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.

Background/Aims: Treatment indications for patients with chronic hepatitis B (CHB) remain contentious, particularly for patients with mild alanine aminotransferase (ALT) elevation. We aimed to evaluate treatment effects in this patient population. Methods: This rollover study extended a placebo-controlled trial that enrolled non-cirrhotic patients with CHB and ALT levels below two times the upper limit of normal. Following 3 years of randomized intervention with either tenofovir disoproxil fumarate (TDF) or placebo, participants were rolled over to open-label TDF for 3 years. Liver biopsies were performed before and after the treatment to evaluate histopathological changes. Virological, biochemical, and serological outcomes were also assessed (NCT02463019). Results: Of 146 enrolled patients (median age 47 years, 80.8% male), 123 completed the study with paired biopsies. Overall, the Ishak fibrosis score decreased in 74 (60.2%), remained unchanged in 32 (26.0%), and increased in 17 (13.8%) patients (p<0.0001). The Knodell necroinflammation score decreased in 58 (47.2%), remained unchanged in 29 (23.6%), and increased in 36 (29.3%) patients (p=0.0038). The proportion of patients with an Ishak score ≥ 3 significantly decreased from 26.8% (n=33) to 9.8% (n=12) (p=0.0002). Histological improvements were more pronounced in patients switching from placebo. Virological and biochemical outcomes also improved in placebo switchers and remained stable in patients who continued TDF. However, serum HBsAg levels did not change and no patient cleared HBsAg. Conclusions In CHB patients with minimally raised ALT, favorable histopathological, biochemical, and virological outcomes were observed following 3-year TDF treatment, for both treatment-naïve patients and those already on therapy.

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.

Background/Aims: Treatment indications for patients with chronic hepatitis B (CHB) remain contentious, particularly for patients with mild alanine aminotransferase (ALT) elevation. We aimed to evaluate treatment effects in this patient population. Methods: This rollover study extended a placebo-controlled trial that enrolled non-cirrhotic patients with CHB and ALT levels below two times the upper limit of normal. Following 3 years of randomized intervention with either tenofovir disoproxil fumarate (TDF) or placebo, participants were rolled over to open-label TDF for 3 years. Liver biopsies were performed before and after the treatment to evaluate histopathological changes. Virological, biochemical, and serological outcomes were also assessed (NCT02463019). Results: Of 146 enrolled patients (median age 47 years, 80.8% male), 123 completed the study with paired biopsies. Overall, the Ishak fibrosis score decreased in 74 (60.2%), remained unchanged in 32 (26.0%), and increased in 17 (13.8%) patients (p<0.0001). The Knodell necroinflammation score decreased in 58 (47.2%), remained unchanged in 29 (23.6%), and increased in 36 (29.3%) patients (p=0.0038). The proportion of patients with an Ishak score ≥ 3 significantly decreased from 26.8% (n=33) to 9.8% (n=12) (p=0.0002). Histological improvements were more pronounced in patients switching from placebo. Virological and biochemical outcomes also improved in placebo switchers and remained stable in patients who continued TDF. However, serum HBsAg levels did not change and no patient cleared HBsAg. Conclusions In CHB patients with minimally raised ALT, favorable histopathological, biochemical, and virological outcomes were observed following 3-year TDF treatment, for both treatment-naïve patients and those already on therapy.

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.

Background/Aims: Treatment indications for patients with chronic hepatitis B (CHB) remain contentious, particularly for patients with mild alanine aminotransferase (ALT) elevation. We aimed to evaluate treatment effects in this patient population. Methods: This rollover study extended a placebo-controlled trial that enrolled non-cirrhotic patients with CHB and ALT levels below two times the upper limit of normal. Following 3 years of randomized intervention with either tenofovir disoproxil fumarate (TDF) or placebo, participants were rolled over to open-label TDF for 3 years. Liver biopsies were performed before and after the treatment to evaluate histopathological changes. Virological, biochemical, and serological outcomes were also assessed (NCT02463019). Results: Of 146 enrolled patients (median age 47 years, 80.8% male), 123 completed the study with paired biopsies. Overall, the Ishak fibrosis score decreased in 74 (60.2%), remained unchanged in 32 (26.0%), and increased in 17 (13.8%) patients (p<0.0001). The Knodell necroinflammation score decreased in 58 (47.2%), remained unchanged in 29 (23.6%), and increased in 36 (29.3%) patients (p=0.0038). The proportion of patients with an Ishak score ≥ 3 significantly decreased from 26.8% (n=33) to 9.8% (n=12) (p=0.0002). Histological improvements were more pronounced in patients switching from placebo. Virological and biochemical outcomes also improved in placebo switchers and remained stable in patients who continued TDF. However, serum HBsAg levels did not change and no patient cleared HBsAg. Conclusions In CHB patients with minimally raised ALT, favorable histopathological, biochemical, and virological outcomes were observed following 3-year TDF treatment, for both treatment-naïve patients and those already on therapy.

