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 observe the reproducibility of radiomics feature(RF)extracted from virtual monoenergetic image(VMI)of rabbit VX2 hepatoma models obtained with 3 different dual-energy CT(DECT)systems,and to explore relationship of reproducibility and diagnostic performance of RF.Methods Fifteen rabbits with VX2 hepatoma were randomly divided into 3 groups(each n=5).Contrast-enhanced abdominal CT scanning under volume CT dose index(CTDIvol)levels of 6,9 and 12 mGy were performed with dual-source DECT(dsDECT),rapid kV switching DECT(rsDECT)and dual-layer detector DECT(dlDECT),respectively.VMI were reconstructed at 10 keV increments from 40 to 140 keV.RF were extracted from VMI,the reproducibility was assessed using intra-class correlation coefficient(ICC),and those with ICC≥0.8 were considered as reproducible RF.The percentage of reproducible features(denoted by R)were compared among different scanner pairings and different CTDIvol levels.Within each CTDIvol group,the reconstruction energy levels yielding the maximum number(denoted by N)of common RF across different scanner pairings were identified.The receiver operating characteristic(ROC)curve was drawn,the area under the curve(AUC)was calculated,and the diagnostic efficacies of reproducible RF and other RF were compared under optimal reproducible conditions.Spearman correlation coefficient between ICC and the corresponding AUC of RF were calculated.Results RrsDECT-dsDECT(6.45％,95％CI[2.36％,8.87％])was higher than RdlDECT-dsDECT(0.72％,95％CI[0.15％,1.79％])and RrsDECT-dlDECT(1.43％,95％CI[0.60％,4.06％])(all adjusted P＜0.05),R9mGy(3.70％,95％CI[1.31％,5.73％])and R12mGy(2.63％,95％CI[0.60％,6.69％])were higher than R6mGy(1.31％,95％CI[0.12％,1.55％])(all adjusted P＜0.05).The optimal reproducible reconstruction energy levels of RF under CTDIvol of 6,9 and 12 mGy concentrated at 50-70 keV.AUC of reproducible RFs were higher than of other RF(all adjusted P＜0.05)and had certain correlation with the reproducibility(rs=0.102-0.516,P＜0.05).Conclusion The reproducibility of RF extracted from contrast-enhanced VMI CT images of rabbit VX2 hepatoma models associated with DECT scanner,CTDIvol level and reconstruction energy level.RF with higher reproducibility might have better diagnostic performance.

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.

At present,there are many difficulties in the diagnosis and treatment of acute vestibular syndrome(AVS).For example,complex and difficult identification of the cause of disease,uneven diagnosis and treatment levels of clinical doctors,weak humanistic care awareness,lack of communication skills,intrinsic affinity and other reasons,which make it difficult for AVS patients in the process of diagnosis and treatment,and cannot receive timely and effective treatment,resulting in an exacerbation of doctor-patient conflicts.Therefore,it is recommended to explore new paths of AVS diagnosis and treatment work using the humanistic care concept,respect each other between doctors and patients,build a team of medical staff with the value orientation of"humanistic care",and promote the organic unity of theory and practice of"humanistic care",with a view to better promoting the implementation of AVS diagnosis and treatment work,helping more patients rebuild confidence,enhancing quality of life,and improving the doctor-patient relationship.

