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.

Sulforaphane is a naturally occurring active substance derived from cruciferous vegetables with potent antioxidant and anticancer properties. Researches have shown that sulforaphane has good bioavailability and can be absorbed by the small intestine through passive transport, followed by excretion in the form of urine via the hydrophobic acid pathway. In addition, since sulforaphane is easy to be absorbed and metabolized, wrapping sulforaphane with nanomaterials can improve its bioavailability and stability, prolong its action time in human body, and better utilize its therapeutic effect. In terms of mechanism of action, sulforaphane can activate Nrf2 and HSF1 signaling pathways, induce the expression of phase II detoxification enzymes HO-1, NADPH, GST and HSP, thus regulating the concentration of oxidative stress ROS in vivo; inhibit NF-κB signaling pathway, thus suppressing the expression of inflammatory factors TNF-α, IL-1 and IL-6; regulate epigenetic modifications, thus inhibiting HDAC and DNMT, and increasing the concentration of histone H3 and H4. By regulating the expression levels of the above factors, sulforaphane can affect the occurrence and development of cancer, neurodegenerative diseases and other diseases. In recent years, several phase I/II clinical trials have shown that sulforaphane has good drug-generating properties. For example, researchers have found that patients with skin cancer have not shown any health problems and their corresponding functional problems have improved greatly after long-term use of sulforaphane. This suggests that in the future sulforaphane has a very high medicinal potential for the treatment of cancer and neurodegenerative diseases. In this paper, we review the pharmacokinetics, target of action and safety of sulforaphane and its research progress in tumor and neurodegenerative diseases to provide a reference for the future application of sulforaphane in the treatment of tumor and neurodegenerative diseases.

Objective To explore the effects of glycyrrhizic acid(GA)on neurons injury in traumatic brain injury(TBI)rats and the possible mechanism.Methods The rats were randomly divided into sham-operation group,model group,control group and experimental-L,-M,-H groups,with 20 rats each group.The sham-operation group was only treated with craniotomy;the other 5 groups were used to establish TBI models by extracorporeal shock method.At 0,24 and 48 h after modeling,the experimental-L,-M,-H groups were intraperitoneally injected with 10,50 and 100 mg·kg-1 GA solution,respectively;control group was intraperitoneally injected with 2 mg·kg-1 nimodipine;sham-operation and model groups were intraperitoneally injected with the equal volume of phosphate buffered solution.The degree of neurological dysfunction was evaluated by cerebral edema and modified neurological severity score(mNSS).The apoptosis rates of neurons in rat brain tissue was evaluated by apoptosis staining.Western blot was used to analyze the expression levels of apoptosis-related proteins and aquaporin 4(AQP4)protein.Results The mNSS scores of experimental-M,-H groups,control group,model group,sham-operation group were(6.98±0.82),(5.28±0.37),(5.91±0.52),(13.28±1.59)and(0.36±0.01)points;the degrees of brain edema were(63.27±10.33)％,(60.09±9.38)％,(66.86±9.91)％,(85.92±11.93)％and(52.17±8.53)％;the apoptosis rates of neurons were(6.81±0.73)％,(5.39±0.25)％,(5.87±0.62)％,(15.13±3.29)％and(2.56±0.03)％;the relative expression levels of B cell lymphoma 2(Bel-2)protein were 0.49±0.06,0.68±0.15,0.62±0.03,0.13±0.03 and 0.95±0.13;the relative expression levels of Bel-2 associated X protein were 0.61±0.08,0.55±0.17,0.39±0.09,0.92±0.19 and 0.16±0.02;the relative expression levels of AQP4 protein were 0.69±0.15,0.38±0.03,0.47±0.09,0.86±0.13 and 0.13±0.09,respectively.There were statistically significant differences in the above indexes between the model group and the experimental-M,-H groups and control group(all P＜0.05).Conclusion GA is able to reduce the brain edema degree and neurological dysfunction in TBI rats,and inhibit neuronal damage and apoptosis,and the mechanism of action may be associated with the inhibition of AQP 4 expression.

