Objective To explore the value of CT-based radiomics and machine learning in predicting the severity of community acquired pneumonia(CAP)in children.Methods The clinical and imaging data of 158 patients diagnosed with CAP in children were analyzed retrospectively.All patients were randomly divided into training set(n=110)and validation set(n=48)in a ratio of 7︰3.Radiomics features were outlined and extracted using 3D Slicer software,and feature selection was achieved using maximum relevance and minimum redundancy(MRMR)and least absolute shrinkage and selection operator(LASSO)algorithms.The construction of the nomogram model and the machine learning combined model was performed by combining clinical features and Radiomics score(Radscore),and its performance was evaluated and validated.Results The area under the curve(AUC)of the clinical model,the radiomics model and the nomogram model in the validation set were classified as 0.82,0.86 and 0.91,respectively.The AUC of the combined multi-layer perceptron(MLP),random forest(RF),and adaptive boosting(ADB)models were 0.926,0.934 and 0.917,respectively in the validation set.Conclusion Radiomics combined with clinical data is expected to be a novel predictor of the severity of CAP in children.MLP,RF and ABD machine learning algorithms can further enable model performance.

Objective To explore the value of a CT radiomics model in differentiating Xpert MTB/RIF-negative pulmonary tuber-culosis(PTB)from non-tuberculous mycobacteria pulmonary disease(NTM-PD).Methods A retrospective analysis was performed on 90 patients with Xpert MTB/RIF-negative PTB and 127 patients with NTM-PD.All patients were randomly divided into training set and testing set at the ratio of 7∶3.Radiomics features were extracted from chest CT images.Feature dimensionality reduction and selection were sequentially performed using the maximum relevance and minimum redundancy(mRMR)algorithm and the least absolute shrinkage and selection operator(LASSO)algorithm.Clinical,radiomics,and combined models were constructed by multi-variable logistic regression.The area under the curve(AUC)of receiver operating characteristic(ROC)curve was utilized to assess the model diagnostic performance.Calibration curves were used to evaluate model stability,and the decision curve analysis(DCA)was used to evaluate the clinical utility.Results The combined model had the highest diagnostic performance in both training and testing sets,with AUC of 0.90 and 0.86,respectively,which were higher than clinical and radiomics models.The calibration curve showed that the combined model had a good consistency between the predicted and the actual observations,and DCA revealed the highest clinical benefit.Conclusion The clinical-radiomics combined model has excellent predictive ability in differentiating Xpert MTB/RIF-negative PTB from NTM-PD,which can provide robust support for clinical diagnosis.

Due to the wide variety and varying quality of medical wound dressings, as well as the current lack of unified national or industry standards for regulation, this paper proposes a research strategy for establishing a quality evaluation system for medical wound dressings‌. By developing a technical roadmap, this strategy clarifies the process flow and key points in the quality evaluation process, establishes evaluation methods for various types of medical wound dressings, and addresses important issues such as how to determine key performance indicators based on product characteristics and how to research and validate test methods for key items. This provides a detailed and feasible research strategy and evaluation method for medical wound dressing manufacturers, testing institutions, and regulatory authorities. It reduces the difficulty and cost of quality evaluation for medical wound dressings and has certain significance in standardizing and improving their quality level, ensuring their safety and effectiveness, and serving the quality and safety regulation of medical devices.‌.
Bandages/standards* ; Quality Control ; Humans ; Wounds and Injuries/therapy*

Objective To explore the value of CT-based radiomics and machine learning in predicting the severity of community acquired pneumonia(CAP)in children.Methods The clinical and imaging data of 158 patients diagnosed with CAP in children were analyzed retrospectively.All patients were randomly divided into training set(n=110)and validation set(n=48)in a ratio of 7︰3.Radiomics features were outlined and extracted using 3D Slicer software,and feature selection was achieved using maximum relevance and minimum redundancy(MRMR)and least absolute shrinkage and selection operator(LASSO)algorithms.The construction of the nomogram model and the machine learning combined model was performed by combining clinical features and Radiomics score(Radscore),and its performance was evaluated and validated.Results The area under the curve(AUC)of the clinical model,the radiomics model and the nomogram model in the validation set were classified as 0.82,0.86 and 0.91,respectively.The AUC of the combined multi-layer perceptron(MLP),random forest(RF),and adaptive boosting(ADB)models were 0.926,0.934 and 0.917,respectively in the validation set.Conclusion Radiomics combined with clinical data is expected to be a novel predictor of the severity of CAP in children.MLP,RF and ABD machine learning algorithms can further enable model performance.

