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]

As a physical treatment technique, modified electro-convulsive therapy (MECT) is used to treat mental and certain neurological disorders by causing seizures with short, suitable electrical currents applied to the brain while the patient is under general anesthesia and muscle relaxants. MECT is recognized for its therapeutic efficacy and clinical safety, rendering it one of the most prevalent interventions in psychiatric care. To enhance clinical outcomes and minimize adverse effects, this consensus document delineates the indications, therapeutic parameters, therapeutic procedures, potential adverse effects, and associated management strategies for MECT. These guidelines are informed by the latest clinical research and expert consensus, integrating evidence-based medicine methodologies. The objective is to furnish clinicians with precise operational guidelines and to advance the standardization of MECT practices in clinical settings.

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]

As a physical treatment technique, modified electro-convulsive therapy (MECT) is used to treat mental and certain neurological disorders by causing seizures with short, suitable electrical currents applied to the brain while the patient is under general anesthesia and muscle relaxants. MECT is recognized for its therapeutic efficacy and clinical safety, rendering it one of the most prevalent interventions in psychiatric care. To enhance clinical outcomes and minimize adverse effects, this consensus document delineates the indications, therapeutic parameters, therapeutic procedures, potential adverse effects, and associated management strategies for MECT. These guidelines are informed by the latest clinical research and expert consensus, integrating evidence-based medicine methodologies. The objective is to furnish clinicians with precise operational guidelines and to advance the standardization of MECT practices in clinical settings.

ObjectiveTo study the mechanism of astragaloside Ⅳ （AS Ⅳ） on db/db mice with type 2 diabetes mellitus （T2DM） and non-alcoholic fatty liver disease （NAFLD） based on network pharmacology and experimental validation. MethodA total of 24 db/db mice were randomly divided into four groups： model group， metformin group， and low-dose and high-dose AS Ⅳ groups. Six C57 mice were used as the blank group. The low-dose and high-dose AS Ⅳ groups were given AS Ⅳ of 0.015 and 0.030 g·kg^-1 by gavage， and the metformin group was given 0.067 g·kg^-1 by gavage. The blank and model groups were given equal volumes of distilled water by gavage. After intragastric administration， fasting blood glucose （FBG） was detected， and an oral glucose tolerance test was performed. Serum lipid level and liver histopathology were detected. The target and enrichment pathway of AS Ⅳ for treating T2DM and NAFLD were predicted by network pharmacology， and the main enrichment pathway was verified by molecular biology techniques. The protein expressions of AMPK， p-AMPK， sterol regulatory element-binding protein-1 （SREBP-1）， and fatty acid synthetase （FAS） in liver tissue were detected by Western blot. ResultCompared with the blank group， the levels of body mass， liver weight coefficient， fasting blood glucose， serum total cholesterol， triglyceride， and low-density lipoprotein cholesterol in mice treated with AS Ⅳ were decreased （P<0.05， P<0.01）. The pathology of liver tissue showed significant improvement in lipid accumulation， and imaging results showed that the degree of fatty liver was reduced after AS Ⅳ therapy. Network pharmacological prediction results showed that vascular endothelial growth factor α （VEGFA）， galactoagglutinin 3 （LGALS3）， serine/threonine kinase B2 （Akt2）， RHO-associated coiled-coil protein kinase 1 （ROCK1）， serine/threonine kinase B1 （Akt1）， signaling and transcriptional activator protein （STAT3）， and messtimal epidermal transformation factor （MET） were key targets in "drug-disease" network. The results from the Kyoto encyclopedia of genes and genomes （KEGG） enrichment showed that the AMP-dependent protein kinase （AMPK） signaling pathway was strongly associated with T2DM and NAFLD. Western blot results showed that compared with the blank group， the expression levels of p-AMPK/AMPK in the model group were significantly down-regulated， while those of SREBP-1 and FAS proteins were significantly up-regulated （P<0.01）. Compared with the model group， the expression levels of p-AMPK/AMPK in the metformin group and high-dose AS Ⅳ group were significantly up-regulated， while those of SREBP-1 and FAS proteins were significantly down-regulated （P<0.05， P<0.01）. ConclusionAS Ⅳ regulates the expression of lipid proteins by activating the AMPK signaling pathway， thereby improving lipid metabolism.