Objective:To investigate the correlation between complement C3 and urine protein level and proteinuria remission status in patients with primary membranous nephropathy (PMN), and better guide individualized clinical treatment.Methods:It was a single-center retrospective study. The clinical data of PMN patients who underwent renal biopsy in the First Affiliated Hospital of Nanjing Medical University from January 2017 to June 2022 were collected. Patients with 24 h urinary protein ≥ 3.5 g were followed up after receiving standard treatment, and the last outpatient or inpatient review was used as the end point of follow-up. 24 h urine protein was collected to evaluate the remission status of proteinuria. Kaplan-Meier method was used to analyze the correlation between serum and renal complements and proteinuria remission. Cox regression analysis method was used to analyze the correlation between serum C3 level and renal tissue C3 deposition and proteinuria remission.Results:This study included 507 PMN patients with 312 (61.54%) males, aged 54 (43, 64) years old. Compared with 24 h urinary protein < 3.5 g group, proportion of males ( χ2=22.479, P<0.001), age ( Z=-2.521, P=0.012), systolic blood pressure ( Z=-4.148, P<0.001), diastolic blood pressure ( Z=-4.084, P<0.001), serum anti-phospholipase A2 receptor (PLA2R) antibody titer ( Z=-7.019, P<0.001), total cholesterol ( Z=-8.796, P<0.001), triglyceride ( Z=-6.158, P<0.001), low density lipoprotein cholesterol ( Z=-8.716, P<0.001), serum creatinine ( Z=-7.368, P<0.001), serum C3 ( Z=-3.663, P<0.001), serum C4 ( Z=-6.560, P<0.001), proportion of glucocorticoid use ( χ2=116.417, P<0.001) and proportion of immunosuppressant use ( χ2=53.839, P<0.001) were all higher, while serum albumin ( Z=12.518, P<0.001), estimated glomerular filtration rate ( Z=6.345, P<0.001) and serum IgG ( Z=7.321, P<0.001) were all lower in 24 h urinary protein ≥3.5 g group. There were 268 patients included in the follow-up cohort with baseline 24 h urinary protein of 7.15 (5.14, 10.24) g, serum anti-PLA2R antibody titer of 61.44 (14.35, 193.24) RU/ml, serum C3 of 1.005 (0.864, 1.150) g/L, and serum C4 of 0.260 (0.214, 0.317) g/L. Kaplan-Meier survival curve showed that the incomplete remission rate of proteinuria in serum C3 > 1.005 g/L group was lower than that in serum C3 ≤ 1.005 g/L group (log-rank χ2=4.757, P=0.029). There was no significant difference in the incomplete remission rate of proteinuria between serum C4 ≤ 0.260 g/L group and serum C4 > 0.260 g/L group (log-rank χ2=3.543, P=0.060). Renal C1q (log-rank χ2=0.167, P=0.683) and C4 (log-rank χ2=1.927, P=0.165) deposition had no significant effects on proteinuria remission in PMN patients. The incomplete remission rate of proteinuria in patients with renal C3 deposition was higher than that in patients without renal C3 deposition (log-rank χ2=7.018, P=0.008). Univariate Cox regression analysis showed that serum C3 level and C3 deposition in renal tissues were influencing factors of incomplete remission of proteinuria (both P<0.05), while adjusting for gender, age, mean arterial pressure, serum anti-PLA2R antibody, serum albumin and 24 h urinary protein, serum C3 ≤ 1.005 g/L ( HR=1.374, 95% CI 1.021-1.849, P=0.036), C3 deposition in renal tissues ( HR=1.949, 95% CI 1.098-3.460, P=0.023), and serum C3 ≤ 1.005 g/L combined with C3 deposition in renal tissues ( HR=1.472, 95% CI 1.093-1.983, P=0.011) were independent influencing factors of incomplete remission of proteinuria. Conclusions:The serum C3 level and C3 deposition in renal tissues are closely related to urinary protein level and proteinuria remission status in PMN patients. The patients with higher urinary protein have higher serum C3. For patients with massive proteinuria, serum C3 ≤ 1.005 g/L, C3 deposition in renal tissues, serum C3 ≤ 1.005 g/L combined with C3 deposition in renal tissues are independent risk factors of incomplete remission of proteinuria.

The aim of the present study was to investigate the effects of short-term ketogenic diet on the low temperature tolerance of mice and the involvement of peroxisome proliferator-activated receptor α (PPARα). C57BL/6J mice were divided into two groups: normal diet (WT+ND) group and ketogenic diet (WT+KD) group. After being fed with normal or ketogenic diet at room temperature for 2 d, the mice were exposed to 4 °C low temperature for 12 h. The changes in core temperature, blood glucose, blood pressure of mice under low temperature condition were detected, and the protein expression levels of PPARα and mitochondrial uncoupling protein 1 (UCP1) were detected by Western blot. PPARα knockout mice were divided into normal diet (PPARα^-/-+ND) group and ketogenic diet (PPARα^-/-+KD) group. After being fed with the normal or ketogenic diet at room temperature for 2 d, the mice were exposed to 4 °C low temperature for 12 h. The above indicators were also detected. The results showed that, at room temperature, the protein expression levels of PPARα and UCP1 in liver and brown adipose tissue of WT+KD group were significantly up-regulated, compared with those of WT+ND group. Under low temperature condition, compared with WT+ND, the core temperature and blood glucose of WT+KD group were increased, while mean arterial pressure was decreased; The ketogenic diet up-regulated PPARα protein expression in brown adipose tissue, as well as UCP1 protein expression in liver and brown adipose tissue of WT+KD group. Under low temperature condition, compared to WT+ND group, PPARα^-/-+ND group exhibited decreased core temperature and down-regulated PPARα and UCP1 protein expression levels in liver, skeletal muscle, white and brown adipose tissue. Compared to the PPARα^-/-+ND group, the PPARα^-/-+KD group exhibited decreased core temperature and did not show any difference in the protein expression of UCP1 in liver, skeletal muscle, white and brown adipose tissue. These results suggest that the ketogenic diet promotes UCP1 expression by up-regulating PPARα, thus improving low temperature tolerance of mice. Therefore, short-term ketogenic diet can be used as a potential intervention to improve the low temperature tolerance.
Animals ; Mice ; Adipose Tissue, Brown/metabolism* ; PPAR alpha/pharmacology* ; Diet, Ketogenic ; Uncoupling Protein 1/metabolism* ; Blood Glucose/metabolism* ; Temperature ; Mice, Inbred C57BL ; Liver ; Adipose Tissue/metabolism*