Objective To explore the value of a CT radiomics model in differentiating Xpert MTB/RIF-negative pulmonary tuber-culosis(PTB)from non-tuberculous mycobacteria pulmonary disease(NTM-PD).Methods A retrospective analysis was performed on 90 patients with Xpert MTB/RIF-negative PTB and 127 patients with NTM-PD.All patients were randomly divided into training set and testing set at the ratio of 7∶3.Radiomics features were extracted from chest CT images.Feature dimensionality reduction and selection were sequentially performed using the maximum relevance and minimum redundancy(mRMR)algorithm and the least absolute shrinkage and selection operator(LASSO)algorithm.Clinical,radiomics,and combined models were constructed by multi-variable logistic regression.The area under the curve(AUC)of receiver operating characteristic(ROC)curve was utilized to assess the model diagnostic performance.Calibration curves were used to evaluate model stability,and the decision curve analysis(DCA)was used to evaluate the clinical utility.Results The combined model had the highest diagnostic performance in both training and testing sets,with AUC of 0.90 and 0.86,respectively,which were higher than clinical and radiomics models.The calibration curve showed that the combined model had a good consistency between the predicted and the actual observations,and DCA revealed the highest clinical benefit.Conclusion The clinical-radiomics combined model has excellent predictive ability in differentiating Xpert MTB/RIF-negative PTB from NTM-PD,which can provide robust support for clinical diagnosis.

Objective To establish an HPLC fingerprint of Dingdang Qigui Decoction and analyze and evaluate it using chemical pattern recognition technology;To determine the contents of 5 effective chemical components in Dingdang Qigui Decoction;To provide a basis for its quality control.Methods The analysis was performed on Agilent 5 TC-C18(2)column(250 mm×4.6 mm).The mobile phase comprised of acetonitrile-0.1%phosphoric acid aqueous solution with the gradient elution at a flow rate of 1.0 mL/min.The detection wavelength was set at 260 nm.The column temperature was maintained at 30℃and the injection volume was 10 μL.SPSS 26.0 and SIMCA 14.1 were used to perform clustering analysis and principal component analysis on the 10 batches of Didang Qigui Decoction.The landmark components for inter batch differences were selected through orthogonal partial least squares discriminant analysis(OPLS-DA).Results The HPLC fingerprint with eighteen common peaks of Didang Qigui Decoction in 10 batches of sample was established,and the similarities of samples were between 0.828 and 0.989.Five indicative components were identified and quantitatively analyzed by comparing with the reference substances,which were paeoniflorin,mauroisoflavone glucoside,hesperidin,cinnamaldehyde and aloe rhodopsin.The linear ranges was 10.000 0-320.000 0 μg/mL,2.500 0-80.000 0 μg/mL,10.000 0-320.000 0 μg/mL,10.000 0-320.000 0 μg/mL,0.078 1-5.000 0 μg/mL,respectively,and their mean recovery ranged from 100.30%to 104.09%.Clustering analysis and principal component analysis divided 10 batches of samples from Didang Qigui Decoction into 2 categories.Through OPLS-DA screening,hairy pistil isoflavone glycosides,paeoniflorin,and hesperidin were selected as landmark components for quality differences.Conclusion The quality evaluation method for Didang Qigui Decoction established in this study is simple,sensitive,accurate,and reproducible,which can provide a basis for the quality evaluation of Didang Qigui Decoction.

