ObjectiveTo explore the mechanism of action of Paeoniae Radix Rubra and Aconiti Lateralis Radix Praeparata （CSFZ） in the treatment of acute-on-chronic liver failure （ACLF） through network pharmacology， molecular docking， and animal experiments. MethodsNetwork pharmacology was used to identify potential targets and related signaling pathways for the treatment of ACLF with CSFZ. Molecular docking was used to examine the binding activity of the core components with corresponding key targets. An ACLF rat model was established by subcutaneous and tail vein injections of bovine serum albumin combined with lipopolysaccharide （LPS） + D-galactosamine （D-GalN） intraperitoneal injection. A normal control group （NC）， a model group， a CSFZ group （CSFZ， 5.85 g·kg^-1）， and a hepatocyte growth-promoting granule group （HGFG， 4.05 g·kg^-1） were set up in this study. Pathological changes in rat liver tissue were observed using hematoxylin and eosin （HE） and Masson staining. Enzyme-linked immunosorbent assay （ELISA） was used to detect the expression levels of interleukin-6 （IL-6）， B-cell lymphoma-2 （Bcl-2）， Caspase-3， and albumin （ALB）. Real-time quantitative polymerase chain reaction （Real-time PCR） and Western blot were used to measure the mRNA and protein expression levels of phosphoinositide 3-kinase （PI3K）， protein kinase B （Akt）， phosphorylated PI3K （p-PI3K）， and phosphorylated Akt （p-Akt）. ResultsNetwork pharmacology screening identified 49 active ingredients of CSFZ， 103 action targets， and 3 317 targets related to ACLF. Among these， 74 targets overlapped with CSFZ drug targets. Key nodes in the protein-protein interaction （PPI） network included Akt1， tumor necrosis factor （TNF）， IL-6， Bcl-2， and Caspase-3. Gene Ontology （GO） functional analysis and Kyoto Encyclopedia of Genes and Genomes （KEGG） enrichment analysis identified multiple signaling pathways， with the PI3K/Akt signaling pathway being the most frequent. Molecular docking showed that the core components of the drug exhibited good binding activity with the corresponding key targets. Animal experiments confirmed that CSFZ significantly improved liver tissue pathological damage in ACLF rats， reduced the release of inflammatory factors and liver cell apoptosis， and upregulated the expression levels of the PI3K/Akt signaling pathway. ConclusionThrough network pharmacology， molecular docking， and in vivo experiments， this study confirms the effect of CSFZ in reducing liver cell inflammatory damage and inhibiting liver cell apoptosis. The specific mechanism may be related to its involvement in regulating the PI3K/Akt signaling pathway.

ObjectiveTo elucidate the critical role of rehabilitation medical records (including electronic records) in rehabilitation medicine's clinical practice and management, comprehensively analyzed the structure, core content and data standards of rehabilitation medical records, to develop a standardized medical record data architecture and core dataset suitable for rehabilitation medicine and to explore the application of rehabilitation data in performance evaluation and payment. MethodsBased on the regulatory documents Basic Specifications for Medical Record Writing and Basic Specifications for Electronic Medical Records (Trial) issued by National Health Commission of China, and referencing the World Health Organization (WHO) Family of International Classifications (WHO-FICs) classifications, International Classification of Diseases (ICD-10/ICD-11), International Classification of Functioning, Disability and Health (ICF), and International Classification of Health Interventions (ICHI Beta-3), this study constructed the data architecture, core content and data standards for rehabilitation medical records. Furthermore, it explored the application of rehabilitation record summary sheets (home page) data in rehabilitation medical statistics and payment methods, including Diagnosis-related Groups (DRG), Diagnosis-Intervention Packet (DIP) and Case Mix Index. ResultsThis study proposed a systematic standard framework for rehabilitation medical records, covering key components such as patient demographics, rehabilitation diagnosis, functional assessment, rehabilitation treatment prescriptions, progress evaluations and discharge summaries. The research analyzed the systematic application methods and data standards of ICD-10/ICD-11, ICF and ICHI Beta-3 in the fields of medical record terminology, coding and assessment. Constructing a standardized data structure and data standards for rehabilitation medical records can significantly improve the quality of data reporting based on the medical record summary sheet, thereby enhancing the quality control of rehabilitation services, effectively supporting the optimization of rehabilitation medical insurance payment mechanisms, and contributing to the establishment of rehabilitation medical performance evaluation and payment based on DRG and DIP. ConclusionStructured rehabilitation records and data standardization are crucial tools for quality control in rehabilitation. Systematically applying the three reference classifications of the WHO-FICs, and aligning with national medical record and electronic health record specifications, facilitate the development of a standardized rehabilitation record architecture and core dataset. Standardizing rehabilitation care pathways based on the ICF methodology, and developing ICF- and ICD-11-based rehabilitation assessment tools, auxiliary diagnostic and therapeutic systems, and supporting terminology and coding systems, can effectively enhance the quality of rehabilitation records and enable interoperability and sharing of rehabilitation data with other medical data, ultimately improving the quality and safety of rehabilitation services.

