Objective To develop and validate a prediction model for in-hospital recurrent intensive care unit (ICU) admission in critically ill patients with ischemic stroke (IS) based on machine learning (ML) algorithms. Methods Clinical data from 2 929 IS patients were included from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database. Least absolute shrinkage and selection operator (LASSO) regression was used to identify predictive factors, and the synthetic minority over-sampling technique (SMOTE) was employed to create a derivation cohort comprising 2 583 patients. These patients were randomly divided into a training set (n=2 066) and a test set (n=517) at an 8:2 ratio. Five ML algorithms, including decision tree, random forest, adaptive boosting (AdaBoost), gradient boosting decision tree (GBDT), and support vector machine (SVM), were performed to construct prediction models. Five-fold cross-validation was used to evaluate the performance of the model in the training set. The area under the receiver operating characteristic curve (ROC-AUC) and decision curve analysis (DCA) were used to assess and compare the models in the testing set. The best-performing model was interpreted by shapley additive explanations (SHAP). Results Among the 2 929 patients included, 704 (24.0%) experienced in-hospital recurrent ICU admission. Among the five ML models, the random forest model demonstrated the best predictive performance, with an AUC of 0.839 (95%CI 0.801–0.877). Feature importance analysis identified five most significant features affecting model prediction, including APS Ⅲ score, albumin, age, heart rate, and SOFA score. Conclusions ML-based models can effectively predict the risk of in-hospital recurrent ICU admission in critically ill patients with IS. The random forest model showed superior predictive performance, which may have potential applications in early clinical risk stratification and intervention.

Smart healthcare plays an important role in easing the strain on medical resources and improving the continuity of chronic disease management. This study analysed the iatrogenic risks from the intrinsic attributes and the external environment of smart healthcare, including doctor-patient conflict risk, technical operation risk, information leakage risk, humanistic absence risk, legal risk, regulatory risk and ethical risk. Based on the " structure process result" model, suggestions were proposed to optimize the construction of a smart healthcare platform for chronic diseases, improve the legal system and industry standards, strengthen talent cultivation and capacity building, establish an integrated regulatory system, and regularly evaluate the effectiveness of chronic disease management. These suggestions provided references for creating a healthy, orderly, and safe smart healthcare environment for chronic disease patients.

Smart healthcare plays an important role in easing the strain on medical resources and improving the continuity of chronic disease management. This study analysed the iatrogenic risks from the intrinsic attributes and the external environment of smart healthcare, including doctor-patient conflict risk, technical operation risk, information leakage risk, humanistic absence risk, legal risk, regulatory risk and ethical risk. Based on the " structure process result" model, suggestions were proposed to optimize the construction of a smart healthcare platform for chronic diseases, improve the legal system and industry standards, strengthen talent cultivation and capacity building, establish an integrated regulatory system, and regularly evaluate the effectiveness of chronic disease management. These suggestions provided references for creating a healthy, orderly, and safe smart healthcare environment for chronic disease patients.

ObjectiveTo investigate the tumor inhibition effect and mechanism of Yifei Sanjie Pills （益肺散结丸， YSP） on lung cancer. MethodsLewis lung cancer tumor-derived mice were established and divided into four groups including model control group， cisplatin group， cisplatin + YSP low-dose group and cisplatin + YSP high-dose group， with 12 mice in each group. The corresponding interventions were given for 14 days. The tumor volume was measured on the 0th， 3rd， 7th， 10th and 14th days of administration to evaluate the tumor growth. The plasma and tumor tissue were collected on the 15th day. Plasma from the model group， the cisplatin group and the cisplatin+YSP high-dose group were selected， and plasma exosomes were extracted； the differences in miRNA expression among the groups were detected and analyzed by second-generation sequencing technology， and the potential mechanism of action of YSP was investigated by principal component analysis， biofunctional enrichment analysis and miRNA-target gene regulatory network analysis. Quantitative real-time PCR was used to detect the expression of miRNA-615-3p in tumor tissues， and the relationship between miRNA-615-3p and overall survival of lung cancer were analyzed using the Kaplan-Meier plotter （kmplot.com） database. ResultsCompared to that of the model control group， the tumor volume of the cisplatin group on day 10， and the cisplatin + YSP low- and high-dose groups on day 7， 10， and 14 were significantly reduced （P＜0.05 or P＜0.01）. Compared to that of the cisplatin group， the tumor volume of the cisplatin + YSP low- and high-dose groups on day 10 and 14 was significantly reduced （P＜0.05）. The principal component analysis of miRNA expression profiles showed significant differences in miRNA expression between different intervention groups. There were 21 differentially expressed miRNAs between the model control group and the cisplatin group， 50 differentially expressed miRNAs between the model control group and the cisplatin+ YSP high-dose group， and 6 differentially expressed miRNAs between the cisplatin group and the cisplatin+ YSP high-dose group. Biological function enrichment analysis showed that the differentially expressed miRNAs were mainly involved in the regulation of signaling pathways related to cell growth， proliferation， differentiation， autophagy and other biological activities. The miRNA-target gene regulatory network showed the top 20 genes that were targeted， among which there were proven miRNAs and genes related to lung cancer， and miRNAs that needed further investigation. The expression of miRNA-615-3p in tumor tissues decreased significantly in the cisplatin group and cisplatin+YSP high-dose group compared to that of the model group（P＜0.05 or P＜0.01）. The miRNA-615-3p was negatively correlated with the survival prognosis of lung cancer（P＜0.05）. ConclusionCisplatin combined with YSP can effectively inhibit the proliferation of Lewis lung cancer tumors， and the tumor-suppressive effect is related to the regulation of multiple miRNAs， especially the downregulation of miRNA-615-3p expression.

