Objective To investigate the efficacy of an interpretable integrated learning model combining clinical indicators,CT image features and radiomics features for the differential diagnosis of lung squamous cell carcinoma and adenocarcinoma,so as to provide references for clincal treatment decisions.Methods A retrospective analysis was conducted on clinical and imaging data from 220 patients(231 lesions)with primary non-small cell lung cancer at Jiangjin Central Hospital of Chongqing(Center 1)and 83 patients(84 lesions)at Chongqing General Hospital(Center 2).In Center 1,the squamous cell carcinoma group consisted of 60 patients(60 lesions),while the adenocarcinoma group included 160 patients(171 lesions).In Center 2,the squamous cell carcinoma group comprised 18 patients(18 lesions),and the adenocarcinoma group involved 65 patients(66 lesions).The patients were categorized into squamous cell carcinoma and adenocarcinoma groups based on pathological findings.Center 1 was randomly partitioned into a training set and a validation set at a 7∶3 ratio,while Center 2 served as the independent test set.Firstly,a deep learning model,VB-Net,was used to automatically segment the tumor region on the lung window image;secondly,the SMOTE(synthetic minority oversampling technique)method was used to balance the categories in the training set and standardize the extracted features with Z-scores;thirdly,the least absolute shrinkage and selection operator(LASSO)were used to select the optimal radiomics features and calculate the radiomics score(Radscore),and univariate and multivariate logistic regression was used to screen clinical indicators and independent clinical factors for differentiating lung squamous cell carcinoma and adenocarcinoma in CT image features;finally,three ensemble learning algorithms(AdaBoost,Bagging decision tree and XGBoost)were used to combine independent clinical factors and Radscore to construct the model.The receiver operating characteristic(ROC)curve was used to evaluate the diagnostic performance of the models.SHAP technique was used to analyze the feature contribution and model decision-making process.Results Among the evaluated ensemble models,AdaBoost and Bagging decision trees demonstrated overfitting tendencies.In contrast,the XGBoost model showed the best performance,achieving AUC values of 0.939,0.887 and 0.853 in the training,validation and independent test sets,respectively.SHAP indicated that Radscore was the most important feature affecting the performance of the model.The decision diagram enabled the visualization of the diagnostic process of the model.Conclusion The interpretable integrated learning model based on clinical indicators,CT image and radiomics features is expected to non-invasively diagnose lung squamous cell carcinoma and adenocarcinoma before treatment and assist clinicians make treatment decisions as early as possible.[Chinese Medical Equipment Journal,2025,46(7):12-20]

Infiltration of a large number of inflammatory cells in the synovial tissue of rheumatoid arthritis(RA)promotes vascu-lar neovascularisation and the formation of aggressive pannus,which ultimately lead to bone erosion and cartilage destruction,causing irreversible damage to the joints.Numerous studies have demonstrated the role of proangiogenic factors such as growth factors,adhesion factors,angiopoietin 2,matrix metalloproteinas-es,and macrophage migration inhibitory factors in stimulating vascular opacification formation during RA progression.In re-cent years,a variety of traditional Chinese medicines have dem-onstrated inhibitory effects on the formation of pannus.In this paper,we elucidate the mechanism of pro-angiogenic factors in RA and review the latest research results on traditional Chinese medicines that inhibit the formation of pannus through the above mechanisms,so as to provide more research ideas for the treat-ment of RA.

Objective To investigate the current situation of the ventilator use and management in secondary and tertiary medical institutions in Sichuan Province to provide references for management and training of ventilator users.Methods A questionnaire survey involving in 235 nurses from 13 secondary and tertiary medical institutions in Sichuan Province was conducted in terms of general information of the respondents,pipeline connection and parameter setup of ventilators,cleaning,sterilization and maintenance of ventilators,identification and treatment of ventilator alarms and hospital-acquired infection prevention and control.Results The results showed 20.4％of the respondents were nurses from critical care departments,and 79.6％of the respondents underwent the training for using the ventilator in their department;91.9％of the respondents could conduct ventilator self-testing by connecting the simulated lungs after the ventilator was switched on;66.4％of the respondents indicated that the initial parameters of the ventilator were set by the doctor;60.9％of the respondents proved that the performance monitoring and routine maintenance of the ventilator were carried out by the nurse;63.4％of the respondents showed disposable lines were commonly used in the departments.There were 89.8％of the respondents said the daily sterilization and management of the ventilator were performed by the nurse;46.0％of the respondents expressed the external surface of the ventilator was disinfected mainly with gamma disinfectant wipes;44.7％of the respondents indicated the external surface of the ventilator was sterilized every day;48.5％of the respondents said the internal airway of the ventilator was disinfected;57.0％of the respondents proved the disinfection was conducted after the expiratory flow sensors were used by any patient.There were 74.5％of the respondents that had paid attention to the ventilator waveform,and by the ventilator waveform only 21.3％were correct in determining whether there was secretion or fluid in the circuit and 22.1％in clarifying whether there was air leakage in the circuit.There were 59.1％of the respondents indicated that the closed suction tube was replaced once every 24 h;71.1％of the respondents could perform airbag pressure monitoring by the special pressure gauge.Conclusion Most of the nurses from secondary and tertiary medical institutions in Sichuan Province can use ventilators correctly,who have problems in disinfection specifications,infection prevention and control or recognition of ventilation waveform.It's suggested the training be strengthened to enhance the clinical nursing staffs in ventilator management.[Chinese Medical Equipment Journal,2025,46(3):75-80]

