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 explore the prognostic value of MUC13 expression in gastric cancer(GC)patients and its impact on the biological behavior of GC cells.Methods:Comprehensive anal-ysis of the expression pattern of MUC genes in GC tissues based on the TCGA database to screen for differentially expressed genes.Spearman correlation analysis determined the correlation of ex-pression between MUC genes in GC tissues.Gene Ontology(GO)functional enrichment analysis and Kyoto Encyclopedia of Genes and Genomes pathway(KEGG)enrichment analysis were used to explore the potential biological functions of MUC genes.Univariate COX regression analysis was performed to explore the relationship between all differentially expressed MUC genes and the prog-nosis of GC patients to screen out MUC genes that were significantly related to the prognosis of GC.Clinical GC tissue samples were used to further verify the expression of MUC13 through im-munofluorescence,and its relationship with the clinicopathological characteristics and prognosis of GC was analyzed.siRNA was used to silence the expression of MUC13 in GC cells,and the effect of MUC13 on cell proliferation,migration and invasion was analyzed through CCK-8,colony forma-tion and Transwell experiments.Results:Among all MUC members,the expression levels of MUC1,MUC2,MUC3A,MUC4,MCU5B,MUC12,and MUC13 were significantly upregulated in GC tissues(P＜0.05).There are certain interactions between these MUC genes,and they are mainly en-riched in pathways related to digestive system processes,epithelial structure maintenance,apical plasma membrane,saliva secretion,etc.Importantly,upregulation of MUC13 in GC tissues indicates poor patient prognosis(Log-rank P＜0.05).In addition,MUC13 expression was significantly correlat-ed with the age(P＜0.001)of GC patients and tumor size(P=0.035).Further cell function experiments showed that after silencing MUC13,the proliferation ability of GC cells was significantly reduced(P＜0.05),while their migration and invasion abilities were not significantly affected(P＞0.05).Con-clusions:Highly expressed MUC13 is closely related to the poor prognosis of gastric cancer,par-ticipates in the regulation of tumor progression and is a potential therapeutic target and prognostic marker for gastric cancer.

In this study, fluvoxamine maleate sustained-release pellet system tablets were prepared and were used to evaluate their release behaviors in vitro. Fluvoxamine maleate pellets were prepared using centrifugal-spherization method and coated by fluidized bed as bottom-spray. The multi-unit sustained-release pellets and appropriate excipients for prescription volumes were mixed uniformly and then compressed to tablets. Screening and determining the optimal formulation of drug loaded pellets through L8 (2⁴) Taguchi experiment. Using Minitab software to design a DOE experiment with 2⁴ partial factors, including material temperature, fan speed, atomization pressure, and spray rate to optimize the bottom spray coating process. Taking monostearate glycerol ester with a particle size of 24-40 mesh as the main diluent for tableting to relieve the delamination phenomenon between pellets and excipients during tablet pressing and reduce mechanical damage to the coating film. By examining the powder fluidity indexes such as angle of repose, bulk density, tapped density, and Hausner ratio of mixed particles, it was found that the flowability and compressibility are good and suitable for direct compression. Evaluate the basic properties of the sustained-release tablets, investigate the in vitro release behavior and study the release mechanism. The results of in vitro release test showed that the self-made sustained-release tablets could disintegrate into independent pellet units in phosphate buffer at pH 6.8 and release slowly within 24 h, which conformed to the first-order drug release model. The fluvoxamine maleate sustained-release pellet system tablets meet the requirements of preparation design and has a great commercial prospect.

Objective To summarize the epidemiological and clinical features of infectious diseases of the central nervous system(CNS)by a single-center analysis.Methods A retrospective analysis was conducted on the data of 1247 cases of CNS infectious diseases diagnosed and treated in the First Medical Center of PLA General Hospital from 2001 to 2020.Results The data for this group of CNS infectious diseases by disease type in descending order of number of cases were viruses 743(59.6％),Mycobacterium tuberculosis 249(20.0％),other bacteria 150(12.0％),fungi 68(5.5％),parasites 18(1.4％),Treponema pallidum 18(1.4％)and rickettsia 1(0.1％).The number of cases increased by 177 cases(33.1％)in the latter 10 years compared to the previous 10 years(P<0.05).No significant difference in seasonal distribution pattern of data between disease types(P>0.05).Male to female ratio is 1.87︰1,mostly under 60 years of age.Viruses are more likely to infect students,most often at university/college level and above,farmers are overrepresented among bacteria and Mycobacterium tuberculosis,and more infections of Treponema pallidum in workers.CNS infectious diseases are characterized by fever,headache and signs of meningeal irritation,with the adductor nerve being the more commonly involved cranial nerve.Matagenomic next-generation sequencing improves clinical diagnostic capabilities.The median hospital days for CNS infectious diseases are 18.00(11.00,27.00)and median hospital costs are ￥29,500(￥16,000,￥59,200).The mortality rate from CNS infectious diseases is 1.6％.Conclusions The incidence of CNS infectious diseases is increasing last ten years,with complex clinical presentation,severe symptoms and poor prognosis.Early and accurate diagnosis and standardized clinical treatment can significantly reduce the morbidity and mortality rate and ease the burden of disease.

