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 establish and validate a multimodal MRI radiomics model based on intratumoral and peritumoral heterogeneity for prediction of spatial pattern of locally recurrent high-grade gliomas(HGGs).Methods A retrospective analysis was conducted on the clinical and imaging data of all HGGs patients who underwent maximum safe resection followed by postoperative radiotherapy combined with temozolomide treatment and experienced in local recurrence in Army Medical Center of PLA from 2012 to 2021.Two radiologists independently assessed the spatial patterns of locally recurrence HGGs through continuous follow-up MRI data,and primarily categorized the pattern into intra-resection cavity recurrence and extra-resection cavity recurrence.The subjected patients were randomly divided into a training set and a validation set in a 7∶3 ratio.In the training set,Pearson or Spearman correlation analysis and least absolute shrinkage and selection operator(LASSO)analysis were employed to screen radiomic features within the intratumoral and peritumoral regions,as well as to calculate radiomic scores.A radiomics model was established using logistic regression analysis.The performance of the model was assessed using calibration curves,Hosmer-Lemeshow goodness-of-fit test,and the area under the receiver operating characteristic curve(AUC).Validation of the model was performed in the validation set.Results A total of 121 patients with locally recurrent HGGs were enrolled in this study,including 54 in intra-resection cavity recurrence group and 67 in extra-resection cavity recurrence group.Among them,84 were assigned into the training set and 37 into the validation set.In the training set,the radiomics score for the extra-resection cavity recurrence group was 0.424(0.278,0.573),which was higher than that for the intra-resection cavity recurrence group[-0.030(-0.226,0.248),P<0.001].In the validation set,the radiomics score for the extra-resection cavity recurrence group was 0.369(0.258,0.487),which was higher than that for the intra-resection cavity recurrence group[0.277(0.103,0.322),P=0.033].The established radiomics model exhibited good calibration and performed well in predicting spatial recurrence patterns,with an AUC value of 0.844(95%CI:0.749～0.914)in the training set and 0.706(95%CI:0.534～0.844)in the validation set.Conclusion Our multimodal radiomics model combined with intratumoral and peritumoral heterogeneity can predict the spatial pattern of locally recurrent HGGs,providing a basis for individualized treatment of HGGs.

This paper aimed to investigate the therapeutic effect and mechanism of action of the Yiqi Fumai Formula(YQFM), a kind of traditional Chinese medicine(TCM), on mice with experimental heart failure based on the "heart-gut axis" theory. Based on the network pharmacology integrated with the group collaboration algorithm, the active ingredients were screened, a "component-target-disease" network was constructed, and the potential pathways regulated by the formula were predicted and analyzed. Next, the model of experimental heart failure was established by intraperitoneal injection of adriamycin at a single high dose(15 mg·kg~(-1)) in BALB/c mice. After intraperitoneal injection of YQFM(lyophilized) at 7.90, 15.80, and 31.55 mg·d~(-1) for 7 d, the protective effects of the formula on cardiac function were evaluated using indicators such as ultrasonic electrocardiography and myocardial injury markers. Combined with inflammatory factors in the cardiac and colorectal tissue, as well as targeted assays, the relevant indicators of potential pathways were verified. Meanwhile, 16S rDNA sequencing was performed on mouse fecal samples using the Illumina platform to detect changes in gut flora and analyze differential metabolic pathways. The results show that the administration of injectable YQFM(lyophilized) for 7 d significantly increased the left ventricular end-systolic internal diameter, fractional shortening, and ejection fraction of cardiac tissue of mice with experimental heart failure(P<0.05). Moreover, markers of myocardial injury were significantly decreased(P<0.05), indicating improved cardiac function, along with significantly suppressed inflammatory responses in cardiac and intestinal tissue(P<0.05). Additionally, the species of causative organisms was decreased, and the homeostasis of gut flora was improved, involving a modulatory effect on PI3K-Akt signaling pathway-related inflammation in cardiac and colorectal tissue. In conclusion, YQFM can affect the "heart-gut axis" immunity through the homeostasis of the gut flora, thereby exerting a therapeutic effect on heart failure. This finding provides a reference for the combination of TCM and western medicine to prevent and treat heart failure based on the "heart-gut axis" theory.
Animals ; Drugs, Chinese Herbal/administration & dosage* ; Heart Failure/microbiology* ; Mice ; Mice, Inbred BALB C ; Male ; Disease Models, Animal ; Gastrointestinal Microbiome/drug effects* ; Heart/physiopathology* ; Humans ; Signal Transduction/drug effects*