Objective To evaluate the forensic application value of used dental floss as a source of bio-logical evidence for individual identification by analyzing the effects of dental floss sample collection methods,DNA extraction methods,preservation conditions,and sampling sites on the success rate of STR typing.Methods Dental floss samples were collected using three techniques:direct cutting,cotton swab wiping,and flocked swab wiping,respectively.DNA was extracted respectively by the Chelex,spin column-based and magnetic bead-based methods.DNA quantification and STR typing were per-formed using the Qubit kit and FGI HumDNA Typing kit(Platinum),respectively.Storage environ-ments(temperature and humidity,ultraviolet radiation)and sampling locations(the floss part,the handle part)on DNA quantity and STR typing were evaluated.Results Through conducting a statisti-cal analysis of three key indicators of average DNA mass concentration,STR locus detection rate,and typing accuracy rate,the direct cutting method demonstrated the highest efficacy,followed by cotton swab wiping mothed,and the flocked swab wiping method had the lowest efficacy.Direct cutting yielded an average DNA mass concentration greater than(4.94±1.87)ng/μL,with STR locus detection and accuracy rates of 100%.Bead-based DNA extraction method produced superior DNA concentration and quality compared to spin column-based and Chelex methods,regardless of whether the sampling technique used.Preservation conditions had a significant impact on the DNA analysis of samples.Par-ticularly,the STR typing accuracy of samples preserved at 55℃/50%RH for 35 days dropped to(81.82±12.31)%,and that of samples exposed to ultraviolet radiation for 12 h dropped to(55.46±34.31)%.DNA concentration from the handle part of dental floss was extremely low,with an STR typing accuracy of only(30.91±27.35)%.Conclusion Using cotton swabs to wipe or directly cutting the thread of dental floss samples,and combining this approach with the magnetic bead method for DNA extraction,can best guarantee the concentration and quality of DNA.In addition,samples should be stored in low-temperature,low-humidity environment,protected from light and ultraviolet radiation.

The objective assessment of hearing loss is one of the critical components in forensic clini-cal research.Auditory brainstem response(ABR)is an important method for objectively assessing hearing levels.It is divided into various types based on different stimulus signals,each with its own characteris-tics and applications.Among them,narrow-band Chirp ABR,due to its frequency specificity,fulfills the basic requirements for objective assessment of forensic audiology,promising to be an important method of objective hearing assessment in forensic medicine.This article reviews the development history,charac-teristics and clinical applications of Chirp ABR,and envisions its application prospects in forensic audi-tory identification.