Objective To discuss the application of the"rotating guidewire and correcting the filter recovery hook direction technique"("rotation-correction loop technique"for short),a technique invented by the authors in clinical practice,in the retrieval of complex inferior vena cava filter(IVCF),and to discuss its technical skills and advantages.Methods The clinical data of 417 patients carrying an IVCF,who were admitted to the Department of Vascular Surgery of Second Hospital of Shanxi Medical University of China to retrieve IVCF between January 2022 and December 2022,were retrospectively analyzed.Taking the time spent on the retrieval of IVCF and the intraoperative radiation dose as the evaluation indicators,the advantages and disadvantages of the standard filter retrieval technique,the"rotation-correction loop technique"and the other loop-assisted techniques were compared.Results Both the intraoperative radiation dose and the time spent on the retrieval of IVCF using"rotation-correction loop technique"were remarkably lower than those of other loop-assisted techniques(P＜0.000 1).Conclusion For the retrieval of complex IVCF,especially for the IVCF which is heavily tilted and/or its recovered hook is attached to the vascular wall,the use of"rotation-correction loop technique"can shorten the time spent on the the retrieval of IVCF and reduce the intraoperative radiation dose.This technique carries high safety and practicability,the device is simple and it can be manipulated by single physician,which is conducive to clinical application and promotion.(J Intervent Radiol,2024,33:289-294)

BACKGROUND:With the increase of patients with cubital tunnel syndrome,ulnar groove plasty does not affect the normal anatomical structure and distribution of the ulnar nerve,which is one of the main surgical procedures for the treatment of cubital tunnel syndrome.3D printing combined with ulnar groove plasty can more accurately position the expansion depth and width of the ulnar groove to avoid some surgical complications. OBJECTIVE:To investigate the effect of 3D printing technology combined with ulnar groove plasty on nerve electrophysiology and prognosis in patients with cubital tunnel syndrome. METHODS:A total of 70 patients with moderate and severe cubital tunnel syndrome who were treated in Cangzhou Integrated Traditional Chinese and Western Medicine Hospital from March 2020 to March 2022 were selected as the study subjects.They were divided into two groups,with 35 cases in each group.The control group underwent traditional ulnar groove plasty.The observation group underwent 3D printing technology combined with ulnar groove plasty.The patients were followed up for 3 months.The clinical efficacy,latency,amplitude of compound muscle action potential of abductor pollicis brevis of the affected limb and ulnar nerve motor conduction velocity,grip strength on the affected side,pinch strength of the middle and thumb fingers,S-W monofilament of the little finger,two-point discrimination of the little finger,and Disabilities of the Arm,Shoulder and Hand Questionnaire score were compared between the two groups. RESULTS AND CONCLUSION:(1)Compared with the control group(74%),the excellent and good rate was significantly higher in the observation group(91%)(P<0.05).(2)Compared with pre-treatment,the latency of compound muscle action potential of abductor pollicis brevis of affected limb was significantly shorter and the wave amplitude and ulnar nerve motor conduction velocity were significantly higher in the two groups after treatment.The latency was significantly shorter and the wave amplitude and ulnar nerve motor conduction velocity were significantly higher in the observation group than those in the control group(P<0.05).(3)Compared with pre-treatment,the grip strength,middle finger and thumb pinch strength of the affected side,S-W monofilament of the little finger and two-point discrimination of the little finger were significantly decreased in the two groups after treatment.The grip strength,middle finger and thumb pinch strength on the affected side were greater,S-W monofilament of the little finger and two-point discrimination of the little finger were significantly smaller in the observation group than those in the control group(P<0.05).(4)Compared with pre-treatment,the Disabilities of the Arm,Shoulder and Hand Questionnaire scores of the two groups were significantly reduced after treatment,and the Disabilities of the Arm,Shoulder and Hand Questionnaire scores of the observation group were significantly lower than those of the control group(P<0.05).(5)It is concluded that 3D printing technology combined with ulnar groove plasty in the treatment of cubital tunnel syndrome can effectively improve its clinical efficacy,promote the neurophysiological recovery of patients,and enhance the function of fingers and upper limbs,which has high clinical application value.