Objective To compare the performance and efficacy of prognostic models constructed by different machine learning algorithms in predicting the survival period of lung transplantation (LTx) recipients. Methods Data from 483 recipients who underwent LTx were retrospectively collected. All recipients were divided into a training set and a validation set at a ratio of 7:3. The 24 collected variables were screened based on variable importance (VIMP). Prognostic models were constructed using random survival forest (RSF) and extreme gradient boosting tree (XGBoost). The performance of the models was evaluated using the integrated area under the curve (iAUC) and time-dependent area under the curve (tAUC). Results There were no significant statistical differences in the variables between the training set and the validation set. The top 15 variables ranked by VIMP were used for modeling and the length of stay in the intensive care unit (ICU) was determined as the most important factor. Compared with the XGBoost model, the RSF model demonstrated better performance in predicting the survival period of recipients (iAUC 0.773 vs. 0.723). The RSF model also showed better performance in predicting the 6-month survival period (tAUC _{6 months} 0.884 vs. 0.809, P = 0.009) and 1-year survival period (tAUC _{1 year} 0.896 vs. 0.825, P = 0.013) of recipients. Based on the prediction cut-off values of the two algorithms, LTx recipients were divided into high-risk and low-risk groups. The survival analysis results of both models showed that the survival rate of recipients in the high-risk group was significantly lower than that in the low-risk group (P<0.001). Conclusions Compared with XGBoost, the machine learning prognostic model developed based on the RSF algorithm may preferably predict the survival period of LTx recipients.

ObjectiveTo observe the clinical effectiveness and safety of Xiaozhong Zhitong Mixture （消肿止痛合剂） combined with antibiotic bone cement in the treatment of diabetic foot ulcer （DFU） with damp-heat obstructing syndrome. MethodsA total of 72 DFU patients with damp-heat obstructing syndrome were randomly assigned to treatment group （36 cases） and the control group （36 cases）. Both groups received standard treatment and topical antibiotic bone cement for ulcer wounds， while the treatment group received oral Xiaozhong Zhitong Mixture （50 ml per time， three times daily） in additionally. Both groups underwent daily wound dressing changes for 21 consecutive days. Ulcer healing rate， serum levels of tumor necrosis factor-alpha （TNF-α）， interleukin-1 beta （IL-1β）， malondialdehyde （MDA）， superoxide dismutase （SOD）， C-reactive protein （CRP）， and white blood cell （WBC） count were observed before and after treatment， and visual analog scale （VAS） scores for wound pain， traditional Chinese medicine （TCM） syndrome scores， and the DFU Healing Scale （DMIST scale） were also compared. Liver and kidney function were evaluated before and after treatment， and adverse events such as allergic reactions， worsening ulcer pain were recorded. ResultsTotally 35 patients in the treatment group and 33 in the control group were included in the final analysis. The ulcer healing rate in the treatment group was （87.93±9.34）%， significantly higher than （81.82±12.02）% in the control group （P = 0.035）. Compared to pre-treatment levels， both groups showed significant reductions in serum CRP， WBC， MDA， IL-1β， and TNF-α levels， with an increase in SOD level （P＜0.05）. TCM syndrome scores， VAS， and DMIST scores also significantly decreased in both groups （P＜0.05）， with greater improvements in the treatment group （P＜0.05）. No significant adverse reactions were observed in either group during treatment. ConclusionXiaozhong Zhitong Mixture combined with antibiotic bone cement has significant advantages in promoting DFU healing， reducing inflammatory response， and alleviating oxidative stress in DFU patients with damp-heat obstructing syndrome， with good safety for DFU patients with damp-heat obstructing syndrome.

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.

Objective To observe the application effect of montelukast sodium combined with terbutaline on cough variant asthma(CVA)in children and its influence on airway remodeling and peripheral blood inflammatory indicators.Methods The children with CVA were randomly classified into control group and treatment group.The control group was given aerosol inhalation of terbutaline(5 mg each time,twice a day),and on the basis of the control group,the treatment group was combined with oral administration of montelukast sodium granules(4 mg each time,once a day,taking before going to bed),and both groups were continuously treated for 3 months.The clinical efficacy,airway cross-section area(AO),airway lumen area(AI),airway wall thickness(T),airway wall area(WA),serum interleukin-5(IL-5),eosinophilic chemotactic factor(Eotaxin),macrophage inflammatory protein-1α(MIP-1α)and T lymphocyte subgroups CD4+,CD8+and CD4+/CD8+were compared between the two groups of children,and the medication safety was assessed.Results Fifty-three cases in control group and 53 cases in treatment group were included.After treatment,the total effective rates in treatment group and control group were 96.23％(51 cases/53 cases)and 83.02％(44 cases/53 cases),respectively(P＜0.05).The AO values in treatment group and control group were(39.42±3.67)and(45.69±4.92)mm2;AI values were(22.36±2.85)and(27.06±3.18)mm2;T values were(1.12±0.28)and(1.44±0.33)mm;WA values were(53.82±4.17)and(60.13±4.66)mm2;serum IL-5 levels were(25.46±5.83)and(41.46±7.64)ng·L-1;Eotaxin levels were(181.24±30.05)and(238.21±39.42)ng·L-1;MIP-1a levels were(15.24±3.67)and(22.43±4.05)ng·L-1;CD4+levels were(37.18±4.06)％and(33.57±3.82)％;CD8+levels were(24.08±3.15)％and(27.31±3.07)％;and CD4+/CD8+levels were 1.54±0.33 and 1.24±0.28,respectively(all P＜0.05).The total incidences of adverse drug reactions in treatment group and control group were 9.43％(5 cases/53 cases)and 3.77％(2 cases/53 cases),respectively(P＞0.05).Conclusion Montelukast sodium combined with terbutaline has an exact efficacy in the treatment of CVA in children,and it can effectively reverse airway remodeling,reduce inflammation level and enhance immune function,and it has good safety.

Objective: To explore the association between parental education level and time spent outdoors among children, so as to provide the scientific evidence for formulating policies of myopia prevention and control among children. Methods: The study was based on secondary analysis of data from outdoor intervention studies in Shanghai. The follow up period was from March to December 2018. It included control group children ( n =1 117) with complete questionnaire surveys, ocular examinations, and time spent outdoors. Generalized linear regression models and trend tests were used to analyze the effect of parental education level on time spent outdoors among children. Results: The median time spent outdoors was 76.4(59.7, 94.6) minutes. After adjusting for covariates including children s sex and age, generalized linear regression model suggested that there was no statistical significance between father s education level and outdoor activity time ( P >0.05). Compared with children whose mothers had a junior high school education or below, children whose mothers had high school/vocational high school education, college or above had shorter time spent outdoors ( β=-6.64, -8.84 , P <0.05). Trend tests revealed that time spent outdoors among children decreased with the increase of parental education level ( P trend <0.01). Conclusions The higher the education level of fathers or mothers, the shorter time spent outdoors of children. In addition to highlight outdoor activities at school, myopia prevention and control efforts should be focused on the role of parents in increasing children s outdoor activities.