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.

This study investigates the effect and underlying mechanism of Guizhi Tongluo Tablets(GZTL) in treating atherosclerosis(AS) in a mouse model. Apolipoprotein E-knockout(ApoE~(-/-)) mice were randomly assigned to the following groups: model, high-, medium-, and low-dose GZTL, and atorvastatin(ATV), and age-matched C57BL/6J mice were selected as the control group. ApoE~(-/-) mice in other groups except the control group were fed with a high-fat diet for the modeling of AS and administrated with corresponding drugs via gavage for 8 weeks. General conditions, signs of blood stasis, and body mass of mice were monitored. Aortic plaques and their stability were assessed by hematoxylin-eosin, Masson, and oil red O staining. Serum levels of total cholesterol(TC), triglycerides(TG), and low-density lipoprotein cholesterol(LDL-C) were measured by biochemical assays, and those of interleukin-1β(IL-1β), tumor necrosis factor-α(TNF-α), and interleukin-6(IL-6) were determined via enzyme-linked immunosorbent assay. Apoptosis was assessed by terminal deoxynucleotidyl transferase dUTP nick end labeling(TUNEL). Single-cell RNA sequencing(scRNA-seq) was employed to analyze the differential expression of CD72hi macrophages(CD72hi-Mφ) in the aortas of AS patients and mice. The immunofluorescence assay was employed to visualize CD72hi-Mφ expression in mouse aortic plaques, and real-time fluorescence quantitative PCR was utilized to determine the mRNA levels of IL-1β, TNF-α, and IL-6 in the aorta. The results demonstrated that compared with the control group, the model group exhibited significant increases in body mass, aortic plaque area proportion, necrotic core area proportion, and lipid deposition, a notable decrease in collagen fiber content, and an increase in apoptosis. Additionally, the model group showcased elevated serum levels of TC, TG, LDL-C, IL-1β, TNF-α, and IL-6, alongside marked upregulations in the mRNA levels of IL-1β, TNF-α, and IL-6 in the aorta. In comparison with the model group, the GZTL groups and the ATV group showed a reduction in body mass, and the medium-and high-dose GZTL groups and the ATV group demonstrated reductions in aortic plaque area proportion, necrotic core area proportion, and lipid deposition, an increase in collagen fiber content, and a decrease in apoptosis. Furthermore, the treatment goups showcased lowered serum levels of TC, TG, LDL-C, IL-1β, TNF-α, and IL-6. The data of scRNA-seq revealed significantly elevated CD72hi-Mφ signaling in carotid plaques of AS patients compared with that in the normal arterial tissue. Animal experiments confirmed that CD72hi-Mφ expression, along with several pro-inflammatory cytokines, was significantly upregulated in the aortas of AS mice, which were downregulated by GZTL treatment. In conclusion, GZTL may alleviate AS by inhibiting CD72hi-Mφ activity.
Animals ; Drugs, Chinese Herbal/administration & dosage* ; Atherosclerosis/immunology* ; Mice ; Mice, Inbred C57BL ; Macrophages/immunology* ; Male ; Humans ; Apolipoproteins E/genetics* ; Tablets ; Tumor Necrosis Factor-alpha/genetics* ; Apoptosis/drug effects* ; Interleukin-1beta/genetics* ; Interleukin-6/genetics* ; Disease Models, Animal ; Mice, Knockout

This study aims to explore the mechanism of lung and gut protection by Tanreqing Capsules on the mice infected with influenza virus based on "the lung-gut axis". A total of 110 C57BL/6J mice were randomized into control group, model group, oseltamivir group, and low-and high-dose Tanreqing Capsules groups. Ten mice in each group underwent body weight protection experiments, and the remaining 12 mice underwent experiments for mechanism exploration. Mice were infected with influenza virus A/Puerto Rico/08/1934(PR8) via nasal inhalation for the modeling. The lung tissue was collected on day 3 after gavage, and the lung tissue, colon tissue, and feces were collected on day 7 after gavage for subsequent testing. The results showed that Tanreqing Capsules alleviated the body weight reduction and increased the survival rate caused by PR8 infection. Compared with model group, Tanreqing Capsules can alleviate the lung injury by reducing the lung index, alleviating inflammation and edema in the lung tissue, down-regulating viral gene expression at the late stage of infection, reducing the percentage of neutrophils, and increasing the percentage of T cells. Tanreqing Capsules relieved the gut injury by restoring the colon length, increasing intestinal lumen mucin secretion, alleviating intestinal inflammation, and reducing goblet cell destruction. The gut microbiota analysis showed that Tanreqing Capsules increased species diversity compared with model group. At the phylum level, Tanreqing Capsules significantly increased the abundance of Firmicutes and Actinobacteria, while reducing the abundance of Bacteroidota and Proteobacteria to maintain gut microbiota balance. At the genus level, Tanreqing Capsules significantly increased the abundance of unclassified＿f＿Lachnospiraceae while reducing the abundance of Bacteroides, Eubacterium, and Phocaeicola to maintain gut microbiota balance. In conclusion, Tanreqing Capsules can alleviate mouse lung and gut injury caused by influenza virus infection and restore the balance of gut microbiota. Treating influenza from the lung and gut can provide new ideas for clinical practice.
Animals ; Drugs, Chinese Herbal/administration & dosage* ; Mice ; Lung/metabolism* ; Mice, Inbred C57BL ; Capsules ; Orthomyxoviridae Infections/virology* ; Gastrointestinal Microbiome/drug effects* ; Male ; Humans ; Female ; Influenza A virus/physiology* ; Influenza, Human/virology*