Objective:To analyze the application effect of intelligent acceptance equipment for orthopedic medical equipment combined with medical device unique device identifier(UDI)code in the management of orthopedic medical devices.Methods:Based on the UDI code,the UDI application process of orthopedic medical devices was formulated,and all operations such as inspection and accurate billing of orthopedic medical devices were completed through the identification and comparison of intelligent acceptance equipment for orthopedic medical devices.A total of 8 317 orthopedic instruments used in orthopedic surgery in Wangjing Hospital of China Academy of Chinese Medical Sciences from September to December 2023 were selected.According to the different time of the implementation of intelligent acceptance equipment for orthopedic medical devices,the 4 072 orthopedic devices used from September to October 2023 was marked as before implementation and adopted the traditional management mode,the 4 245 orthopedic devices used from November 2023 to December 2023 were marked as before implementation and adopted the intelligent acceptance management mode.The management effect and incidence of adverse events were compared before and after the implementation of intelligent acceptance equipment for orthopedic medical devices.Results:The total effective rate of management after the implementation of intelligent acceptance equipment for orthopedic medical instruments was 98.78%,which was significantly higher than that before the implementation,the difference was statistically significant(x2=272.03,P<0.01).The total incidence of adverse events after the implementation of the intelligent acceptance equipment for orthopedic medical devices was 8.83%,which was significantly lower than that before the implementation,the difference was statistically significant(x2=281.38,P<0.01).Conclusion:The intelligent acceptance device combined with UDI code for orthopedic medical devices can achieve efficient distribution,accurate acceptance and billing,reduce the occurrence of adverse events,meet the requirements of the whole process traceability management of one thing and one code,and improve the management level orthopedic medical devices.

Objective:To measure and assess relevant radiation doses at the radiotherapy site of the first domestic single-vault proton therapy system.Methods:The radiation levels of the therapy system during and after beam irradiation were measured, and annual effective doses were assessed for personnel at the site.Results:During beam irradiation, the highest radiation dose was detected at the shielded door of the equipment floor, with a gamma radiation level of 2.140 μSv/h and a neutron radiation level of 0.850 μSv/h. Neutron radiation disappeared immediately once the beams stopped. In contrast, the radiation activated originated mostly from gamma rays. A longer time after beams stopped was associated with lower induced radiation intensity at the same location. Furthermore, a farther distance from the irradiated object corresponded to lower induced radiation intensity at the same time. The assessment result reveal that the annual effective doses to the personnel were at the safe level, with physicists exposed to the highest dose of 2.138 mSv.Conclusions:The radiation level at the studied proton therapy site meets the safety requirement, and the treatment can be performed safely at this site.