Objective To investigate the imaging features of intestinal schwannoma(IS)in order to improve the diagnostic ability of the disease.Methods The clinical and imaging data of 14 patients with surgically and pathologically confirmed IS were retrospectively analyzed,including the location,size,morphology,nature,growth pattern,CT density,MRI signal,PET/CT metabolism and other characteristics of the tumors.Results Of the 14 IS cases,the lesions of 3 cases were located in the duodenum,2 cases in the cecum,8 cases in the colon and 1 case in the rectum.The lesions were all round or oval,with an average maximum diameter of(2.4±1.1)cm.The lesions were solid in 13 cases,extraluminal growth in 10 cases,cystic degeneration in 1 case and myxoid degeneration in 1 case.Chronic inflammatory lymph nodes were seen around the diseased intestines in 9 cases,and the short diameter of lymph nodes was greater than 5 mm in 6 cases.All 14 cases of IS showed low attenuation on plain CT scan,and progressive enhancement after contrast injection,including 1 case of mild enhancement,2 cases of moderate enhancement,and 11 cases of obvious enhancement.Two cases of IS showed low signal intensity on T1WI,slightly high signal intensity on T2WI,significantly high signal intensity on DWI,and obvious progressive enhancement after contrast injection on MRI.Two cases of IS showed high metabolism on 18F-FDG-PET/CT,and the SUVmax was 9.4 and 8.8,respectively.Conclusion The imaging findings of IS were characteristic to a certain extent.They mainly manifested as solid nodules or masses derived from the intestinal submucosa,with uniform attenuation or signal intensity,obvious progressive enhancement after contrast injection,obvious hypermetabolism on 18F-FDG-PET/CT,and slightly larger homogeneous lymph nodes were common around the lesions.

Purpose To investigate the clinicopathologic,immunophenotypic features,genetic alterations and prognosis of melanotic Xp11 neoplasms/melanotic TFE3-rearrangement neo-plasms.Methods Five cases were selected from the Depart-ment of Pathology,Union Hospital,Huazhong University of Sci-ence and Technology from November 2018 to July 2023.The clinicopathologic,immunohistochemical,FISH assays,next-generation sequencing(NGS)and follow-up details were collect-ed.Results There were 1 male and 4 females,with their ages ranging from 16 to 59 years(mean 28.2 years).The maximum diameters of the masses were 3-6 cm(average 4.7 cm).The tumors located in right kidneys(3 cases),tubal interstitium(1 case)and pelvis(1 case).Microscopically,most tumors shared similar morphology such as nested,acinar structures sep-arated by a delicate vascular network.Epithelioid tumor cells presented with clear to granular eosinophilic cytoplasm.Lym-phocytic infiltration was seen in the background;melanin depo-sition was noted in the cases;neoplastic necrosis was detected in 4 cases.Mitotic activity was low with 5 cases showing＜3/10 HPF.Intravascular tumor thrombus was detected in 2 cases,no lymphovascular and nerve invasions were detected in other 3 ca-ses.Immunohistochemically,all 5 cases expressed TFE3 dif-fusely,and expressed HMB45,Melan A to varying degrees,CK(AE1/AE3),CK7,EMA,PAX8,TFEB,S-100,SOX10,SMA,desmin were all non-reactive in the 5 cases.The Ki67-la-beling index was＜20％.TFE3 separation signal in 4 cases were detected by FISH,1 case was interpreted as negative due to atypical signal which was confirmed by next-generation se-quencing(NGS)assay as RBM10-TFE3.Clinical follow-up was available for five patients for 2-60 months,in which four pa-tients were alive with no evidence of disease after initial resec-tion,and one patient with thoracic spine metastasis was currently in stable condition.Conclusion Melanotic Xp1 1 neoplasms/melanotic TFE3-rearrangement neoplasms has unique morpholog-ic,immunophenotypic and genetic characteristics.It might be reclassified into a distinctive malignant mesenchymal tumor enti-ty.

