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 investigate the factors influencing international normalized ratio (INR)>3.0 in patients undergoing warfarin anticoagulation therapy after mechanical heart valve replacement. Methods A retrospective analysis was performed on the clinical data of patients who underwent mechanical heart valve replacement surgery and received warfarin anticoagulation therapy at West China Hospital of Sichuan University from January 1, 2011 to June 30, 2022. Based on the discharge INR values, patients were divided into two groups: an INR≤3.0 group and an INR>3.0 group. The factors associated with INR>3.0 at the time of discharge were analyzed. Results A total of 8901 patients were enrolled, including 3409 males and 5492 females, with a median age of 49.3 (43.5, 55.6) years. The gender, body mass index (BMI), New York Heart Association (NYHA) cardiac function grading, INR, glutamic oxaloacetic transaminase, and preoperative prothrombin time (PT) were statistically different between the two groups (P<0.05). Multivariate logistic regression analysis revealed that lower BMI, preoperative PT>15 s, and mitral valve replacement were independent risk factors for INR>3.0 at discharge (P<0.05). Conclusion BMI, preoperative PT, and surgical site are factors influencing INR>3.0 at discharge in patients undergoing warfarin anticoagulation therapy after mechanical heart valve replacement. Special attention should be given to patients with lower BMI, longer preoperative PT, and mitral valve replacement to avoid excessive anticoagulation therapy.

Aim To explore the improvement effect of Bazi Bushen capsule on thymic degeneration in SAMP6 mice and the possible mechanism.Methods Twenty 12 week old male SAMP6 mice were randomly divided into the model group(SAMP6)and the Bazi Busheng capsule treatment group(SAMP6+BZBS).Ten SAMR1 mice were assigned to a homologous control group(SAMR1).The SAMP6+BZBS group was oral-ly administered Bazi Bushen capsule suspension(2.8 g·kg-1)daily,while the other two groups were orally administered an equal amount of distilled water.After nine weeks of administration,the morphology of the thymus in each group was observed and the thymus in-dex was calculated;HE staining was used to observe the structural changes of thymus tissue;SA-β-gal stai-ning was used to detect thymic aging;flow cytometry was used to detect the proportion of thymic CD3+T cells in each group;Western blot was used to detect the levels of p16,Bax,Bcl-2,and cleaved caspase-3 proteins in thymus;immunofluorescence was applied to detect the proportion of cortical thymic epithelial cells in each group;ELISA was employed to detect IL-7 lev-els in thymus.Results Compared with the SAMP6 group,the thymic index of the SAMP6+BZBS group significantly increased(P＜0.05);the disordered thy-mic structure was significantly improved;the positive proportion of SA-β-gal staining significantly decreased(P＜0.01);the proportion of CD3+T cells apparently increased(P＜0.05);the level of p16 protein signifi-cantly decreased(P＜0.05);the level of Bcl-2 pro-tein significantly increased(P＜0.05),while the lev-el of cleaved caspase-3 protein markedly decreased(P＜0.05);the proportion of cortical thymic epithelial cells evidently increased;the level of IL-7 significantly increased(P＜0.01).Conclusions Bazi Bushen capsule can delay thymic degeneration,inhibit cell ap-optosis in thymus and promote thymic cell development in SAMP6 mice,which may be related to increasing the proportion of cortical thymic epithelial cells and promoting IL-7 secretion.

Objective To investigate the efficacy and safety of a new type of self-made bone drill applied to percutaneous transforaminal endoscopic discectomy for L5/S1 intervertebral disc herniation.Methods The clinical data of 52 patients with L5/S1 intervertebral disc herniation admitted to our hospital were retrospectively analyzed.All patients underwent percutaneous transforaminal endoscopic discectomy,with a new type of self-made bone drill for foraminoplasty during the surgery.The surgical conditions and occurrence of complications were recorded.The pain of patients before surgery,3 days after surgery,3 months after surgery,6 months after surgery,and 1 year after surgery was assessed by visual analogue scale(VAS);and the neurological function improvement before and after surgery was evaluated by Oswestry disability index(ODI).Results All patients underwent successful surgery without serious complications or recurrence after surgery.The VAS and ODI scores of patients 3 days,3 months,6 months,and 1 year after surgery were significantly lower than those before surgery(P<0.05).Conclusion The self-made new bone drill can significantly improve the efficiency of foraminoplasty and ensure surgical safety,with satisfactory early clinical effect.

