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.

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

Objective To introduce a partially nested design based on the characteristics of TCM in treating the same disease with different treatments and syndrome differentiation and treatment.Methods Partially nested design was used for standardized treatment of complex interventions.The TCM group was divided into multiple subsets according to"syndrome type-treatment method-prescription"(with nested structure),while the control group was treated with standardized Western medicine(without nested structure);taking a case study of"different treatments for the same disease"data for ulcerative colitis,this design type was applied and analyzed using a multi-level model.Results The partially nested design was consistent with the feature of TCM of"different treatments for the same disease"and met the methodological requirements for evidence-based evaluation.Multilevel models allowed analyses with this type of data.Conclusion The use of partially nested design enables the evaluation of the comprehensive effectiveness of"different treatments for the same disease",which can provide a methodological reference for the assessment of clinical effectiveness of TCM.

Objective:To investigate the indications and effects of arthroscopic all-inside reconstruction in the treatment of isolated posterior cruciate ligament (PCL) injury.Methods:A retrospective analysis was performed on 47 patients with isolated PCL injury, who underwent arthroscopic all-inside reconstruction in the Third Medical Center of the PLA General Hospital from January 2016 to January 2020. There were 39 males and 8 females, aged 27.14±7.70 years old (range 16-40 years old). The preoperative kneeling-position stress X-ray showed that the degree of tibial posterior displacement was 8-10 mm, which was a complete and isolated Grade II PCL injury. The tibial and femoral tunnels were created through posterior-medial, anteromedial, and anterolateral portals, while the lateral portal to the medial femoral condyle was enlarged to position the tibial tunnel and protect the anterior cruciate ligament. The autologous graft tendon was pulled through the femoral and tibial tunnels secured with an adjustable loop plate. The efficacy was evaluated by evaluating and comparing preoperative and postoperative Lachman test, posterior drawer test, knee range of motion and relaxation, pain visual analogue scale (VAS) and Lysholm score.Results:43 patients were followed up for 35.21±3.88 months (range 12-40 months). The symptoms of knee instability all improved after surgery. At the follow-up of 1 year after surgery, 41 (95%) and 40 (93%) patients showed normal or I-degree laxity in Lachman test and posterior drawer test, respectively. The active range of motion and passive flexion of the knee joint were increased to 90°-110° and 110°-130°, respectively. The Lysholm score was 86.44±4.08 at the first year of follow-up and 90.12±3.33 at the last follow-up with significant difference compared with pre-operations ( P<0.05). The VAS score was 2.07±0.94 at the first year of follow-up and 1.28±0.83 at the last follow-up with significant difference compared with pre-operations ( P<0.05). The Lysholm score and VAS were 90.12±3.33 and 1.28±0.83, which were significantly improved compared to 1-year-follow-up ( P<0.05). Conclusion:Routine kneeling stress X-rays can evaluate the degree of tibial posterior displacement in isolated PCL injuries. With tibial posterior displacement equal to or greater than 10 mm, surgical reconstruction was required. All-inside reconstruction of isolated PCL injury was a safe and minimally invasive surgery to improve symptoms and restore knee functions.

BACKGROUND:The lower cervical vertebral pedicle is the main stress site of the posterior column of the spine,which is of great significance for the maintenance of the stability of the human center of gravity and the reduction of shock.At present,there are few reports on the characteristics of the internal bone trabeculae,and the characteristics of the joint site of the vertebral pedicle with the articular process and the vertebral body.It is urgent to understand the fine anatomical structure of the vertebral pedicle and the relationship and function of each part. OBJECTIVE:To observe the microanatomical morphology of the vertebral pedicle by Micro-CT scanning of cervical vertebra specimens,and to measure and analyze the microstructure and morphometric parameters of the bone trabecula in the cervical pedicle under normal conditions to evaluate the safety performance of the cervical spine. METHODS:Micro-CT scanning was performed on 31 sets of cervical vertebrae C3-C7.By checking and reconstructing the areas of interest in the bone trabecular within the vertebral pedicle,the morphological characteristics and distribution direction of the bone trabecular within the cervical pedicle were observed,and the bone microstructure parameters were detected,and the differences in the bone microstructure of the C3-C7 vertebral pedicle were analyzed and compared. RESULTS AND CONCLUSION:(1)The Micro-CT images showed that the honeycomb bone trabeculae of the pedicle of the lower cervical spine presented a complex network of microstructures.The trabeculae near the cortical bone were lamellar and relatively compact,extending forward toward the vertebral body and backward toward the articular process lamina.Abatoid bone trabeculae extended into the medullary cavity and transformed into a network structure,and then into rod-shaped bone trabeculae.The rod-shaped bone trabeculae were sparsely distributed in the medullary cavity.(2)Statistical results of morphological parameters of bone trabeculae showed that bone volume fraction values in C4 and C5 were higher than that in C7(P＜0.05).The bone surface/bone volume value in C7 was higher than that in C3,C4 and C6(P＜0.05).The bone surface density of bone trabeculae in C7 was higher than that in C3,C4,C5 and C6(P＜0.05).Trabecular thickness in C7 was higher than that in C3,C4 and C5(P＜0.05).Bone surface/bone volume and bone surface density of the left pedicle bone trabecular were greater than those on the right side(P＜0.05).(3)The microstructural changes of C3-C7 were summarized,in which the load capacity and stress of the C7 pedicle were poor,and the risk of injury was high in this area.

BACKGROUND:Myocardial patches are used as an effective way to repair damaged myocardium,and there is controversy over which cells to use to make myocardial patches and how to maximize the therapeutic effect of myocardial patches in vivo. OBJECTIVE:To find out the best way to make myocardial patches by overviewing the cellular sources of myocardial patches and strategies for perfecting them. METHODS:The first author searched PubMed and Web of Science databases by using"cell sheet,cell patch,cardiomyocytes,cardiac progenitor cells,fibroblasts,embryonic stem cell,mesenchymal stem cells"as English search terms,and searched CNKI and Wanfang databases by using"myocardial patch,biological 3D printing,myocardial"as Chinese search terms.After enrollment screening,94 articles were ultimately included in the result analysis. RESULTS AND CONCLUSION:(1)The cellular sources of myocardial patches are mainly divided into three categories:somatic cells,monoenergetic stem cells,and pluripotent stem cells,respectively.There are rich sources of cells for myocardial patches,but not all of them are suitable for making myocardial patches,e.g.,myocardial patches made from fibroblasts and skeletal myoblasts carry a risk of arrhythmogenicity,and mesenchymal stem cells have a short in vivo duration of action and ethical concerns.With the discovery of induced multifunctional stem cells,a reliable source of cells for making myocardial patches is available.(2)There are two methods of making myocardial patches.One is using cell sheet technology.The other is using biological 3D printing technology.Cell sheet technology can preserve the extracellular matrix components intact and can maximally mimic the cell growth ring in vivo.However,it is still difficult to obtain myocardial patches with three-dimensional structure by cell sheet technology.Biologicasl 3D printing technology,however,can be used to obtain myocardial patches with three-dimensional structures through computerized personalized design.(3)The strategies for perfecting myocardial patches mainly include:making myocardial patches after co-cultivation of multiple cells,improving the ink formulation and scaffold composition in biological 3D printing technology,improving the therapeutic effect of myocardial patches,suppressing immune rejection after transplantation,and perfecting the differentiation and cultivation protocols of stem cells.(4)There is no optimal cell source or method for making myocardial patches,and myocardial patches obtained from a particular cell or technique alone often do not achieve the desired therapeutic effect.Therefore,researchers need to choose the appropriate strategy for making myocardial patches based on the desired therapeutic effect before making them.