Gegen Qinlian Decoction(GQD) is a classic prescription for the clinical treatment of ulcerative colitis(UC). This study, based on the differences in efficacy observed in UC mice under different level of bile acids treated with GQD, aims to clarify the impact of bile acids on UC and its therapeutic effects. It further investigates the expression of bile acid receptors in the liver of UC mice, and preliminarily reveals the mechanism through which GQD affects bile acid synthesis in the treatment of UC. A UC mouse model was established using dextran sulfate sodium(DSS) induction. The efficacy of GQD was evaluated by assessing the general condition, disease activity index(DAI) score, colon length, and histopathological changes in colon tissue via hematoxylin and eosin(HE) staining. ELISA and Western blot were used to evaluate the inflammatory response in colon tissue. The total bile acid(TBA) level and liver damage were quantified using an automatic biochemistry analyzer. The expression levels of bile acid receptors and bile acid synthetases in liver tissue were detected by Western blot and RT-qPCR. The results showed that compared with the model group, GQD treatment significantly improved the DAI score, colon shortening, and histopathological damage in UC mice. The levels of pro-inflammatory factors TNF-α and IL-6 in the colon were significantly reduced. Serum TBA levels were significantly decreased, while alkaline phosphatase(ALP) levels significantly increased. After administration of cholic acid(CA), UC symptoms in the CA + GQD group were significantly aggravated compared with the GQD group. The DAI score, degree of weight loss, colon injury, serum TBA, and liver injury markers all increased significantly. However, compared with the CA group, the CA + GQD group showed a marked reduction in TBA levels and a significant improvement in UC-related symptoms, indicating that GQD can alleviate UC damage exacerbated by CA. Further investigation into the expression of bile acid receptors and synthetases in the liver showed that under GQD treatment, the expression of farnesoid X receptor(FXR) and small heterodimer partner(SHP) significantly increased, while the expression of G protein-coupled receptor 5(TGR5) and cholesterol 7α-hydroxylase(Cyp7A1) significantly decreased. These findings suggest that GQD may affect bile acid receptors and synthetases, inhibiting bile acid synthesis through the FXR/SHP pathway to treat UC.
Animals ; Colitis, Ulcerative/genetics* ; Bile Acids and Salts/biosynthesis* ; Drugs, Chinese Herbal/administration & dosage* ; Mice ; Male ; Humans ; Receptors, Cytoplasmic and Nuclear/metabolism* ; Colon/metabolism* ; Disease Models, Animal ; Liver/metabolism* ; Mice, Inbred C57BL

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 investigate the comparative neuroprotective effects of human umbilical cord mesenchymal stem cells(hUC-MSCs-Exos)administered via different routes on hypoxic ischemic brain damage(HIBD)in neonatal mice.Methods Healthy one-week-old SPF-grade BALB/c mice were randomly divided into 4 groups:sham operation group(n=6),model group(n=6),exosome group 1(n=8),exosome group 2(n=8).HIBD was induced using the Rice-Vannucci method.Exosome group 1 and Exosome group 2 were intraperitoneal injection/intranasal drip of phosphate buffer(PBS)100 μl containing 10 μl exosomes within 24 h after successful modeling,respectively.Sham operation and model groups were intraperitoneal injection of PBS 100 μl.On the 7th day after the intervention,neuromotor function was assessed using the horizontal grid test and pole climbing test.On the 2nd day after the evaluation,all mice were killed and their brains were removed by decapitation.HE staining was used to observe the pathological injury of brain tissue,toluidine blue staining was used to observe the survival of neurons in cerebral cortex,and TUNEL staining was used to observe the apoptosis of cerebral cortex cells.Results Compared with sham operation group,model group,exosome group 1 and exosome group 2 exhibited increased hind limb drops in horizontal grid test and climbing scores(P<0.05).No significant difference was found in model group,exosome group 1 and exosome group 2 in these measures(P<0.05).Significant pathology was observed in model group,exosome group 1 and exosome group 2 compared to sham operation group(P<0.05),with significantly reduced damage in exosome group 1 and exosome group 2 compared to model group(P<0.05).Compared with sham operation group,Nissl body count was lower in model group and exosome group 1 and exosome group 2,with a higher count in exosome group 2 compared to exosome group 1(P<0.05).Compared with sham operation group,apoptotic cells were higher in model group and exosome group 1 and exosome group 2,with a significant reduction in exosome group 1 and exosome group 2 compared to model group,and the lowest in exosome group 2(P<0.05).Conclusions hUC-MSCs-Exos can improve the neuronal motor function,promote neuron repair and inhibit apoptosis in HIBD mice.Intranasal administration of hUC-MSCs-Exos is more effective than intraperitoneal administration for reducing neuronal apoptosis in HIBP neonatal mice,offering a convenient and rapid method suitable for clinical application.