This study aims to systematically review and evaluate the quality of clinical research on the treatment of adenomyosis(AM) with traditional Chinese medicine(TCM) in recent ten years, using evidence graphs. Computer searches were conducted on eight Chinese and English databases, commonly used guideline databases, and guideline-related websites, covering the period from January 1, 2014, to October 1, 2024. Two researchers independently screened, extracted information, and evaluated the quality of the evidence. The distribution and quality of the clinical research evidence were presented using both text and charts. A total of 565 articles were included in the study, comprising 523 intervention studies, 23 observational studies, 18 systematic reviews/Meta-analysis, and 1 guideline. The overall publication volume has shown a downward trend in past two years. The sample sizes of the intervention and observational studies primarily focused on 60 to 120 cases. The intervention schemes mainly involved multi-therapy combinations, including 33 classic prescriptions and 25 Chinese patent medicines. Among these, 48 studies related to 17 classic prescriptions and 45 studies related to 10 types of Chinese patent medicines involved TCM syndrome types. Randomized controlled trial(RCT) tended to focus on overall clinical efficacy and the degree of dysmenorrhea as key outcome measures. Methodological quality issues were found in 97 RCTs related to TCM decoctions and 131 RCTs related to Chinese patent medicines, primarily involving unclear explanations of some information. The AMSTAR scores for the 18 systematic reviews/Meta-analysis ranged from 1 to 8 points, with 16 studies suggesting "evidence of potential therapeutic efficacy". The recommended level for the one included guideline was B-level. TCM shows significant advantages in treating AM. Future clinical research should further standardize study designs, reference relevant reporting guidelines, improve the quality of clinical research, generate higher-level evidence-based results, and promote the high-quality development of clinical research on TCM for treating AM.
Humans ; Adenomyosis/drug therapy* ; Drugs, Chinese Herbal/therapeutic use* ; Female ; Medicine, Chinese Traditional ; Randomized Controlled Trials as Topic

OBJECTIVES: To study the clinical characteristics of pediatric Behçet syndrome (BS). METHODS: A retrospective review was conducted on the medical records of children hospitalized in the Department of Pediatrics at the Second Hospital of Hebei Medical University between December 2014 and December 2024 who met diagnostic criteria for BS. RESULTS: Among 45 children with BS, 26 (58%) were male. Oral aphthous ulcers were the most common manifestation (43/45, 96%), followed by genital ulcers (23/45, 51%) and gastrointestinal involvement (18/45, 40%). Genital ulcers were more frequent in girls, whereas ocular involvement was more common in boys (P<0.05). The pathergy test was positive in 10 (22%), and HLA-B51 was positive in 13 (29%). Fecal calprotectin (FC) was elevated in 16 (36%); gastrointestinal involvement was more frequent in children with elevated FC than in those with normal FC (P<0.05). According to the respective criteria, 17 (38%) patients met the International Study Group criteria (1990), 33 (73%) met the International Criteria for Behçet Disease (2014), and 13 (29%) met the Pediatric Behçet Disease criteria (2015). CONCLUSIONS Pediatric BS shows marked clinical heterogeneity. HLA-B51 is associated with disease susceptibility.
Humans ; Behcet Syndrome/genetics* ; Male ; Female ; Child ; Retrospective Studies ; Adolescent ; Child, Preschool ; Leukocyte L1 Antigen Complex/analysis* ; HLA-B51 Antigen

OBJECTIVE: The aim of this study is to investigate the independent risk factors of benign prostatic hyperplasia (BPH) complicated with bladder stones, and construct a nomogram prediction model for clinical progression of bladder stones in patients with BPH. METHODS: The clinical data of 368 BPH patients who underwent transurethral resection of the prostate in the Second Affiliated Hospital of Zhengzhou University from January 2018 to January 2021 were retrospectively analyzed. Patients with BPH were divided into group 1 (with bladder stones, n=94) and group 2 (without bladder stones, n=274). Univariate and multivariate logistic regression analyses were performed to determine the independent risk factors of bladder stones in patients with BPH. A nomogram model was developed, and the areas under the ROC curve and calibration curve were calculated to assess the accuracy of clinical application. RESULTS: Logistic analysis showed that age (HR:1.075,95%CI:1.032 to 1.120), hypertension (HR:2.801,95%CI:1.520 to 5.161), blood uric acid (HR:1.006,95%CI:1.002 to 1.010), intravesical prostatic protrusion (HR:1.189,95%CI1.119 to 1.264）, prostatic urethral angel（HR:1.127,95%CI:1.078to 1.178）were independent risk factors for bladder stones in patients with BPH. The discrimination of the nomogram model based on independent risk factors to predict the occurrence of bladder stones in patients with BPH was 0.874. CONCLUSION The nomogram model can predict the risk of bladder stones in BPH patients with good differentiation and calibration, which is a good guide for clinical work on BPH patients with high risk of bladder stones.
Humans ; Male ; Prostatic Hyperplasia/complications* ; Nomograms ; Urinary Bladder Calculi/etiology* ; Retrospective Studies ; Risk Factors ; Aged ; Logistic Models ; Middle Aged ; ROC Curve ; Transurethral Resection of Prostate