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.

Sensory conflict impacts postural control, yet its effect on cortico-muscular interaction remains underexplored. We aimed to investigate sensory conflict's influence on the cortico-muscular network and postural stability. We used a rotating platform and virtual reality to present subjects with congruent and incongruent sensory input, recorded EEG (electroencephalogram) and EMG (electromyogram) data, and constructed a directed connectivity network. The results suggest that, compared to sensory congruence, during sensory conflict: (1) connectivity among the sensorimotor, visual, and posterior parietal cortex generally decreases, (2) cortical control over the muscles is weakened, (3) feedback from muscles to the cortex is strengthened, and (4) the range of body sway increases and its complexity decreases. These results underline the intricate effects of sensory conflict on cortico-muscular networks. During the sensory conflict, the brain adaptively decreases the integration of conflicting information. Without this integrated information, cortical control over muscles may be lessened, whereas the muscle feedback may be enhanced in compensation.
Humans ; Muscle, Skeletal ; Electromyography/methods* ; Electroencephalography/methods* ; Brain ; Brain Mapping

Aim To investigate the role of metabolites of eicosapentaenoic acid (EPA) in promoting the transdifferentiation of pancreatic α cells to β cells. Methods Male C57BL/6J mice were injected intraperitoneally with 60 mg/kg streptozocin (STZ) for five consecutive days to establish a type 1 diabetes (T1DM) mouse model. After two weeks, they were randomly divided into model groups and 97% EPA diet intervention group, 75% fish oil (50% EPA +25% DHA) diet intervention group, and random blood glucose was detected every week; after the model expired, the regeneration of pancreatic β cells in mouse pancreas was observed by immunofluorescence staining. The islets of mice (obtained by crossing GCG

The gene GeDRP1E encoding dynamin-related protein 1E in Gastrodia elata was cloned by specific primers which were designed based on the transcriptome data of G. elata. Bioinformatics analysis on GeDRP1E gene was carried out by using ExPASy, ClustalW, MEGA, etc. Positive transgenic Arabidopsis plant and potato minituber were obtained with the genetic transformation system of Arabidopsis and potato. The plant height and seed setting rate of transgenic Arabidopsis, and agronomic characters, such as size, weight and starch content of potato minituber of transgenic potato were tested and analyzed. And GeDRP1E gene function was preliminarily investigated. The results showed that the open reading frame of GeDRP1E gene was 1 899 bp in length and 632 amino acids residues were encoded, with a relative molecular weight of 69.90 kDa and a molecular formula of C₃₀₇₉H₄₉₇₃N₈₈₃O₉₃₃S₁₉. It was predicted that the theoretical isoelectric point was 7.27, the instability coefficient was 43.34, and the average hydrophilicity index was -0.259, which was indicative of an unstable hydrophilic protein. GeDRP1E has no transmembrane structure and signal peptide, and was localized in the cytoplasm. The phylogenetic tree showed that GeDRP1E was highly homologous with DRP1E proteins of other plant species, among which GeDRP1E had the highest homology with DcDRP1E (XP_020689662.1) in Dendrobium candidum, reaching 90.05%. GeDRP1E plant expression vector pCambia1300-35Spro-GeDRP1E was constructed by double digests, and Arabidopsis complementary mutant and potato overexpression strain of GeDRP1E gene were obtained by Agrobacterium-mediated gene transformation. Compared with the Arabidopsis AtDRP1E mutant, the height and seed setting rate of the GeDRP1E complementation mutant were rescued. The minituber of GeDRP1E overexpression potato had larger size, heavier weight and higher starch content, comparing to wild-type potato. It was preliminarily induced that GeDRP1E was involved in mitochondrial morphology regulation, which related to the growth and development of Arabidopsis plants and potato miniature. The research results laid a foundation for further elucidating the molecular mechanisms underlying the growth and development of G. elata tuber development.

Objective:To investigate the safety and therapeutic effect of split liver transplantation (SLT) in clinical application.Methods:This is a retrospective case-series study. The clinical data of 203 consecutive SLT, 79 living donor liver transplantation (LDLT) and 1 298 whole liver transplantation (WLT) performed at the Third Affiliated Hospital of Sun Yat-sen University from July 2014 to July 2023 were retrospectively analyzed. Two hundred and three SLT liver grafts were obtained from 109 donors. One hundred and twenty-seven grafts were generated by in vitro splitting and 76 grafts were generated by in vivo splitting. There were 90 adult recipients and 113 pediatric recipients. According to time, SLT patients were divided into two groups: the early SLT group (40 cases, from July 2014 to December 2017) and the mature SLT technology group (163 cases, from January 2018 to July 2023). The survival of each group was analyzed and the main factors affecting the survival rate of SLT were analyzed. The Kaplan-Meier method and Log-rank test were used for survival analysis.Results:The cumulative survival rates at 1-, 3-, and 5-year were 74.58%, 71.47%, and 71.47% in the early SLT group, and 88.03%, 87.23%, and 87.23% in the mature SLT group, respectively. Survival rates in the mature SLT group were significantly higher than those in the early SLT group ( χ2=5.560, P=0.018). The cumulative survival rates at 1-, 3- and 5-year were 93.41%, 93.41%, 89.95% in the LDLT group and 87.38%, 81.98%, 77.04% in the WLT group, respectively. There was no significant difference among the mature SLT group, the LDLT group and the WLT group ( χ2=4.016, P=0.134). Abdominal hemorrhage, infection, primary liver graft nonfunction,and portal vein thrombosis were the main causes of early postoperative death. Conclusion:SLT can achieve results comparable to those of WLT and LDLT in mature technology liver transplant centers, but it needs to go through a certain time learning curve.

Objective To understand the respiratory protection competency of staff in hospitals.Methods Staff from six hospitals of different levels and characteristics in Beijing were selected,including doctors,nurses,medical technicians,and servicers,to conduct knowledge assessment on respiratory protection competency.According to exposure risks of respiratory infectious diseases,based on actual cases and daily work scenarios,content of respira-tory protection competency assessment was designed from three aspects:identification of respiratory infectious di-seases,transmission routes and corresponding protection requirements,as well as correct selection and use of masks.The assessment included 6,6,and 8 knowledge points respectively,with 20 knowledge points in total,all of which were choice questions.For multiple-choice questions,full marks,partial marks,and no mark were given respective-ly if all options were correct,partial options were correct and without incorrect options,and partial options were correct but with incorrect options.Difficulty and discrimination analyses on question of each knowledge point was conducted based on classical test theory.Results The respiratory protection competency knowledge assessment for 326 staff members at different risk levels in 6 hospitals showed that concerning the 20 knowledge points,more than 60％participants got full marks for 6 points,while the proportion of full marks for other questions was relatively low.Less than 10％participants got full marks for the following 5 knowledge points:types of airborne diseases,types of droplet-borne diseases,conventional measures for the prevention and control of healthcare-associated infec-tion with respiratory infectious diseases,indications for wearing respirators,and indications for wearing medical protective masks.Among the 20 knowledge questions,5,1,and 14 questions were relatively easy,medium,and difficult,respectively;6,1,4,and 9 questions were with discrimination levels of ≥0.4,0.30-0.39,0.20-0.29,and ≤0.19,respectively.Conclusion There is still much room for hospital staff to improve their respiratory protection competency,especially in the recognition of diseases with different transmission routes and the indications for wearing different types of masks.