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 study on the identification of traditional Chinese medicine of Macleaya cordata(M. cordata) and its similar varieties. METHODS By consulting the ancient herbal books and modern literature, this paper systematically combs and studies the M. cordata. The morphological identification, microscopic identification, physiochemical identification, molecular identification were used to identify M. cordata and its similar varieties. RESULTS Obtained M. cordata herbal textual research data. There were some differences between M. cordata and Macleaya microcarpa(M. microcarpa) and other similar varieties in traits, microscopic, physicochemical and molecular characteristics. Molecular identification results showed that the length of the rbcL gene of M. cordata were 600 bp to 603 bp, with the average GC content ranging from 43.95% to 44.28%. There were significant differences in the variation sites between M. cordata and other similar varieties, and the variation sites with M. microcarpa were the least. The interspecific genetic distance between M. cordata and its similar varieties was greater than its maximum intraspecific genetic distance. NJ analysis results of rbcL could effectively distinguish M. cordata from other similar varieties accurately and quickly. There were significant differences in the secondary structure of rbcL between M. cordata and its similar varieties. CONCLUSION The traditional Chinese medicine identification methods of M. cordata, M. microcarpa and other similar varieties are constructed, which provides experimental basis for the variety identification of M. cordata and the subsequent development of traditional Chinese medicine resources.

Objective To explore the efficacy and safety of recombinant human anti-severe acute respiratory syn-drome coronavirus 2(anti-SARS-CoV-2)monoclonal antibody injection(F61 injection)in the treatment of patients with coronavirus disease 2019(COVID-19)combined with renal damage.Methods Patients with COVID-19 and renal damage who visited the PLA General Hospital from January to February 2023 were selected.Subjects were randomly divided into two groups.Control group was treated with conventional anti-COVID-19 therapy,while trial group was treated with conventional anti-COVID-19 therapy combined with F61 injection.A 15-day follow-up was conducted after drug administration.Clinical symptoms,laboratory tests,electrocardiogram,and chest CT of pa-tients were performed to analyze the efficacy and safety of F61 injection.Results Twelve subjects(7 in trial group and 5 in control group)were included in study.Neither group had any clinical progression or death cases.The ave-rage time for negative conversion of nucleic acid of SARS-CoV-2 in control group and trial group were 3.2 days and 1.57 days(P=0.046),respectively.The scores of COVID-19 related target symptom in the trial group on the 3rd and 5th day after medication were both lower than those of the control group(both P＜0.05).According to the clinical staging and World Health Organization 10-point graded disease progression scale,both groups of subjects improved but didn't show statistical differences(P＞0.05).For safety,trial group didn't present any infusion-re-lated adverse event.Subjects in both groups demonstrated varying degrees of elevated blood glucose,elevated urine glucose,elevated urobilinogen,positive urine casts,and cardiac arrhythmia,but the differences were not statistica-lly significant(all P＞0.05).Conclusion F61 injection has initially demonstrated safety and clinical benefit in trea-ting patients with COVID-19 combined with renal damage.As the domestically produced drug,it has good clinical accessibility and may provide more options for clinical practice.

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.

Objective:To analyze the clinical characteristics and influencing factors of vascular involvement in Beh?et′s Disease (BD) to improve and provideunderstanding of insights for clinicians to better understand this condition.Methods:Clinical data from 220 BD patients admitted to the First Affiliated Hospital of Guangxi Medical University from January 2012 to May 2022 were collected. Clinical manifestations and laboratory findings were compared between BD patients with and without vascular involvement, as well as between those with improved conditions and those with progressive conditions. Binary logistic regression was used to analyze the influencing factors.Results:①The average age of the 220 BD patients was 36.5±15.3 years. Among them, 23 patients (10.5%) had vascular involvement, including 20 males (87.0%).②Compared to BD patients without vascular involvement, those with vascular involvement had significantly higher rates of smoking [6.1%(12/197) vs.34.8%(8/23), χ2=17.19, P<0.001], cardiac involvement [1.5%(3/197) vs. 13.0%(9/23), χ2=6.42, P=0.011], and elevated C-reactive protein(CRP) levels (78.3% vs. 56.3%, χ2=4.08, P=0.043).③ Among BD patients with vascular involvement, 11 cases (47.8%) had venous lesions, and 20 cases (87.0%) had arterial lesions, with 8 cases (34.8%) having both venous and arterial involvement. The most common type of vascular involvement was arterial dilatation (11 cases), mainly aneurysms (10 cases), and deep venous thrombosis of the lower extremities (7 cases).④The 23 BD patients with vascular involvement were followed up for an average of 18.3 months. Among them, 16 patients (69.6%) showed stable improvement, while 7 patients (30.4%) experienced disease progression, including 4 deaths (1 male and 3 females). A total of 91.3% (21/23) of the patients received glucocorticoid therapy. Immunosuppressive therapy was administered to 82.6% (19/23) of the patients, with 65.2% (10/23) receiving with cyclophosphamide and 43.5% receiving with thalidomide. Additionally, 13% (3/23) of the patients were treated with cyclosporine and methotrexate, respectively, and 8.7% (2/23) were treated with received mycophenolate mofetil. Anticoagulant therapy was given to 21.7% (5/23) of the patients, using either warfarin or low molecular weight heparin. Biologic therapy was administered to 17.4% (4/23) of the patients, and surgical intervention was performed in 43.5% (10/23) of the patients. ⑤Binary logistic regression analysis identified male gender [ OR(95% CI)=5.70(1.60, 20.90), P=0.009] as an indepe-ndent risk factor for vascular involvement in BD. Conclusion:The incidence of vascular involvement in BD is 10.5%, with a higher prevalence in males. Arterial involvement is more common than venous involvement, with arterial aneurysms being the most common manifestation. Clinicians should pay attention to CRP and total cholesterol levels in BD patients.