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 explore the relationship between related factors of non-suicidal self-injury behavior (NSSI) among middle school students in Guizhou Province, so as to provide the evidence for preventing high risk behaviors in adolescents. Methods: A stratified cluster random sampling method was used to select 1 034 junior and senior middle school students from Zunyi City, Qiannan Prefecture and Tongren City in Guizhou Province from April to October in 2023. Questionnaire survey was conducted to collect information including Adolescent Self injury Scale and Family Assessment Device. The R 4.4.1 software was employed for network analysis visualization, centrality indicators, and result stability assessment. Results: The detection rate of NSSI behavior among middle school students in Guizhou province was 29.6%, with a detection rate of 25.5% for boys and 33.1% for girls, showing a statistically significant difference ( χ 2=7.07, P <0.05). There were statistically significant differences in scores of emotional communication, egoism, family rules, positive communication, problem solving, expression of positive emotions and management of negative emotions self-efficacy, and bullying victimization in various dimensions between middle school students with and without NSSI ( Z =-13.66 to -7.05, P <0.01). NSSI among middle school students was positively correlated with social/relational bullying, depression and anxiety, and there were relatively close connections in the network ( r =0.35, 0.43, 0.42, P <0.01). Centrality indicators showed that the highest in strength and closeness centrality were stress ( Z =1.29, 1.58), the highest in betweenness centrality was for emotional communication ( Z =1.91), and the highest in expected influence index was for physical bullying ( Z =1.44)( P < 0.05). Conclusions Stress, emotional communication and physical bullying have significant impacts in the network of factors related to NSSI. Social/relational bullying, depression and anxiety have strong direct correlations with NSSI behavior among middle school students.

Objective To compare the performance and efficacy of prognostic models constructed by different machine learning algorithms in predicting the survival period of lung transplantation (LTx) recipients. Methods Data from 483 recipients who underwent LTx were retrospectively collected. All recipients were divided into a training set and a validation set at a ratio of 7:3. The 24 collected variables were screened based on variable importance (VIMP). Prognostic models were constructed using random survival forest (RSF) and extreme gradient boosting tree (XGBoost). The performance of the models was evaluated using the integrated area under the curve (iAUC) and time-dependent area under the curve (tAUC). Results There were no significant statistical differences in the variables between the training set and the validation set. The top 15 variables ranked by VIMP were used for modeling and the length of stay in the intensive care unit (ICU) was determined as the most important factor. Compared with the XGBoost model, the RSF model demonstrated better performance in predicting the survival period of recipients (iAUC 0.773 vs. 0.723). The RSF model also showed better performance in predicting the 6-month survival period (tAUC _{6 months} 0.884 vs. 0.809, P = 0.009) and 1-year survival period (tAUC _{1 year} 0.896 vs. 0.825, P = 0.013) of recipients. Based on the prediction cut-off values of the two algorithms, LTx recipients were divided into high-risk and low-risk groups. The survival analysis results of both models showed that the survival rate of recipients in the high-risk group was significantly lower than that in the low-risk group (P<0.001). Conclusions Compared with XGBoost, the machine learning prognostic model developed based on the RSF algorithm may preferably predict the survival period of LTx recipients.

