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.

Paroxysmal nocturnal hemoglobinuria (PNH) is an acquired clonal hematopoietic stem cell disease caused by abnormal expression of glycosylphosphatidylinositol (GPI) on the cell membrane due to mutations in the phosphatidylinositol glycan class A(PIGA) gene. It is commonly characterized by intravascular hemolysis, repeated thrombosis, and bone marrow failure, as well as multiple systemic involvement symptoms such as renal dysfunction, pulmonary hypertension, swallowing difficulties, chest pain, abdominal pain, and erectile dysfunction. Due to the rarity of PNH and its strong heterogeneity in clinical manifestations, multidisciplinary collaboration is often required for diagnosis and treatment. Peking Union Medical College Hospital, relying on the rare disease diagnosis and treatment platform, has invited multidisciplinary clinical experts to form a unified opinion on the diagnosis and treatment of PNH, and formulated the Expert Consensus of Multidisciplinary Diagnosis and Treatment for Paroxysmal Nocturnal Hemoglobinuria (2024), with the hope of promoting the standardization of PNH diagnosis and treatment.

Following the principles of evidence-based medicine,in accordance with the structure and drafting rules of standardized documents,based on literature research,according to the characteristics of chronic cough in children and issues that need to form a consensus,the TCM Guidelines for Diagnosis and Treatment of Chronic Cough in Children was formulated based on the Delphi method,expert discussion meetings,and public solicitation of opinions.The guideline includes scope of application,terms and definitions,eti-ology and diagnosis,auxiliary examination,treatment,prevention and care.The aim is to clarify the optimal treatment plan of Chinese medicine in the diagnosis and treatment of this disease,and to provide guidance for improving the clinical diagnosis and treatment of chronic cough in children with Chinese medicine.

Objective To develop a method for the determination of ketamine analogues in hair samples by liquid chromatography quadrupole linear ion trap mass spectrometry(QTRAP LC-MS/MS).Methods 20 mg of washed and dried hair was added to 1 mL extracting solution and then prepared using an ultrasonic extraction with frozen pulverization method.After centrifugation and purification with membrane,the supernatant was separated in a ACQUITY UPLC? HSS T3 column with gradient elution,finally tested with multiple reaction monitoring for the detection of 10 ketamine analogues.The above method was applied for quantitative analysis of ethylfluamine,F-norketamine and tiletamine in 20 positive samples.Results When the concentration ranged from 0.01 to 2.00 ng/mg,there was good linearity for 10 ketamine analogues with the correlation coefficients over 0.99.The recoveries ranged from 89.1％to 106.1％,and the matrix effects were between 88.3％and 106.0％.Among the 20 positive samples,the contents of ethylfluamine,F-norketamine and tiletamine in hair ranged between 0.02～8.35 ng/mg,0.01～0.94 ng/mg and 0.02～10.93 ng/mg,respectively.Their mean values were 1.59 ng/mg,0.28 ng/mg and 2.69 ng/mg.Their medians were 0.40 ng/mg,0.19 ng/mg and 2.11 ng/mg.Conclusion The established method was simple,efficient,reliable and suitable for the determination of ketamine analogues in hair.The data provided reference for the drug control and forensic science practice.

Objective To plan microwave antenna puncture direction effectively and realize personalized preoperative simulation by exploring microwave ablation(MWV)outcomes of lung cancer based on real anatomical model.Methods Firstly,a personalized MWA simulation model consisting of the lung tissue,tumor and vascular system was constructed based on the lung CT data of real patients.Secondly,the MWA effect was simulated by coupling 2 physical fields including an electromagnetic field and a biological heat transfer field,so as to determine the volume of the ablation thermocoagulation zone and the temperature distribution of the lung tissue.Finally,the effects of the vascularized network on the ablation results were quantitatively evaluated in terms of conductivity and blood perfusion,and the ablation results were analyzed with different distances between the large vessels and the antennae(5 and 10 mm from the antennae tips)and puncture angles(large vessels parallelling or intersecting with the antennae tips).Results The vascularized network reduced the volume of the thermocoagulation zone by 0.5％to 3.7％,and blood perfusion made the ablation temperature and the volume of the thermocoagulation zone decreased significantly.The cooling effect gradually diminished with the increase of the distance between the large vessels and the antenna.With the same treatment parameters,the thermocoagulation zone formed when the large vessels paralleled with the antenna was obviously larger than that when the vessles intersected with the antenna.Conclusion Personalized MWA simulation analysis based on real CT data contributes to clarifying the temperature distribution and damage estimation close to the actual situation,which provides guidance and reference for precise treatment of the lung tumor and determination of microwave antenna puncture direction.[Chinese Medical Equipment Journal,2024,45(9):27-34]

Objective To investigate the impact of spermidine on proliferation and apoptosis of diffuse large B-cell lymphoma(DLBCL)cell lines.Methods The impact of spermidine on cellular growth was assessed using a CCK-8 assay.Flow cytometry was employed to investigate the effects of spermidine on the proliferation and cell cycle dynamics of DLBCL cell lines,as well as to evaluate its influence on apoptosis in DLBCL cell lines,mouse splenocytes,and peripheral blood mononuclear cells(PBMCs)derived from healthy individuals.Western blot analysis was conducted to examine alterations in protein expression levels associated with apoptosis and the cell cycle following treatment with spermidine.Results The CCK-8 assay revealed a significant inhibitory effect of spermidine on DLBCL cell growth(P<0.001).Flow cytometric analysis demonstrated that spermidine had no impact on the proliferation or cell cycle of DLBCL cells,but significantly induced apoptosis(P<0.001).Spermidine exhibited a pro-apoptotic effect on mouse splenocytes(P<0.01),albeit weaker compared to its effect on DLBCL cells(P<0.001),and showed no significant pro-apoptotic effect on PBMCs.Western blot results indicated that spermidine did not influence the expression levels of cell cycle proteins CDK2 and CDK4,but enhanced the activation of Caspase-9 in A20 cells and Caspase-8 in OCI-Ly3 cells.Conclusion Spermidine induces apoptosis and suppresses cell growth in DLBCL cell lines,while exhibiting diminished or absent pro-apoptotic effects on mouse splenocytes and healthy human PBMCs,suggesting its potential as a specific inhibitor for the growth of DLBCL cell lines in vivo.