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:We aimed to develop a novel visualized model based on nomogram to predict postoperative overall survival.Methods:This was a multicenter, retrospective, observational cohort study, including participants with histologically confirmed gastric and colorectal cancer who underwent radical surgery from 11 medical centers in China from August 1, 2015 to June 30, 2018. Baseline characteristics, histopathological data and nutritional status, as assessed using Nutrition Risk Screening 2002 (NRS 2002) score and the scored Patient-Generated Subjective Global Assessment, were collected. The least absolute shrinkage and selection operator regression and Cox regression were used to identify variables to be included in the predictive model. Internal and external validations were performed.Results:There were 681 and 127 patients in the training and validation cohorts, respectively. A total of 188 deaths were observed over a median follow-up period of 59 (range: 58 to 60) months. Two independent predictors of NRS 2002 and Tumor-Node-Metastasis (TNM) stage were identified and incorporated into the prediction nomogram model together with the factor of age. The model's concordance index for 1-, 3- and 5-year overall survival was 0.696, 0.724, and 0.738 in the training cohort and 0.801, 0.812, and 0.793 in the validation cohort, respectively.Conclusions:In this study, a new nomogram prediction model based on NRS 2002 score was developed and validated for predicting the overall postoperative survival of patients with gastric colorectal cancer. This model has good differentiation, calibration and clinical practicability in predicting the long-term survival rate of patients with gastrointestinal cancer after radical surgery.

During the process of dairy farming,various factors such as physical injury and bacterial infection act upon body tissues or organs,leading to the disruption of skin or mucous tissue integ-rity and subsequent tissue injury and trauma.The healing of these injuries is a complex process that necessitates the coordinated efforts of different cells and involvement of diverse cytokines.A-mong them,the interaction between macrophages and myofibroblasts is indispensable for efficient tissue repair.Nod-like receptor protein 3(NLRP3),a pattern recognition receptor in the innate im-mune system,may play a regulatory role in modulating this intricate process.In this study,cow myofibroblasts and M1 type bone marrow-derived macrophages were cultured in vitro,followed by collection of cell culture supernatant for co-culture analysis.Both cytokine secretion levels in M1 type bone marrow-derived macrophages as well as expression patterns levels of myofibroblast growth factor protein and mRNA were detected.The regulatory mechanism underlying NLRP3 in-volvement in mediating interactions between these two cell types was investigated using NLRP3 inhibitor MCC950.The results showed that an effective method for culturing cow muscle fibroblasts in vitro was successfully established and myofibroblast conditioned medium(MFbCM)could regulate M1 macrophage secretion profiles.Moreover,M1 macrophage conditioned medium(M1?CM)was found to influence myofibroblast growth factor expression levels.Our findings sug-gest that NLRP3 plays a significant regulatory role during crosstalk between myofibroblasts and M1-type pro-inflammatory macrophages.

Type B insulin resistance syndrome(TBIR)is a rare autoimmune disease caused by the presence of autoantibodies against insulin receptors in the human body,leading to severe refractory hyperglycemia or refractory hypoglycemia.This article reports a case of TBIR patient,summarizes and analyzes its epidemiological characteristics and diagnosis and treatment methods,providing a basis for clinical treatment.