Objective To develop a predictive model for postoperative mortality risk in patients with acute aortic dissection(AAD)using the Extreme Gradient Boosting(XGBoost)algorithm combined with Shapley Additive Explanation(SHAP),and to establish a prediction website to serve as a diagnostic and therapeutic support platform for clinicians and patients.Methods A retrospective cohort study design was adopted.Data from 782 AAD patients who underwent surgical treatment at the Fourth Hospital of Hebei Medical University from January 2013 to December 2023 were collected,including basic information and initial serum biomarker test results.Patients were randomly divided into training and test sets at a 7:3 ratio.An external validation set consisting of 313 AAD patients admitted to the Second Hospital of Hebei Medical University from January 2020 to December 2023 was also established for further model validation.Variables were screened using LASSO regression,and an XGBoost machine learning model was constructed and interpreted using SHAP.The predictive performance of the model was evaluated using receiver operating characteristic(ROC)curve analysis.Using the Shiny package,the XGBoost model was deployed to shinyapps.io to create a prediction website for postoperative mortality risk in AAD patients.One patient was selected by simple random sampling from the test set and the external validation set respectively for the prediction example on the Shiny webpage.Results The XGBoost model demonstrated high predictive performance for postoperative mortality in AAD patients,with area under the ROC curve(AUC)values of 0.928(95%CI 0.901-0.956)in the training set,0.919(95%CI 0.891-0.949)in the test set,and 0.941(95%CI 0.915-0.967)in the external validation set.SHAP values indicated the following order of variable importance in the model(from highest to lowest):"lactate dehydrogenase""blood chlorine""multiple organ injury""carbon dioxide combining power""prothrombin time""α-hydroxybutyric acid""creatine kinase isoenzyme""Stanford classification""combined use of bedside blood purification""gender""acute kidney injury""gastrointestinal bleeding""brain injury"and"shock".A risk prediction website for adverse postoperative outcomes in AAD patients was developed using XGBoost-SHAP method(https://dun-dunxiaolu.shinyapps.io/document/)and validated with examples.One randomly selected patient from each of the test and external validation sets was applied:the predicted mortality risk value for patient 1(who died postoperatively)was 0.9539,and that for patient 2(who survived postoperatively)was 0.0206.Conclusions The XGBoost-SHAP model demonstrates high accuracy in predicting postoperative mortality risk for AAD patients.The online prediction tool established based on this model enhances the identification efficiency of high-risk postoperative mortality patients.

Infiltration of a large number of inflammatory cells in the synovial tissue of rheumatoid arthritis(RA)promotes vascu-lar neovascularisation and the formation of aggressive pannus,which ultimately lead to bone erosion and cartilage destruction,causing irreversible damage to the joints.Numerous studies have demonstrated the role of proangiogenic factors such as growth factors,adhesion factors,angiopoietin 2,matrix metalloproteinas-es,and macrophage migration inhibitory factors in stimulating vascular opacification formation during RA progression.In re-cent years,a variety of traditional Chinese medicines have dem-onstrated inhibitory effects on the formation of pannus.In this paper,we elucidate the mechanism of pro-angiogenic factors in RA and review the latest research results on traditional Chinese medicines that inhibit the formation of pannus through the above mechanisms,so as to provide more research ideas for the treat-ment of RA.

Objective To investigate the current situation of the ventilator use and management in secondary and tertiary medical institutions in Sichuan Province to provide references for management and training of ventilator users.Methods A questionnaire survey involving in 235 nurses from 13 secondary and tertiary medical institutions in Sichuan Province was conducted in terms of general information of the respondents,pipeline connection and parameter setup of ventilators,cleaning,sterilization and maintenance of ventilators,identification and treatment of ventilator alarms and hospital-acquired infection prevention and control.Results The results showed 20.4％of the respondents were nurses from critical care departments,and 79.6％of the respondents underwent the training for using the ventilator in their department;91.9％of the respondents could conduct ventilator self-testing by connecting the simulated lungs after the ventilator was switched on;66.4％of the respondents indicated that the initial parameters of the ventilator were set by the doctor;60.9％of the respondents proved that the performance monitoring and routine maintenance of the ventilator were carried out by the nurse;63.4％of the respondents showed disposable lines were commonly used in the departments.There were 89.8％of the respondents said the daily sterilization and management of the ventilator were performed by the nurse;46.0％of the respondents expressed the external surface of the ventilator was disinfected mainly with gamma disinfectant wipes;44.7％of the respondents indicated the external surface of the ventilator was sterilized every day;48.5％of the respondents said the internal airway of the ventilator was disinfected;57.0％of the respondents proved the disinfection was conducted after the expiratory flow sensors were used by any patient.There were 74.5％of the respondents that had paid attention to the ventilator waveform,and by the ventilator waveform only 21.3％were correct in determining whether there was secretion or fluid in the circuit and 22.1％in clarifying whether there was air leakage in the circuit.There were 59.1％of the respondents indicated that the closed suction tube was replaced once every 24 h;71.1％of the respondents could perform airbag pressure monitoring by the special pressure gauge.Conclusion Most of the nurses from secondary and tertiary medical institutions in Sichuan Province can use ventilators correctly,who have problems in disinfection specifications,infection prevention and control or recognition of ventilation waveform.It's suggested the training be strengthened to enhance the clinical nursing staffs in ventilator management.[Chinese Medical Equipment Journal,2025,46(3):75-80]