Objective To explore the clinical efficacies of different surgical methods for elderly patients with lumbar tuberculosis.Methods The clinical data of 289 elderly patients with lumbar tuberculosis admitted to Hebei Chest Hospital from August 2018 to August 2021 were retrospectively analyzed.According to surgical methods,the patients were divided into the posterior group(109 cases),the anterior and posterior combination group(81 cases),and the anterior group(99 cases).The time of bone graft and fusion,operation time,hospital stay,intraoperative blood loss,and complications of the three groups were collected and compared among the three groups.The spine Cobb angle was regularly determined,the correction degree was calculated;the levels of erythrocyte sedimentation rate(ESR),white blood cell count(WBC),and C-reactive protein(CRP)were collected and compared among the three groups;and the Frankel grading and visual analogue scale(VAS)scores of the three groups were compared.Results After a 2-year follow-up,there was no significant difference in the time of bone graft and fusion among the three groups(P>0.05),the anterior group had the shortest operation time,the posterior group had the shortest hospital stay,and the lowest intraoperative blood loss and incidence of complications,with statistically significant differences(P<0.05).The correction degree of the anterior and posterior combination group was better than that of the posterior group and the anterior group(P<0.05),and the Cobb angles after operation and at the last follow-up in the posterior group was better(P<0.05).The anterior and posterior combination group had better improvement effect on CRP and ESR at the last follow-up(P<0.05),the WBC level of the posterior group was lower(P<0.05).The proportions of patients in grade E of Frankel grading at the last follow-up in the three groups were higher than those after surgery(P<0.05);compared with the preoperative period,the VAS scores at the last follow-up of the three groups decreased(P<0.05),and the VAS score of the posterior group was lower(P<0.05).Conclusion The effects of anterior surgery,posterior surgery and anterior and posterior combined surgery in the treatment of elderly lumbar tuberculosis are good,and the approach method can be scientifically and reasonably formulated according to patients' physical condition to improve the clinical treatment effect.

Objective:We aimed to develop a novel visualized model based on nomogram to predict postoperative overall survival.Methods:This was a multicenter, retrospective, observational cohort study, including participants with histologically confirmed gastric and colorectal cancer who underwent radical surgery from 11 medical centers in China from August 1, 2015 to June 30, 2018. Baseline characteristics, histopathological data and nutritional status, as assessed using Nutrition Risk Screening 2002 (NRS 2002) score and the scored Patient-Generated Subjective Global Assessment, were collected. The least absolute shrinkage and selection operator regression and Cox regression were used to identify variables to be included in the predictive model. Internal and external validations were performed.Results:There were 681 and 127 patients in the training and validation cohorts, respectively. A total of 188 deaths were observed over a median follow-up period of 59 (range: 58 to 60) months. Two independent predictors of NRS 2002 and Tumor-Node-Metastasis (TNM) stage were identified and incorporated into the prediction nomogram model together with the factor of age. The model's concordance index for 1-, 3- and 5-year overall survival was 0.696, 0.724, and 0.738 in the training cohort and 0.801, 0.812, and 0.793 in the validation cohort, respectively.Conclusions:In this study, a new nomogram prediction model based on NRS 2002 score was developed and validated for predicting the overall postoperative survival of patients with gastric colorectal cancer. This model has good differentiation, calibration and clinical practicability in predicting the long-term survival rate of patients with gastrointestinal cancer after radical surgery.