Objective To explore the effect of acute caffeine and theanine supplementation on coordi-nation and aerobic performance in mentally fatigued soccer players.Methods A randomized crossover de-sign was employed with 15 male amateur soccer players.Participants underwent three different interven-tions—caffeine(caffeine group),theanine(theanine group),and placebo(placebo group)—with a one-week washout period between each intervention.After each supplementation,participants performed a 45-minute Stroop task to induce mental fatigue,followed by a speed dribbling test(SDT)and the 30-15 intermittent fitness test(30-15IFT)to assess coordination and aerobic performance,respectively.Mea-surements included visual analog scale for mental fatigue(VAS-MF),motivation(VAS-MO),Brunel mood scale for fatigue(BRUMS-F)and vigor(BRUMS-V)pre-and post-Stroop task,response time(RT),response accuracy(ACC),average heart rate(HRave)during Stroop,mental exertion(VAS-ME)post-Stroop,rating of perceived exertion(RPE),HRave,and peak heart rate(HRpeak)during SDT and 30-15IFT.All data were analyzed using repeated measures ANOVA.Results The change in VAS-MF(ΔVAS-MF)before and after the Stroop task was lower in the caffeine group compared to the placebo group(P=0.064),while the theanine group showed similar ΔVAS-MF to the latter group(P=0.999).Both the caffeine and theanine groups had significantly faster RT(P=0.003 and 0.033,respectively)and higher ACC(P=0.006 and 0.033,respectively)during the Stroop task compared to the placebo group.Moreover,coordination performance in both the caffeine and theanine groups was better than the placebo group(P=0.096 and 0.078,respectively).Meanwhile,aerobic performance in the caffeine group was significantly better than the placebo group[time to exhaustion(TTE):P=0.012;last stage ve-locity of 30-15IFT(VIFT):P=0.007;maximal oxygen uptake(VO2max):P=0.008],whereas no significant differences were found between the theanine group and the placebo group in the aerobic performance(TTE:P=0.999;VIFT:P=0.999;VO2max:P=0.999).Conclusion Both acute caffeine and theanine supple-mentation can mitigate the negative effect of mental fatigue on coordination performance in soccer play-ers.Additionally,acute caffeine supplementation can also alleviate the negative impact of mental fa-tigue on aerobic performance.

Objective:To investigate the clinical features and therapeutic efficacy of patients with hereditary leiomyomatosis and renal cell carcinoma(RCC) syndrome-associated RCC (HLRCC-RCC) in China.Methods:The clinical data of 119 HLRCC-RCC patients with fumarate hydratase (FH) germline mutation confirmed by genetic diagnosis from 15 medical centers nationwide from January 2008 to December 2021 were retrospectively analyzed. Among them, 73 were male and 46 were female. The median age was 38(13, 74) years. The median tumor diameter was 6.5 (1.0, 20.5) cm. There were 38 cases (31.9%) in stage Ⅰ-Ⅱand 81 cases (68.1%) in stage Ⅲ-Ⅳ. In this group, only 11 of 119 HLRCC-RCC patients presented with skin smooth muscle tumors, and 44 of 46 female HLRCC-RCC patients had a history of uterine fibroids. The pathological characteristics, treatment methods, prognosis and survival of the patients were summarized.Results:A total of 86 patients underwent surgical treatment, including 70 cases of radical nephrectomy, 5 cases of partial nephrectomy, and 11 cases of reductive nephrectomy. The other 33 patients with newly diagnosed metastasis underwent renal puncture biopsy. The results of genetic testing showed that 94 patients had FH gene point mutation, 18 had FH gene insertion/deletion mutation, 4 had FH gene splicing mutation, 2 had FH gene large fragment deletion and 1 had FH gene copy number mutation. Immunohistochemical staining showed strong 2-succinocysteine (2-SC) positive and FH negative in 113 patients. A total of 102 patients received systematic treatment, including 44 newly diagnosed patients with metastasis and 58 patients with postoperative metastasis. Among them, 33 patients were treated with tyrosine kinase inhibitor (TKI) combined with immune checkpoint inhibitor (ICI), 8 patients were treated with bevacizumab combined with erlotinib, and 61 patients were treated with TKI monotherapy. Survival analysis showed that the median progression-free survival (PFS) of TKI combined with ICI was 18 (5, 38) months, and the median overall survival (OS) was not reached. The median PFS and OS were 12 (5, 14) months and 30 (10, 32) months in the bevacizumab combined with erlotinib treatment group, respectively. The median PFS and OS were 10 (3, 64) months and 44 (10, 74) months in the TKI monotherapy group, respectively. PFS ( P=0.009) and OS ( P=0.006) in TKI combined with ICI group were better than those in bevacizumab combined with erlotinib group. The median PFS ( P=0.003) and median OS ( P=0.028) in TKI combined with ICI group were better than those in TKI monotherapy group. Conclusions:HLRCC-RCC is rare but has a high degree of malignancy, poor prognosis and familial genetic characteristics. Immunohistochemical staining with strong positive 2-SC and negative FH can provide an important basis for clinical diagnosis. Genetic detection of FH gene germ line mutation can confirm the diagnosis. The preliminary study results confirmed that TKI combined with ICI had a good clinical effect, but it needs to be confirmed by the results of a large sample multi-center randomized controlled clinical study.