee osteoarthritis and hip osteoarthritis as described in observational studies.Further research is needed to explore the specific mechanisms of statin treatment for osteoarthritis.

R-spondin2 (Rspo2) is a member of protein family RSPOs, which can be coupled to receptor 4/5 (leucine-rich repeat-containing g protein-coupled receptor 4/5, LGR4/5), cell surface transmembrane E3 ubiquitin ligase ZNRF3/RNF43 (zinc and ring finger 3/ring finger protein 43), heparan sulfate proteoglycan (heparan sulfate proteoglycans, HSPGs) and the IQ motif (IQ gap 1) containing GTP enzyme activating protein 1, regulating the Wnt/β-catenin signaling pathway, which is the most widely studied signaling pathway and directly related to basic bone biology. Any problem in this pathway may have an impact on bone regulation. In recent years, it has been found that Rspo2 can act on osteoblast, osteoclast and chondrocytes through Wnt/β-catenin, and take part in occureace and development of some bone diseases such as ossification of the posterior longitudinal ligament (OPLL), osteoarthritis (OA) and rheumatoid arthritis (RA), so the study of Rspo2 may become a new therapeutic direction for bone-related diseases. Based on the latest research progress, this paper reviews the structure and main functions of Rspo2, the mechanism of Rspo2 regulating Wnt/β-catenin signaling pathway and its influence on skeletal system, in order to provide new ideas and ways for the prevention and treatment of bone-related diseases.