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 observe the effect of high-frequency repetitive transcranial magnetic stimulation (rTMS) at different frequencies on cognitive impairment due to high-altitude hypoxia.Methods:Sixty officers and soldiers displaying cognitive impairment in a hypoxic high-altitude environment were randomly divided into 15Hz, 20Hz and 25Hz groups, each of 20. They were given rTMS at those frequencies for 30 days. Before the stimulation and after 15 and 30 days, event-related potentials, latencies of mismatched negativity (MMN) and P300 signals were recorded. The participants′ cognition was also evaluated using the Montreal Cognitive Assessment Scale (MoCA). Correlation between the electrophysiological indexes and the MoCA scores was computed.Results:After 15 days, all had shorter MMN latencies, higher total MoCA scores and better memory scores. The only significant difference among the three groups was in the average memory scores. After 15 days, MMN latency was significantly negatively correlated with the memory scores in all three groups ( r=0.44 to -0.54). Conclusions:rTMS at frequencies above 15Hz can effectively relieve cognitive impairment, especially memory dysfunction, resulting from high-altitude hypoxia.

Objective:To analyze the epidemiological characteristics and influencing factors of single-cigarette use and dual cigarette-cigar use in China.Methods:This study was a cross-sectional study that selected 85 638 urban and rural residents who met the inclusion criteria from the 2018 China Health Literacy Survey as research subjects. An analysis was conducted on 21 849 users of cigarettes and cigars among them. Due to the small number of individuals who exclusively used cigars (247 cases), the research subjects were divided into two categories: exclusive cigarette users and dual users of cigarettes and cigars. The groups were categorized by age (18-34 years, 35-54 years, ≥55 years), gender (male, female), education level (primary school and below, junior high school and high school, university and above) and annual household income (<20 000 yuan, 20 000-<80 000 yuan, ≥80 000 yuan) to compare the tobacco usage rate and conduct subgroup analyses for each subgroup. Multivariate logistic regression analysis was employed, incorporating general demographic characteristic information to explore the influencing factors of exclusive cigarette use and dual use of cigarettes and cigars, respectively.Results:The rate of exclusive cigarette use in our country was 24.3%, while the dual use rate of cigarettes and cigars was 0.9%. The exclusive cigarette use rate and the dual use rate of cigarettes and cigars among males were significantly higher than those among females (48.25% vs 2.48%, and 1.84% vs 0.06%) (both P<0.001). For males, the high-risk factors for exclusive cigarette use included living in urban areas ( OR: 1.37, 95% CI: 1.23-1.54), being Han ethnicity ( OR: 1.73, 95% CI: 1.51-1.98), and having an annual household income ≥20 000 yuan ( OR: 1.54, 95% CI: 1.38-1.82) while having a junior high school education or higher was a protective factor ( OR: 0.68, 95% CI: 0.52-0.90). Age≥35 years ( OR: 3.36, 95% CI: 2.62-4.32) and having a junior high school education or higher ( OR: 1.30, 95% CI: 1.02-1.67) were risk factors for dual use of cigarettes and cigars in males. Among females, living in urban areas ( OR: 1.53, 95% CI: 1.19-1.97) and being Han ethnicity ( OR: 5.96, 95% CI: 4.47-7.96) were risk factors for exclusive cigarette use, while having a university education or higher was a protective factor ( OR: 0.28, 95% CI: 0.18-0.42). However, for female dual use of cigarettes and cigars, no significant effects were observed for any demographic characteristics. Conclusions:The use rate of cigarettes alone in China is significantly higher than that of cigarette-cigar dual use, and the rates of cigarette use alone and cigarette-cigar dual use in men are significantly higher than those in women. Tobacco use is being affected by sociodemographic factors, among which place of residence, ethnicity and education level are the main influencing factors of cigarette use alone, and gender, age and education level are the main influencing factors of cigarette-cigar dual use.

