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.

Persistent left superior vena cava(PLSVC)is a common congenital anomaly of systemic venous drainage,often draining into the right atrium without the need for special treatment.Sometimes,PLSVC drains into the left atrium,creating a right-to-left shunt,leading to reduced blood oxygen saturation and paradoxical embolism,requiring intervention.Traditional surgical ligation of PLSVC is the conventional approach for managing abnormal shunting,but it is associated with significant trauma and carries the risk of damaging the phrenic nerve.Here,we present a case of a patient with right heart dysfunction due to an untreated PLSVC-left atrium communication after corrective surgery for complex congenital heart disease,resulting in left-to-right shunting postoperatively.The patient was successfully treated by using a Plug vascular occluder via a transseptal approach to occlude the PLSVC.To our knowledge,this is the first report of successful closure of the left-to-right shunting through the heart chambers via a transseptal approach,indicating that interventional occlusion is an ideal management approach.

Low-level patent foramen ovale nonocclusion(PFO)is a rare type of PFO in which the PFO opening is low during transcatheter closure of PFO and the distance between the PFO left atrial opening and the root of the septal side of the mitral valve is less than 9 mm,and the smallest model of the current double-disk PFO occluder(18/18)commonly used in clinical practice for low-level PFOs can touch the mitral valve,resulting in increased risk of mitral regurgitation or leaflet abrasion.The risk of mitral regurgitation or leaflet abrasion is increased,and transcatheter closure of PFO procedure can only be abandoned when encountered intraoperatively.In this article,we present a case of successful transcatheter closure of a low-level PFO using the Amplatzer ADOⅡ occluder,which provides new ideas and strategies to deel wtih this rare type of PFO.

Objective To monitor the antifungal resistance of clinical isolates of Candida spp.in the East China region.Methods MALDI-TOF MS or molecular methods were used to re-identify the strains collected from January 2018 to December 2022.Antifungal susceptibility testing was performed using the broth microdilution method.The susceptibility test results were interpreted according to the breakpoints of 2022 Clinical and Laboratory Standards Institute(CLSI)documents M27 M44s-Ed3 and M57s-Ed4.Results A total of 3 026 strains of Candida were collected,65.33％of which were isolated from sterile body sites,mainly from blood(38.86％)and pleural effusion/ascites(10.21％).The predominant species of Candida were Candida albicans(44.51％),followed by Candida parapsilosis complex(19.46％),Candida tropicalis(13.98％),Candida glabrata(10.34％),and other Candida species(0.79％).Candida albicans showed overall high susceptibility rates to the 10 antifungal drugs tested(the lowest rate being 93.62％).Only 2.97％of the strains showed dose-dependent susceptibility(SDD)to fluconazole.Candida parapsilosis complex had a SDD rate of 2.61％and a resistance rate of 9.42％to fluconazole,and susceptibility rates above 90％to other drugs.Candida glabrata had a SDD rate of 92.01％and a resistance rate of 7.99％to fluconazole,resistance rates of 32.27％and 48.24％to posaconazole and voriconazole non-wild-type strains(NWT),respectively,and susceptibility rates above 90％to other drugs.Candida tropicalis had resistance rates of 29.55％and 26.24％to fluconazole and voriconazole,respectively,resistance rates of 76.60％and 21.99％to posaconazole and echinocandins non-wild-type strains(NWT),and a resistance rate of 2.36％to echinocandins.Conclusions The prevalence and species distribution of Candida spp.in the East China region are consistent with previous domestic and international reports.Candida glabrata exhibits certain degree of resistance to fluconazole,while Candida tropicalis demonstrates higher resistance to triazole drugs.Additionally,echinocandins resistance has emerged in Candida albicans,Candida glabrata,Candida tropicalis,and Candida parapsilosis.

Objective:To investigate the safety and clinical effect of testis-sparing microsurgery(TSMS)in the treatment of benign testis tumor(BTT).Methods:We retrospectively analyzed the clinical data on 16 cases of BTT treated in the Department of Andrology of the Affiliated Hospital of Qingdao University from October 2020 to February 2023.The median age of the patients was 23 years.All the tumors were unilateral,7 in the left and 9 in the right side,with a median diameter of 1.85 cm(1.0-3.5 cm).The patients all underwent color Doppler flow imaging(CDFI),MRI,semen analysis and examination of serum T,alpha-fetoprotein(AFP),human chorionic gonadotropin(HCG)and lactate dehydrogenase(LDH),followed by TSMS.The boundaries between the tumors and normal testis tissue were accurately identified under the microscope,and the tumors and the adjacent normal testis tissue 2 mm from their margins were excised completely.Bipolar coagulation forceps were used for wound hemostasis to maximally preserve the normal testis tissue.The resected specimens were subjected to fast frozen pathology intraoperatively,and the patients were followed up for 14-40 months by regular scrotal CDFI,MRI and examinations of serum T and semen parameters.Results:The levels of serum T,AFP,HCG and LDH and semen parameters were all within the normal range preoperatively.TSMS were successfully completed in all the cases,and all were pathologically confirmed as BTT according to the latest edition of WHO Classification of Tumors:Urinary and Male Genital Tumors.CDFI showed normal blood supply within the testis tissue at 1 month after surgery.No signs of intra-testicu-lar tumor residue,recurrence or metastasis,nor significant changes in the levels of serum T,AFP,HCG or LDH or semen parameters were observed during the follow-up as compared with the baseline.Natural conception was achieved in 2 cases at 16 and 18 months re-spectively after surgery.Conclusion:BTT can be differentially diagnosed by CDFI and MRI before surgery and confirmed by histo-pathology.TSMS can achieve complete excision of the tumor,maximal sparing of the normal testis tissue and thereby effective preserva-tion of male fertility.

Patients with severe trauma require an extremely timely treatment and transfusion plays an irreplaceable role in the emergency treatment of such patients. An increasing number of evidence-based medicinal evidences and clinical practices suggest that patients with severe traumatic bleeding benefit from early transfusion of low-titer group O whole blood or hemostatic resuscitation with red blood cells, plasma and platelet of a balanced ratio. However, the current domestic mode of blood supply cannot fully meet the requirements of timely and effective blood transfusion for emergency treatment of patients with severe trauma in clinical practice. In order to solve the key problems in blood supply and blood transfusion strategies for emergency treatment of severe trauma, Branch of Clinical Transfusion Medicine of Chinese Medical Association, Group for Trauma Emergency Care and Multiple Injuries of Trauma Branch of Chinese Medical Association, Young Scholar Group of Disaster Medicine Branch of Chinese Medical Association organized domestic experts of blood transfusion medicine and trauma treatment to jointly formulate Chinese expert consensus on blood support mode and blood transfusion strategies for emergency treatment of severe trauma patients ( version 2024). Based on the evidence-based medical evidence and Delphi method of expert consultation and voting, 10 recommendations were put forward from two aspects of blood support mode and transfusion strategies, aiming to provide a reference for transfusion resuscitation in the emergency treatment of severe trauma and further improve the success rate of treatment of patients with severe trauma.