Objective:To explore the strategy of prostate biopsy in patients with prostate specific antigen(PSA)gray zone based on prostate imaging reporting and data system (PI-RADS).Methods:The clinical data of 427 patients who underwent transperineal prostate biopsy in the First Affiliated Hospital of Nanjing Medical University from January 2020 to December 2022 were retrospectively analyzed. The median age was 66 (61, 72) years old. The median PSA was 6.62 (5.46, 8.19) ng/ml. The median PSA density (PSAD) was 0.15 (0.11, 0.21) ng/ml 2. The median prostate volume (PV) was 43.68 (31.12, 56.82) ml. PSA velocity (PSAV) data were available in 65 patients with negative MRI examination(PI-RADS <3), and the median PSAV was 1.40 (0.69, 2.89) ng/(ml· year). Among the patients with positive MRI(PI-RADS≥3), there were 174 patients with only 1 lesion and 83 patients with ≥2 lesions. A total of 170 patients with negative MRI underwent systematic biopsy, and 257 patients with positive MRI underwent systematic combined targeted biopsy. The PI-RADS score, regions of interest(ROI), PSAD, f/tPSA and PSAV were analyzed to explore the biopsy strategy for patients with PSA gray area based on bpMRI imaging. Results:Of the 427 patients included in the study, 194 were positive and 233 were negative. Among the patients with positive biopsy pathology, 140 cases were clinically significant prostate cancer (CsPCa). Among the MRI-negative patients, there were 33 cases with PSAV ≥1.4 ng/(ml·year), and 10 cases of prostate cancer and 6 cases of CsPCa were detected by systematic biopsy.In 32 cases with PSAV <1.4 ng/(ml·year), 3 cases of prostate cancer and 0 case of CsPCa were detected by systematic biopsy. The sensitivity of systematic biopsy for the diagnosis of prostate cancer and CsPCa in patients with PSAV≥1.4 ng/(ml·year) were 76.9% (10/13) and 100.0% (6/6) respectively, the specificity were 55.8% (29/52) and 54.2% (32/59) respectively, the negative predictive value were 90.6% (29/32) and 100.0% (32/32) respectively, and the positive predictive value were 30.3% (10/33) and 18.2% (6/33) respectively. In MRI-positive patients with PI-RADS 3, the prostate cancer detection rates of targeted biopsy combined with systematic biopsy, systematic biopsy and targeted biopsy were 41.7% (45/108), 32.4% (35/108) and 35.2% (38/108), respectively ( P=0.349). The detection rates of CsPCa were 27.8% (30/108), 21.3% (23/108) and 25.0% (27/108), respectively ( P=0.541). In patients with PI-RADS 4-5 and PSAD > 0.15 ng/ml 2, the detection rates of CsPCa in targeted biopsy combined with systematic biopsy, systematic biopsy and targeted biopsy were 67.8% (61/90), 58.9% (53/90) and 67.8% (61/90), respectively ( P=0.354). Conclusions:For MRI-negative patients, all CsPCa could be detected by perineal systematic biopsy when PSAV ≥1.4 ng/(ml·year), and active observation could be performed when PSAV <1.4 ng/(ml·year). For MRI-positive patients, targeted combined systemic biopsy was required when PI-RADS score was 3, and targeted biopsy only could be performed when PI-RADS score ≥4 and PSAD >0.15 ng/ml 2, otherwise targeted combined systemic biopsy was required.