Objective:To develop multiplex cytokine detection reagents to analyze expression levels of cytokines,angiogene-sis and bone remodeling proteins in relapse/refractory multiple myeloma(RRMM).Methods:Multiplex bead-based immunoassay by flow cytometry was used to develop quantitative detection reagents of multiplex cytokines,which were applied to detect serum samples from 55 RRMM patients and 22 healthy controls.Expression levels of cytokines,angiogenesis,and bone remodeling proteins in pa-tients,and their correlation with clinical characteristics were analyzed.Results:Detection reagents of 10-plex cytokine immunoassay were successfully developed in this study,with average sensitivity of 7.1 pg/ml,average recovery rate of 97.4%,average intra-assay CV of 4.8%,and average inter-assay CV of 9.0%.In addition,results of RRMM samples found that levels of IL-2,IL-17,DKK1,RANKL and OPG were positively correlated with the level of IgG monoclonal protein,and TIMP1 was positively correlated with levels of IgG and IgA monoclonal protein.Conclusion:In this study,ten kinds of cytokine detection reagents with high sensitivity and speci-ficity are developed,and we found that IL-2,IL-17,DKK1,RANKL,OPG and TIMP1 have potential value in tracking disease pro-gression in RRMM.The established development process of multiplex cytokine reagents has important reference significance for ex-panding the development and application of multiplex detection reagents for protein markers in the future.

Objective:To Summarize the best evidence of follow-up management of patients with acute kidney injury to provide reference for clinical nursing work.Methods:Retrieved relevant literature on follow-up management of ICU transferred acute kidney injury patients from databases such as Cochrane Library, PubMed, CNKI, Wanfang Database, Chinese Biomedical Literature, and related professional websites based on the "6S" model system.The search deadline was from database establishment to May 30, 2023.Two researchers independently conducted literature quality evaluation, evidence screening, and evidence level assessment, and summarized the evidence.Results:Eight articles were selected, including 4 guidelines, 3 systematic review, 1 expert consensuses. Finally 16 pieces of best evidence from 6 dimensions of follow-up principles and methods, follow-up time/requency, follow- up assessment content, nutritional guidance, drug guidance and life guidance.Conclusions:This study summarized the best evidence summary of the follow-up management of patients with ICU transfer out of acute kidney dormitory, providing a reference for the clinical work of ICU medical staff. Medical staff can develop scientific and effective follow-up management based on patients and clinical conditions to improve the quality of care for ICU transferred patients.

Diabetes mellitus(DM)is a major metabolic disease endangering global health,with diabetic ne-phropathy(DN)as a primary complication lacking curative therapy.Sporoderm-broken spores of Ganoderma lucidum(GLP),an herbal medicine,has been used for the treatment of metabolic disorders.In this study,DN was induced in Sprague-Dawley rats using streptozotocin(STZ)and a high-fat diet(HFD),and the protective mechanisms of GLP were investigated through transcriptomic,metabolomic,and network pharmacology(NP)analyses.0ur results demonstrated that GLP intervention ameliorated renal damage and inflammation levels in DN rats.Integrative metabolomic and transcriptomic analysis revealed that GLP treatment modulated glucose and cellular energy metabolisms by regulating relevant genes.GLP significantly suppressed the inflammations by impacting glucose and energy metabolism-related gene expression(Igfbp1 and Angptl4)and enhanced metabolic biomarkers of 4-Aminocatechol.In addition,NP analysis further indicated that GLP may efficiently alleviate DN via immune-related pathways.In conclusion,this study provides supportive evidence of the anti-inflammatory effects of GLP supplements,highlighting their potential for promising clinical applications in treating DN.

Diabetes mellitus (DM) is a major metabolic disease endangering global health, with diabetic nephropathy (DN) as a primary complication lacking curative therapy. Sporoderm-broken spores of Ganoderma lucidum (GLP), an herbal medicine, has been used for the treatment of metabolic disorders. In this study, DN was induced in Sprague-Dawley rats using streptozotocin (STZ) and a high-fat diet (HFD), and the protective mechanisms of GLP were investigated through transcriptomic, metabolomic, and network pharmacology (NP) analyses. Our results demonstrated that GLP intervention ameliorated renal damage and inflammation levels in DN rats. Integrative metabolomic and transcriptomic analysis revealed that GLP treatment modulated glucose and cellular energy metabolisms by regulating relevant genes. GLP significantly suppressed the inflammations by impacting glucose and energy metabolism-related gene expression (Igfbp1 and Angptl4) and enhanced metabolic biomarkers of 4-Aminocatechol. In addition, NP analysis further indicated that GLP may efficiently alleviate DN via immune-related pathways. In conclusion, this study provides supportive evidence of the anti-inflammatory effects of GLP supplements, highlighting their potential for promising clinical applications in treating DN.