Objective To investigate the efficacy of an interpretable integrated learning model combining clinical indicators,CT image features and radiomics features for the differential diagnosis of lung squamous cell carcinoma and adenocarcinoma,so as to provide references for clincal treatment decisions.Methods A retrospective analysis was conducted on clinical and imaging data from 220 patients(231 lesions)with primary non-small cell lung cancer at Jiangjin Central Hospital of Chongqing(Center 1)and 83 patients(84 lesions)at Chongqing General Hospital(Center 2).In Center 1,the squamous cell carcinoma group consisted of 60 patients(60 lesions),while the adenocarcinoma group included 160 patients(171 lesions).In Center 2,the squamous cell carcinoma group comprised 18 patients(18 lesions),and the adenocarcinoma group involved 65 patients(66 lesions).The patients were categorized into squamous cell carcinoma and adenocarcinoma groups based on pathological findings.Center 1 was randomly partitioned into a training set and a validation set at a 7∶3 ratio,while Center 2 served as the independent test set.Firstly,a deep learning model,VB-Net,was used to automatically segment the tumor region on the lung window image;secondly,the SMOTE(synthetic minority oversampling technique)method was used to balance the categories in the training set and standardize the extracted features with Z-scores;thirdly,the least absolute shrinkage and selection operator(LASSO)were used to select the optimal radiomics features and calculate the radiomics score(Radscore),and univariate and multivariate logistic regression was used to screen clinical indicators and independent clinical factors for differentiating lung squamous cell carcinoma and adenocarcinoma in CT image features;finally,three ensemble learning algorithms(AdaBoost,Bagging decision tree and XGBoost)were used to combine independent clinical factors and Radscore to construct the model.The receiver operating characteristic(ROC)curve was used to evaluate the diagnostic performance of the models.SHAP technique was used to analyze the feature contribution and model decision-making process.Results Among the evaluated ensemble models,AdaBoost and Bagging decision trees demonstrated overfitting tendencies.In contrast,the XGBoost model showed the best performance,achieving AUC values of 0.939,0.887 and 0.853 in the training,validation and independent test sets,respectively.SHAP indicated that Radscore was the most important feature affecting the performance of the model.The decision diagram enabled the visualization of the diagnostic process of the model.Conclusion The interpretable integrated learning model based on clinical indicators,CT image and radiomics features is expected to non-invasively diagnose lung squamous cell carcinoma and adenocarcinoma before treatment and assist clinicians make treatment decisions as early as possible.[Chinese Medical Equipment Journal,2025,46(7):12-20]

Ketamine,an antagonist of the glutamate N-methyl-D-aspartate(NMDA)receptor,is cur-rently one of the most widely abused psychoactive substances.Prolonged abuse can result in damages to various systems in the body,making it crucial to investigate the regulatory mechanism of ketamine addic-tion and screening related biomarkers.In this study,zebrafish embryos/larvae were initially exposed a-cutely to ketamine.Then,a ketamine addiction model was established in 6-month-old zebrafish through conditioned place preference(CPP)experiments.The zebrafish brain transcriptome was analyzed using RNA-seq,while qPCR and Western blotting were employed to detect the expression of key genes.Results revealed significant reductions in the spontaneous tail coiling,embryo hatching rate,and survival rate of zebrafish embryos in the ketamine-treated group compared to the control group.The distance moved also decreased significantly,from 1904.2 mm in the control group to 319.0 mm in the high dose of ketamine group(300 μmol/L).Conditional positional preference experiments demonstrated that the control ze-brafish did not exhibit significant changes in activity in the CPP tank.In contrast,the ketamine-treated group increased their activity time in the light zone of the tank from 385.2 s before training to 706.4 s af-ter training,representing a 26.8％increase(***P＜0.001).This suggests a preference for ketamine stimulation in zebrafish.KEGG analysis indicated enrichment of differentially expressed genes in the neu-roactive ligand-receptor interaction pathway in the ketamine-treated samples.GSEA analysis further re-veals a significant upregulation of the glutamatergic synapse pathway(NES=1.5).In addition,compared with the control group,the mRNA levels of Grin2b and Gria2 in the ketamine group increased by 4.6 and 1.4 times,respectively,while the protein levels increased by 2.0 and 1.4 times,respectively.These findings suggest that ketamine can induce addiction in zebrafish,potentially through upregulation of the glutamatergic synaptic pathway.