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]

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]

In the present study, the antibacterial spectrum of turmeric extract was analyzed by measuring the minimum inhibitory concentration (MIC), and the antibacterial mechanism of turmeric extract was elaborated by determining its effects on the permeability and integrity of the cytoplasmic membrane, energy metabolism, and the morphology of the tested bacteria (Bacillus subtilis) with the highest susceptibility to the extract. The results showed that turmeric extract possessed broad-spectrum antibacterial activity against Gram-positive, Gram-negative bacteria and fungi, especially against Bacillus subtilis, with the MIC of 0.5 mg·mL^-1. Turmeric extract disrupted the liposome membrane and released calcein encapsulated within it. The permeability of the bacterial cell membrane was increased, leading to leakage of intracellular K⁺, Ca²⁺and cell wall proteins, and the integrity of the cell membrane was broken down, causing leakage of intracellular proteins and polysaccharides. Scanning electron microscope observation confirmed that the bacteria treated with turmeric extract was severely deformed. Simultaneously, cellular energy metabolism was affected, resulting in a significant reduction in the intracellular ATP content and ATPase activity in bacteria. In summary, the antibacterial mode of turmeric extract is closely related to its disruption of bacterial membrane structure.

Objective To observe the efficacy and safety of Morinda officinalis oligosaccharides in the continuation treatment of mild and moderate depression.Methods An open,single-arm,multi-center design was adopted in our study.Adult patients with mild and moderate depression who had received acute treatment of Morinda officinalis oligosaccharides were enrolled and continue to receive Morinda officinalis oligosaccharides capsules for 24 weeks,the dose remained unchanged during continuation treatment.The remission rate,recurrence rate,recurrence time,and the change from baseline to endpoint of Hamilton Depression Scale(HAMD),Hamilton Anxiety Scale(HAMA),Clinical Global Impression-Severity(CGI-S)and Arizona Sexual Experience Scale(ASEX)were evaluated.The incidence of treatment-related adverse events was reported.Results The scores of HAMD-17 at baseline and after treatment were 6.60±1.87 and 5.85±4.18,scores of HAMA were 6.36±3.02 and 4.93±3.09,scores of CGI-S were 1.49±0.56 and 1.29±0.81,scores of ASEX were 15.92±4.72 and 15.57±5.26,with significant difference(P＜0.05).After continuation treatment,the remission rate was 54.59％(202 cases/370 cases),and the recurrence rate was 6.49％(24 cases/370 cases),the recurrence time was(64.67±42.47)days.The incidence of treatment-related adverse events was 15.35％(64 cases/417 cases).Conclusion Morinda officinalis oligosaccharides capsules can be effectively used for the continuation treatment of mild and moderate depression,and are well tolerated and safe.

Molecular imprinting is a biomimetic technique that simulates the specific recognition of biological macromolecules such as antibody. Based on molecular imprinting and high-specificity affinity analysis,the biomimetic imprinting affinity analysis (BIA) possesses many advantages such as high sensitivity,strong tolerance,good specificity and low cost,and thus,it has shown excellent prospects in food safety detection,pharmaceutical analysis and environmental pollution monitoring. In this review,the construction methods of recognition interfaces for BIA were summarized,including bulk polymerization,electro-polymerization and surface molecular imprinting. The application of molecularly imprinted polymers in different analysis methods,such as radiolabeled affinity analysis,enzyme-labeled affinity analysis,fluorescence-labeled affinity analysis,chemiluminescence affinity analysis and electrochemical immunosensor was mainly discussed. Furthermore,the challenges and future development trends of BIA in practical application were elucidated. This review might provide new reference ideas and technical supports for the further development of BIA technique.

Objective To analyze the characteristics of healthcare-associated infection(HAI)in patients in liver transplantation intensive care unit(ICU),and provide basis for the effective prevention and control of liver post-transplantation infection.Methods Targeted surveillance data of HAI in liver transplantation ICU from 2018 to 2022 were analyzed retrospectively.Incidence,incidence trend,infection site,pathogens and drug resistance were analyzed.Results A total of 3 762 liver transplantation patients were surveilled,106 patients developed 133 cases of HAI,with an incidence of 2.82％and a case incidence of 3.54％.There was no significant difference among the years(P=0.473).Infection mainly occurred within 2 weeks after admission to ICU,accounting for 85.85％.The main infection sites included blood system(26.32％),respiratory system(22.56％),and surgical site(19.55％).The average utilization rates of central veinous catheterization,urethral catheterization,and ventilator were 85.77％,70.58％,and 40.83％,respectively.The incidences of central line-associated bloodstream infection(CLABSI),catheter-associated urinary tract infection(CAUTI),and ventilator-associated pneumonia(VAP)were 0.54‰,0.33‰,and 1.84‰,respectively.A total of 131 strains of pathogens were detected,of which Gram-negative bac-teria accounted for 38.17％and Gram-positive bacteria accounted for 29.77％.The top three pathogens were Kleb-siella pneumoniae(15.27％),Enterococcus faecium(11.45％),and Acinetobacter baumannii(9.16％).Conclusion Effective prevention and control measures should be taken based on the characteristics of HAI in the liver transplan-tation ICU,so as to curb bacterial resistance and reduce liver post-transplantation HAI.