OBJECTIVES: To study the incidence and disease burden of congenital birth defects in children under five in China from 1990 to 2021 and to predict the incidence of congenital birth defects in this population from 2022 to 2036, providing a reference for the prevention of congenital birth defects in children. METHODS: Using the Global Burden of Disease Study 2021 (GBD 2021) database, the incidence and disability-adjusted life years (DALY) were employed to describe the disease burden. The Joinpoint regression model was used to analyze the trends in incidence and DALY rates of congenital birth defects in children under five. A grey prediction model GM(1,1) was applied to fit the trend of incidence rates of congenital birth defects in this age group and to predict the incidence from 2022 to 2036. RESULTS: In 2021, the incidence rate of congenital birth defects among children under five in China was 737.28 per 100 000. Among these, congenital musculoskeletal and limb deformities had the highest incidence rate at 307.15 per 100 000, followed by congenital heart defects (223.53 per 100 000), congenital urinary and genital tract malformations (74.99 per 100 000), and congenital gastrointestinal malformations (62.61 per 100 000). From 1990 to 2021, the incidence rate and DALY rate of congenital birth defects in children under five in China decreased at an average annual rate of 1.73% and 5.42%, respectively. The prediction analysis indicated a decreasing trend in the incidence of congenital birth defects among children under five in China from 2022 to 2036, with the incidence rate dropping from 892.36 per 100 000 in 2022 to 783.35 per 100 000 in 2036. CONCLUSIONS The incidence and disease burden of congenital birth defects in children under five in China showed a significant declining trend from 1990 to 2021. It is predicted that this incidence will continue to decrease until 2036.
Humans ; Congenital Abnormalities/epidemiology* ; China/epidemiology* ; Incidence ; Infant ; Infant, Newborn ; Child, Preschool ; Female ; Male ; Forecasting ; Disability-Adjusted Life Years

Coronavirus disease 2019 (COVID-19) is an acute infectious respiratory disease that has been prevalent since December 2019. Chinese medicine (CM) has demonstrated its unique advantages in the fight against COVID-19 in the areas of disease prevention, improvement of clinical symptoms, and control of disease progression. This review summarized the relevant material components of CM in the treatment of COVID-19 by searching the relevant literature and reports on CM in the treatment of COVID-19 and combining with the physiological and pathological characteristics of the novel coronavirus. On the basis of sorting out experimental methods in vivo and in vitro, the mechanism of herb action was further clarified in terms of inhibiting virus invasion and replication and improving related complications. The aim of the article is to explore the strengths and characteristics of CM in the treatment of COVID-19, and to provide a basis for the research and scientific, standardized treatment of COVID-19 with CM.
Humans ; Drugs, Chinese Herbal/pharmacology* ; COVID-19 Drug Treatment ; SARS-CoV-2/drug effects* ; COVID-19/therapy* ; Medicine, Chinese Traditional/methods* ; Antiviral Agents/pharmacology* ; Animals

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.

Transcranial temporal interference stimulation (tTIS) is a novel non-invasive neuromodulation technique with the potential to precisely target deep brain structures. This study explores the neural and behavioral effects of tTIS on the superior colliculus (SC), a region involved in eye movement control, in mice. Computational modeling revealed that tTIS delivers more focused stimulation to the SC than traditional transcranial alternating current stimulation. In vivo experiments, including Ca²⁺ signal recordings and eye movement tracking, showed that tTIS effectively modulates SC neural activity and induces eye movements. A significant correlation was found between stimulation frequency and saccade frequency, suggesting direct tTIS-induced modulation of SC activity. These results demonstrate the precision of tTIS in targeting deep brain regions and regulating eye movements, highlighting its potential for neuroscientific research and therapeutic applications.
Animals ; Superior Colliculi/physiology* ; Transcranial Direct Current Stimulation/methods* ; Eye Movements/physiology* ; Male ; Mice ; Mice, Inbred C57BL