Objective To comparatively analyze the clinical characteristics of primary bilateral macronodular adrenal hyperplasia(PBMAH)and adrenal cortisol-producing Adenoma(CPA),and enhance the understanding of two diseases.Methods The clinical data of 85 PBMAH patients(PBMAH group)and 195 CPA patients(CPA group)diagnosed at Department of Endocrinology,the First Medical Center of Chinese PLA General Hospital,from September 2014 to August 2024 were retrospectively analyzed.The demographic characteristics,comorbidities,biochemical indicators,adrenocorticotropic hormone-cortisol(ACTH-F)levels,and adrenal imaging features and treatment conditions were compared between the two groups.Results(1)General characteristics:Compared with CPA group,PBMAH group had older age at diagnosis and a higher proportion of male patients.(2)Clinical characteristics:Compared with CPA group,PBMAH group had a longer disease duration,a higher proportion of subclinical Cushing's syndrome(CS),and a higher proportion of hypertension,impaired glucose tolerance/diabetes,bone mass reduction or osteoporosis,with higher serum potassium levels,and the differences were statistically significant(P<0.01).(3)Hormone levels:Both PBMAH and CPA groups showed ACTH-F rhythm disorder,significantly increased cortisol levels and suppressed ACTH.Compared with PBMAH group,CPA group had stronger autonomous cortisol secretion ability,manifested by increased midnight serum cortisol(F0:00),16:00 serum cortisol(F16:00),24-hour urinary free cortisol(24 h UFC)levels and lower 8:00 serum ACTH(ACTH8:00)and 16:00 serum ACTH(ACTH16:00)(P<0.01).After low-dose dexamethasone suppression test(LDDST),CPA group showed lower suppression rates of ACTH and cortisol,and higher proportions of paradoxical elevation in serum cortisol and 24 h UFC compared with PBMAH(P<0.01).Conclusions PBMAH has a longer disease course and higher proportions of comorbid metabolic disorders than CPA,mostly manifested as subclinical Cushing's syndrome.CPA has stronger autonomous cortisol secretion ability,with cortisol less likely to be suppressed after LDDST and more obvious paradoxical elevation of cortisol and 24 h UFC.

Objective The study aims to investigate the impact of microRNA-874-3p(miR-874-3p)regulation of plakophilin 3(PKP3)on the malignant biological behavior of lung adenocarcinoma cells and its underlying mechanism.Methods Immunohistochemistry and immunocytochemistry were used to detect the expression of PKP3 in lung adenocarcinoma tissue microarray and lung adenocarcinoma cell line A549 cells respectively,and the relationship between PKP3 and clinicopathological features of lung adenocarcinoma patients was analyzed.Select lung adenocarcinoma cell line A549,the experiment was divided into A549 cell group(blank control group),miR-NC group(transfected with miR-NC)and miR-mimics group(transfected with miR-874-3p mimics),sh-NC group(control group transfected with PKP3 silencing plasmid),sh-PKP3 group(transfected with PKP3 silencing plasmid),miR+pcDNA-PKP3 group(transfected with miR-874-3P mimics+pcDNA-PKP3,rescue group)and miR+pcDNA-NC group(transfected with miR-874-3p mimics+pcDNA-NC).The proliferation,invasion,migration and apoptosis of cells in each group were detected.ENCORI database was used to predict the upstream gene of PKP3,and dual luciferase assay was used to detect the targeting relationship between miR-874-3p and PKP3.MAPK/mTOR pathway-related proteins were detected by Western blotting.Results The expression of PKP3 in lung adenocarcinoma tissue was significantly higher than that in adjacent tissues.The high expression of PKP3 was related to clinical stage,tumor size,and lymph node metastasis(P＜0.05).Compared with the human normal lung epithelial cells(BEAS-2B),the expression of PKP3 in A549 cells increased significantly,and the expression of miR-874-3p decreased(P＜0.05).Overexpression of miR-874-3p decreased the PKP3 expression level(P＜0.05).Compared with the control group,both overexpression of miR-874-3p and silenced PKP3 inhibited the cloning and invasion ability of A549 cells,caused cell cycle arrest,and decreased the expression levels of cyclin dependent kinase 4(CDK4),cyclin D1,cyclin E1 proteins in A549 cells(P＜0.05).The expressions of Bax protein and Caspase-3 protein were up-regulated(P＜0.05),and apoptosis increased.Overexpression of PKP3 could reverse the biological behavior of overexpression of miR-874-3p.Overexpression of miR-874-3p and silencing of PKP3 significantly decreased the expressions of P38 MAPK and mTOR phosphorylated proteins.Conclusion MiR-874-3p can negatively regulate PKP3 expression and inhibit the malignant biological behavior of A549 cells through MAPK/mTOR pathway.