Objective To analyze the characteristics of healthcare-associated infection(HAI)in patients in liver transplantation intensive care unit(ICU),and provide basis for the effective prevention and control of liver post-transplantation infection.Methods Targeted surveillance data of HAI in liver transplantation ICU from 2018 to 2022 were analyzed retrospectively.Incidence,incidence trend,infection site,pathogens and drug resistance were analyzed.Results A total of 3 762 liver transplantation patients were surveilled,106 patients developed 133 cases of HAI,with an incidence of 2.82％and a case incidence of 3.54％.There was no significant difference among the years(P=0.473).Infection mainly occurred within 2 weeks after admission to ICU,accounting for 85.85％.The main infection sites included blood system(26.32％),respiratory system(22.56％),and surgical site(19.55％).The average utilization rates of central veinous catheterization,urethral catheterization,and ventilator were 85.77％,70.58％,and 40.83％,respectively.The incidences of central line-associated bloodstream infection(CLABSI),catheter-associated urinary tract infection(CAUTI),and ventilator-associated pneumonia(VAP)were 0.54‰,0.33‰,and 1.84‰,respectively.A total of 131 strains of pathogens were detected,of which Gram-negative bac-teria accounted for 38.17％and Gram-positive bacteria accounted for 29.77％.The top three pathogens were Kleb-siella pneumoniae(15.27％),Enterococcus faecium(11.45％),and Acinetobacter baumannii(9.16％).Conclusion Effective prevention and control measures should be taken based on the characteristics of HAI in the liver transplan-tation ICU,so as to curb bacterial resistance and reduce liver post-transplantation HAI.

Objective:To establish a machine learning model for the diagnosis of clinically significant prostate cancer based on transrectal contrast-enhanced ultrasound parameters and clinically relevant data.Methods:A retrospective analysis was performed on 151 patients in Chongqing University Cancer Hospital who underwent transrectal contrast-enhanced ultrasonography and transrectal ultrasound-guided needle biopsy from November 2018 to September 2021. The time intensity curve was drawn using VueBox software and 12 parameters such as rise time, peak time, average transit time, peak intensity, and rising slope were quantitatively analyzed. Age, total prostate-specific antigen, free prostate-specific antigen, free prostate-specific antigen ratio, volume, prostate-specific antigen density, and transrectal contrast-enhanced ultrasonography parameters, a total of 18 characteristic parameters, were analyzed and screened through relevant attribute values and information gain attribute values. The screening features were trained and tested by the machine learning single algorithm and integrated algorithm, and then the model was evaluated by the F1 value and the area under the ROC curve(AUC).Results:Using the related attribute value and the information gain attribute value, 12 variables and 5 variables were screened out respectively to establish a machine learning model. The model established by the ensemble algorithm was better than the single algorithm. For the two variable selection methods, the AUC (0.810 vs 0.789) and F1 values (0.748 vs 0.742) of the Bagging ensemble algorithm model, which basic algorithm was decision tree, were the highest, followed by Logistic regression and support vector machine(SVM) in order of AUC and F1 values.Conclusions:Based on transrectal contrast-enhanced ultrasound parameters and clinical data, the Bagging ensemble model based on decision tree has the best performance in diagnosing clinically significant prostate cancer.