Objective To explore the clinical efficacy and influencing factors of omadacycline(OMC)in the treat-ment of patients with infectious diseases.Methods Data about hospitalized patients who received OMC monothera-py or combination therapy at Xiangya Hospital of Central South University from January 2022 to December 2023 were analyzed retrospectively.The influencing factors for failure of OMC treatment was analyzed by univariate and multivariate logistic regression analysis.Results A total of 160 patients were included in analysis,with an overall effective treatment rate of 69.4％(n=111).After treatment with OMC,patients in effective group was observed that body temperature improved([36.83±0.52]℃ vs[37.85±0.92]℃,P＜0.001),white blood cell count([7.78±4.07]× 109/L vs[10.06±6.49]× 109/L,P＜0.001),procalcitonin([0.63±1.19]ng/mL vs[4.43±10.14]ng/mL,P=0.001),C-reactive protein([35.16±37.82]mg/L vs[105.08±99.47]mg/L,P＜0.001),and aspartate aminotransferase([50.50±40.04]U/L vs[77.17±91.43]U/L,P=0.004)all decreased signifi-cantly.Only one patient had adverse reactions such as diarrhea,but treatment was not interrupted.Univariate ana-lysis showed that patients in failure treatment group had a higher acute physiology and chronic health evaluation Ⅱ(APACHE Ⅱ)score(17.0[9.5-22.0]vs 12.0[9.0-19.0],P=0.046)and sequential organ failure assessment(SOFA)score(7.0[4.5-10.0]vs 4.0[2.0-9.0],P=0.019).Multivariate analysis showed that end-stage liver disease(OR=77.691,95％CI:5.448-1 107.880,P=0.001),mechanical ventilation(OR=6.686,95％CI:1.628-27.452,P=0.008)and the combination treatment of vancomycin(OR=6.432,95％CI:1.891-21.874,P=0.003)were risk factors for the failure of OMC treatment,while the course of OMC treatment(OR=0.905,95％CI:0.825-0.994,P=0.037)was a protective factor for the effective treatment.Conclusion OMC can be used as an alternative therapy for refractory severe infection,with fewer adverse reaction.End-stage liver disease,mechanical ventilation and combination treatment of vancomycin are risk factors for failure of OMC treatment in in-fected patients.Adequate OMC treatment course can improve patients'clinical outcome,large-scale case studies are needed to confirm the initial conclusion.

Objective To describe the changing trend and related factors of prevalence rates of healthcare-associa-ted infection(HAI)in a tertiary hospital in the past 10 years,and analyze the influencing factors for HAI.Methods A cross-sectional survey on HAI was conducted for 10 consecutive years from 2013 to 2022(one day was selected as the survey day each year),data were collected.The distribution and related factors of prevalence rates of HAI were analyzed by trend-x2 test and Pearson correlation coefficient.Multivariate logistic regression and multilayer percep-tron(MLP)models were constructed to analyze the independent effect and significance of factors.Results From 2013 to 2022,the prevalence rates of HAI ranged from 4.66％to 8.07％in this hospital,showing a linear upward trend.The proportions of ICU patients and utilization rate of central venous catheters within 2 days before the sur-vey showed linear upward trends,while the proportion of patients with urinary catheters within 2 days before the survey and proportion of patients undergoing surgery within 30 days before the survey decreased.The MLP model revealed that the top 3 important factors for HAI were length of hospital stay＞10 days,admission in ICU,and in-dwelling central venous catheters within 2 days before the survey.Multivariate logistic regression model indicated that length of hospital stay＞10 days,indwelling central venous catheters or urinary catheters within 2 days before the survey,surgery within 30 days before the survey,and admission in ICU were independent influencing factors for HAI.Conclusion The incidence of HAI in this hospital presents a linear increase in recent 10 years,the causes should be further analyzed and the direction of intervention should be determined through targeted surveillance.Adopting trend test statistical analysis method,logistic regression,MLP multi-factor model can further explore the data value of HAI prevalence survey.

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.