ObjectiveBased on ultra performance liquid chromatography-quadrupole-time-of-flight mass spectrometry（UPLC-Q-TOF-MS）， network pharmacology， molecular docking and cell experiments， the active ingredients， possible targets and molecular mechanisms of Baoxin granules（BXG） regulating ferroptosis in the treatment of heart failure（HF） were explored. MethodsBXG intestinal absorption fluid was prepared by everted gut sac and the chemical composition contained therein were identified by UPLC-Q-TOF-MS. According to the obtained components， the potential targets of BXG were predicted， and the HF-related targets and related genes of ferroptosis were retrieved at the same time， and the intersecting targets were obtained by Venn diagram. In addition， the protein-protein interaction（PPI） network and the component-target network were constructed， and the core components and core targets were obtained by topological analysis. Then Gene Ontology（GO） function and Kyoto Encyclopedia of Genes and Genomes（KEGG） enrichment analysis were performed on the core targets， and molecular docking validation of the key targets and main components was carried out by AutoDockTools 1.5.7. H9c2 cells were used to establish a oxygen-glucose deprivation model， and the protective effect of BXG on cells was investigated by detecting cell viability， cell survival rate and reactive oxygen species（ROS） level. The protein expression levels of signal transducer and activator of transcription 3（STAT3）， phosphorylation（p）-STAT3 and glutathione peroxidase 4（GPX4） were detected by Western blot to clarify the regulatory effect of BXG on ferroptosis. ResultsA total of 61 chemical components in BXG intestinal absorption fluid were identified， and network pharmacology obtained 27 potential targets of BXG for the treatment of HF， as well as 139 signaling pathways. BXG may act on core targets such as STAT3， tumor protein p53（TP53）， epidermal growth factor receptor（EGFR）， JUN and prostaglandin-endoperoxide synthase 2（PTGS2） through core components such as glabrolide and limonin， which in turn intervene in lipid and atherosclerosis， phosphatidylinositol 3-kinase/protein kinase B（PI3K/Akt）， endocrine resistance and other signaling pathways to exert therapeutic effects on HF. Molecular docking showed that the docking results of multiple groups of targets and compounds were good. In vitro cell experiments showed that compared with the blank group， the cell viability and survival rate of the model group were significantly decreased， the level of ROS was significantly increased（P<0.01）， the expression levels of STAT3， p-STAT3， p-STAT3/STAT3 and GPX4 proteins were significantly decreased（P<0.05， P<0.01）. Compared with the model group， the cell viability and survival rate of the BXG group were significantly increased， the ROS level was significantly decreased（P<0.01）， the STAT3， p-STAT3， p-STAT3/STAT3 and GPX4 protein levels were significantly increased（P<0.05， P<0.01）. ConclusionBXG may inhibit the occurrence of ferroptosis by up-regulating the expression of STAT3 and GPX4， thus exerting a therapeutic effect on HF， and flavonoids may be the key components of this role.

ObjectiveBased on ultra performance liquid chromatography-quadrupole-time-of-flight mass spectrometry（UPLC-Q-TOF-MS）， network pharmacology， molecular docking and cell experiments， the active ingredients， possible targets and molecular mechanisms of Baoxin granules（BXG） regulating ferroptosis in the treatment of heart failure（HF） were explored. MethodsBXG intestinal absorption fluid was prepared by everted gut sac and the chemical composition contained therein were identified by UPLC-Q-TOF-MS. According to the obtained components， the potential targets of BXG were predicted， and the HF-related targets and related genes of ferroptosis were retrieved at the same time， and the intersecting targets were obtained by Venn diagram. In addition， the protein-protein interaction（PPI） network and the component-target network were constructed， and the core components and core targets were obtained by topological analysis. Then Gene Ontology（GO） function and Kyoto Encyclopedia of Genes and Genomes（KEGG） enrichment analysis were performed on the core targets， and molecular docking validation of the key targets and main components was carried out by AutoDockTools 1.5.7. H9c2 cells were used to establish a oxygen-glucose deprivation model， and the protective effect of BXG on cells was investigated by detecting cell viability， cell survival rate and reactive oxygen species（ROS） level. The protein expression levels of signal transducer and activator of transcription 3（STAT3）， phosphorylation（p）-STAT3 and glutathione peroxidase 4（GPX4） were detected by Western blot to clarify the regulatory effect of BXG on ferroptosis. ResultsA total of 61 chemical components in BXG intestinal absorption fluid were identified， and network pharmacology obtained 27 potential targets of BXG for the treatment of HF， as well as 139 signaling pathways. BXG may act on core targets such as STAT3， tumor protein p53（TP53）， epidermal growth factor receptor（EGFR）， JUN and prostaglandin-endoperoxide synthase 2（PTGS2） through core components such as glabrolide and limonin， which in turn intervene in lipid and atherosclerosis， phosphatidylinositol 3-kinase/protein kinase B（PI3K/Akt）， endocrine resistance and other signaling pathways to exert therapeutic effects on HF. Molecular docking showed that the docking results of multiple groups of targets and compounds were good. In vitro cell experiments showed that compared with the blank group， the cell viability and survival rate of the model group were significantly decreased， the level of ROS was significantly increased（P<0.01）， the expression levels of STAT3， p-STAT3， p-STAT3/STAT3 and GPX4 proteins were significantly decreased（P<0.05， P<0.01）. Compared with the model group， the cell viability and survival rate of the BXG group were significantly increased， the ROS level was significantly decreased（P<0.01）， the STAT3， p-STAT3， p-STAT3/STAT3 and GPX4 protein levels were significantly increased（P<0.05， P<0.01）. ConclusionBXG may inhibit the occurrence of ferroptosis by up-regulating the expression of STAT3 and GPX4， thus exerting a therapeutic effect on HF， and flavonoids may be the key components of this role.

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.