AIM To investigate the protective effects and the mechanism of corosolic acid on doxorubicin-induced cardiotoxicity in H9c2 cardiomyocytes.METHODS To screen and determine the effective concentration of corosolic acid,the injury models of H9c2 cardiomyocytes established by 1 μmol/L doxorubicin were exposed to 24 h different concentrations of corosolic acid,followed by detections of their cell activity by MTT method;their cell apoptosis morphology by Hoechst 33342 staining method;their cell apoptosis rate by Annexin V-FITC/PI double staining method;their intracellular ROS level by DCFH-DA probe;their intracellular iron level by iron ion colorimetry;and their protein expressions of Bax,Bcl-2,cleaved-caspase3,Nrf2,GPX4 and Ptgs2 by Western blot.RESULTS Upon the doxorubicin-induced injury models of H9c2 cardiomyocytes,corosolic acid improved their viability and survival rate(P<0.05),decreased their levels of ROS and Fe2+ and the apoptosis rate(P<0.05),up-regulated the protein expressions of Bcl-2,Nrf2 and GPX4(P<0.05),and down-regulated the protein expressions of Bax,cleved-caspase 3 and Ptgs2(P<0.05).CONCLUSION Corosolic acid can inhibit the ROS level and apoptosis of doxorubicin-induced injury models of H9c2 cardiomyocytes,and the iron death as well via activating Nrf2/GPX4 pathway.

To explore the value of portable oto-endoscopy system in clinical teaching of otolaryngology residents.

Objective:To investigate the incidence of postoperative complications in Chinese patients with gastric or colorectal cancer, and to evaluate the risk factors for postoperative complications.Methods:This was a national, multicenter, prospective, registry-based, cohort study of data obtained from the database of the Prevalence of Abdominal Complications After Gastro- enterological Surgery (PACAGE) study sponsored by the China Gastrointestinal Cancer Surgical Union. The PACAGE database prospectively collected general demographic characteristics, protocols for perioperative treatment, and variables associated with postoperative complications in patients treated for gastric or colorectal cancer in 20 medical centers from December 2018 to December 2020. The patients were grouped according to the presence or absence of postoperative complications. Postoperative complications were categorized and graded in accordance with the expert consensus on postoperative complications in gastrointestinal oncology surgery and Clavien-Dindo grading criteria. The incidence of postoperative complications of different grades are presented as bar charts. Independent risk factors for occurrence of postoperative complications were identified by multifactorial unconditional logistic regression.Results:The study cohort comprised 3926 patients with gastric or colorectal cancer, 657 (16.7%) of whom had a total of 876 postoperative complications. Serious complications (Grade III and above) occurred in 4.0% of patients (156/3926). The rate of Grade V complications was 0.2% (7/3926). The cohort included 2271 patients with gastric cancer with a postoperative complication rate of 18.1% (412/2271) and serious complication rate of 4.7% (106/2271); and 1655 with colorectal cancer, with a postoperative complication rate of 14.8% (245/1655) and serious complication rate of 3.0% (50/1655). The incidences of anastomotic leakage in patients with gastric and colorectal cancer were 3.3% (74/2271) and 3.4% (56/1655), respectively. Abdominal infection was the most frequently occurring complication, accounting for 28.7% (164/572) and 39.5% (120/304) of postoperative complications in patients with gastric and colorectal cancer, respectively. The most frequently occurring grade of postoperative complication was Grade II, accounting for 65.4% (374/572) and 56.6% (172/304) of complications in patients with gastric and colorectal cancers, respectively. Multifactorial analysis identified (1) the following independent risk factors for postoperative complications in patients in the gastric cancer group: preoperative comorbidities (OR=2.54, 95%CI: 1.51-4.28, P<0.001), neoadjuvant therapy (OR=1.42, 95%CI:1.06-1.89, P=0.020), high American Society of Anesthesiologists (ASA) scores (ASA score 2 points:OR=1.60, 95% CI: 1.23-2.07, P<0.001, ASA score ≥3 points:OR=0.43, 95% CI: 0.25-0.73, P=0.002), operative time >180 minutes (OR=1.81, 95% CI: 1.42-2.31, P<0.001), intraoperative bleeding >50 mL (OR=1.29,95%CI: 1.01-1.63, P=0.038), and distal gastrectomy compared with total gastrectomy (OR=0.65,95%CI: 0.51-0.83, P<0.001); and (2) the following independent risk factors for postoperative complications in patients in the colorectal cancer group: female (OR=0.60, 95%CI: 0.44-0.80, P<0.001), preoperative comorbidities (OR=2.73, 95%CI: 1.25-5.99, P=0.030), neoadjuvant therapy (OR=1.83, 95%CI:1.23-2.72, P=0.008), laparoscopic surgery (OR=0.47, 95%CI: 0.30-0.72, P=0.022), and abdominoperineal resection compared with low anterior resection (OR=2.74, 95%CI: 1.71-4.41, P<0.001). Conclusion:Postoperative complications associated with various types of infection were the most frequent complications in patients with gastric or colorectal cancer. Although the risk factors for postoperative complications differed between patients with gastric cancer and those with colorectal cancer, the presence of preoperative comorbidities, administration of neoadjuvant therapy, and extent of surgical resection, were the commonest factors associated with postoperative complications in patients of both categories.