Objective: To analyze and compare therapy responses, outcomes, and incidence of severe hematologic adverse events of flumatinib and imatinib in patients newly diagnosed with chronic phase chronic myeloid leukemia (CML) . Methods: Data of patients with chronic phase CML diagnosed between January 2006 and November 2022 from 76 centers, aged ≥18 years, and received initial flumatinib or imatinib therapy within 6 months after diagnosis in China were retrospectively interrogated. Propensity score matching (PSM) analysis was performed to reduce the bias of the initial TKI selection, and the therapy responses and outcomes of patients receiving initial flumatinib or imatinib therapy were compared. Results: A total of 4 833 adult patients with CML receiving initial imatinib (n=4 380) or flumatinib (n=453) therapy were included in the study. In the imatinib cohort, the median follow-up time was 54 [interquartile range (IQR), 31-85] months, and the 7-year cumulative incidences of CCyR, MMR, MR(4), and MR(4.5) were 95.2%, 88.4%, 78.3%, and 63.0%, respectively. The 7-year FFS, PFS, and OS rates were 71.8%, 93.0%, and 96.9%, respectively. With the median follow-up of 18 (IQR, 13-25) months in the flumatinib cohort, the 2-year cumulative incidences of CCyR, MMR, MR(4), and MR(4.5) were 95.4%, 86.5%, 58.4%, and 46.6%, respectively. The 2-year FFS, PFS, and OS rates were 80.1%, 95.0%, and 99.5%, respectively. The PSM analysis indicated that patients receiving initial flumatinib therapy had significantly higher cumulative incidences of CCyR, MMR, MR(4), and MR(4.5) and higher probabilities of FFS than those receiving the initial imatinib therapy (all P<0.001), whereas the PFS (P=0.230) and OS (P=0.268) were comparable between the two cohorts. The incidence of severe hematologic adverse events (grade≥Ⅲ) was comparable in the two cohorts. Conclusion: Patients receiving initial flumatinib therapy had higher cumulative incidences of therapy responses and higher probability of FFS than those receiving initial imatinib therapy, whereas the incidence of severe hematologic adverse events was comparable between the two cohorts.
Adult ; Humans ; Adolescent ; Imatinib Mesylate/adverse effects* ; Incidence ; Antineoplastic Agents/adverse effects* ; Retrospective Studies ; Pyrimidines/adverse effects* ; Leukemia, Myelogenous, Chronic, BCR-ABL Positive/drug therapy* ; Treatment Outcome ; Benzamides/adverse effects* ; Leukemia, Myeloid, Chronic-Phase/drug therapy* ; Aminopyridines/therapeutic use* ; Protein Kinase Inhibitors/therapeutic use*

OBJECTIVES: To investigate the clinical treatment outcomes and the changes of the outcomes over time in extremely preterm twins in Guangdong Province, China. METHODS: A retrospective analysis was performed for 269 pairs of extremely preterm twins with a gestational age of <28 weeks who were admitted to the department of neonatology in 26 grade A tertiary hospitals in Guangdong Province from January 2008 to December 2017. According to the admission time, they were divided into two groups: 2008-2012 and 2013-2017. Besides, each pair of twins was divided into the heavier infant and the lighter infant subgroups according to birth weight. The perinatal data of mothers and hospitalization data of neonates were collected. The survival rate of twins and the incidence rate of complications were compared between the 2008-2012 and 2013-2017 groups. RESULTS: Compared with the 2008-2012 group, the 2013-2017 group (both the heavier infant and lighter infant subgroups) had lower incidence rates of severe asphyxia and smaller head circumference at birth (P<0.05). The mortality rates of both of the twins, the heavier infant of the twins, and the lighter infant of the twins were lower in the 2013-2017 group compared with the 2008-2012 group (P<0.05). Compared with the 2008-2012 group, the 2013-2017 group (both the heavier infant and lighter infant subgroups) had lower incidence rates of pulmonary hemorrhage, patent ductus arteriosus (PDA), periventricular-intraventricular hemorrhage (P-IVH), and neonatal respiratory distress syndrome (NRDS) and a higher incidence rate of bronchopulmonary dysplasia (P<0.05). CONCLUSIONS There is a significant increase in the survival rate over time in extremely preterm twins with a gestational age of <28 weeks in the 26 grade A tertiary hospitals in Guangdong Province. The incidences of severe asphyxia, pulmonary hemorrhage, PDA, P-IVH, and NRDS decrease in both the heavier and lighter infants of the twins, but the incidence of bronchopulmonary dysplasia increases. With the improvement of diagnosis and treatment, the multidisciplinary collaboration between different fields of fetal medicine including prenatal diagnosis, obstetrics, and neonatology is needed in the future to jointly develop management strategies for twin pregnancy.
Bronchopulmonary Dysplasia/epidemiology* ; Female ; Gestational Age ; Humans ; Infant ; Infant, Extremely Premature ; Infant, Newborn ; Pregnancy ; Respiratory Distress Syndrome, Newborn/epidemiology* ; Retrospective Studies ; Treatment Outcome