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.

ObjectiveTo investigate the role of 4-week high-intensity interval training (HIIT) in modulating the metabolic homeostasis of the pyruvate-lactate axis in the hippocampus of rats with chronic unpredictable mild stress (CUMS) to improve their depressive-like behavior. MethodsForty-eight SPF-grade 8-week-old male SD rats were randomly divided into 4 groups: the normal quiet group (C), the CUMS quiet group (M), the normal exercise group (HC), and the CUMS exercise group (HM). The M and HM groups received 8 weeks of CUMS modeling, while the HC and HM groups were exposed to 4 weeks of HIIT starting from the 5th week (3 min (85%-90%) S_max+1 min (50%-55%) S_max, 3-5 cycles, S_max is the maximum movement speed). A lactate analyzer was used to detect the blood lactate concentration in the quiet state of rats in the HC and HM groups at week 4 and in the 0, 2, 4, 8, 12, and 24 h after exercise, as well as in the quiet state of rats in each group at week 8. Behavioral indexes such as sucrose preference rate, number of times of uprightness and number of traversing frames in the absenteeism experiment, and other behavioral indexes were used to assess the depressive-like behavior of the rats at week 4 and week 8. The rats were anesthetized on the next day after the behavioral test in week 8, and hippocampal tissues were taken for assay. LC-MS non-targeted metabolomics, target quantification, ELISA and Western blot were used to detect the changes in metabolite content, lactate and pyruvate concentration, the content of key metabolic enzymes in the pyruvate-lactate axis, and the protein expression levels of monocarboxylate transporters (MCTs). Results4-week HIIT intervention significantly increased the sucrose preference rate, the number of uprights and the number of traversed frames in the absent field experiment in CUMS rats; non-targeted metabolomics assay found that 21 metabolites were significantly changed in group M compared to group C, and 14 and 11 differential metabolites were significantly dialed back in the HC and HM groups, respectively, after the 4-week HIIT intervention; the quantitative results of the targeting showed that, compared to group C, lactate concentration in the hippocampal tissues of M group, compared with group C, lactate concentration in hippocampal tissue was significantly reduced and pyruvate concentration was significantly increased, and 4-week HIIT intervention significantly increased the concentration of lactate and pyruvate in hippocampal tissue of HM group; the trend of changes in blood lactate concentration was consistent with the change in lactate concentration in hippocampal tissue; compared with group C, the LDHB content of group M was significantly increased, the content of PKM2 and PDH, as well as the protein expression level of MCT2 and MCT4 were significantly reduced. The 4-week HIIT intervention upregulated the PKM2 and PDH content as well as the protein expression levels of MCT2 and MCT4 in the HM group. ConclusionThe 4-week HIIT intervention upregulated blood lactate concentration and PKM2 and PDH metabolizing enzymes in hippocampal tissues of CUMS rats, and upregulated the expression of MCT2 and MCT4 transport carrier proteins to promote central lactate uptake and utilization, which regulated metabolic homeostasis of the pyruvate-lactate axis and improved depressive-like behaviors.

Aim To investigate the therapeutic effect of the MW-9 on ulcerative colitis(UC)and reveal the underlying mechanism, so as to provide a scientific guidance for the MW-9 treatment of UC. Methods The model of lipopolysaccharide(LPS)-stimulated RAW264.7 macrophage cells was established. The effect of MW-9 on RAW264.7 cells viability was detected by MTT assay. The levels of nitric oxide(NO)in RAW264.7 macrophages were measured by Griess assay. Cell supernatants and serum levels of inflammatory cytokines containing IL-6, TNF-α and IL-1β were determined by ELISA kits. Dextran sulfate sodium(DSS)-induced UC model in mice was established and body weight of mice in each group was measured. The histopathological damage degree of colonic tissue was assessed by HE staining. The protein expression of p-p38, p-ERK1/2 and p-JNK was detected by Western blot. Results MW-9 intervention significantly inhibited NO release in RAW264.7 macrophages with IC50 of 20.47 mg·L-1 and decreased the overproduction of inflammatory factors IL-6, IL-1β and TNF-α(P<0.05). MW-9 had no cytotoxicity at the concentrations below 6 mg·L-1. After MW-9 treatment, mouse body weight was gradually reduced, and the serum IL-6, IL-1β and TNF-α levels were significantly down-regulated. Compared with the model group, MW-9 significantly decreased the expression of p-p38 and p-ERK1/2 protein. Conclusions MW-9 has significant anti-inflammatory activities both in vitro and in vivo, and its underlying mechanism for the treatment of UC may be associated with the inhibition of MAPK signaling pathway.