Objective To investigate the factors influencing the prognosis of complex intracranial aneurysms treated with pipeline flow-directed device(PED)and to develop a nomogram prediction model.Methods The clinical data of a total of 98 patients with complex intracranial aneurysm,who were admitted to the Anyue County People's Hospital or the Second Affiliated Hospital of Guilin Medical College of China from January 2021 to April 2023 to receive PED treatment,were retrospectively analyzed.The influencing factors that might affect the prognosis of patients with complex intracranial aneurysm were collected.According to the modified Rankin Scale(mRS)score,the patients were divided into good prognosis group(being defined as mRS ≤2 points)and poor prognosis group(being defined as mRS＞2 points).The clinical data were compared between the two groups,and a nomogram model was established and validated.Results In the 98 patients,poor prognosis was seen in 10(10.20％).The differences in age,history of hypertension,history of diabetes mellitus,clopidogrel resistance,Fisher classification,repeated aneurysm rupture,aneurysm location,aneurysm size,aneurysm neck,multiple lesions,and Hunt-Hess grade on admission between good prognosis group and poor prognosis group were statistically significant(all P＜0.05).Multivariate analysis revealed that history of hypertension,clopidogrel resistance,repeated aneurysm rupture,aneurysm location,multiple lesions,and Hunt-Hess grade were the independent factors influencing the prognosis of patients with complex intracranial aneurysm after receiving PED treatment.The AUC of the nomogram model in predicting the prognosis of PED for complex intracranial aneurysms was 0.849(95％CI=0.758-0.939).The predicted curves of the model group and validation group were basically fitted to the standard curves.The results of the decision curve analysis showed that the net benefit to patients was greater than 0 when the probability threshold of the nomogram model for predicting a poor prognosis of PED for complex intracranial aneurysms was 0.10-0.90.Conclusion The factors causing poor prognosis of PED for complex intracranial aneurysms mainly include history of hypertension,clopidogrel resistance,repeated aneurysm rupture,etc.The nomogram model established in this study can predict the risk of poor prognosis in patients with complicated intracranial aneurysm after receiving PED treatment.

Objective To investigate the value of CT radiomics models based on intranodal and perinodal in distinguishing pulmonary cryptococcosis(PC)from lung adenocarcinoma.Methods A total of 194 patients,including PC(n=94)and lung adenocarcinoma(n=100),confirmed by surgical or puncture pathology were analyzed retrospectively and randomly divided into training set and test set in a ratio of 7∶3.3D Slicer was used to delineate and extract the intranodal and perinodal volume of interest(VOI)radiomics features within a 5 mm range.The minimum redundancy maximum relevance(mRMR)and least absolute shrinkage and selection operator(LASSO)methods were used to dimensionality reduction.Statistically significant indicators were screened by one-way logistic regression and further incorporated into the multifactor logistic regression model.Support vector machine(SVM)was used to construct the intranodal image-based radiomics model,the perinodal image-based radiomics model,the intranodal-and-perinodal image-based radiomics model,and the combined model.The diagnostic efficacy of each model was evaluated by receiver operating characteristic(ROC)curve.Results In the test set,the area under the curve(AUC)of the clinical imaging model,the intranodal image-based radiomics model,the perinodal image-based radiomics model,the intranodal-and-perinodal image-based radiomics model,and the combined model were 0.84,0.88,0.85,0.90,and 0.94,respectively.Conclusion The combined model based on clinical imaging features,intranodal and perinodal radiomics features can improve the ability of differentiating PC from lung adenocarcinoma.

Objective To explore the CT manifestations and clinical features of checkpoint inhibitor-related pneumonitis(CIP).Methods Chest CT images and clinical data of 34 patients with CIP in Ningbo No.2 Hospitael were collected to retrospectively analysis.According to the site of tumor occurrence,22 patients were divided into lung cancer group and 12 patients in other malignant tumor group,and the differences in CT manifestations between two groups were compared.Results Cough(70.59％)and dyspnea(52.94％)were the common clinical symptoms.CIP occurred earlier and over a greater time span in lung cancer group 114.5(41.50,281.50)d than in other maligment tumor group 144(55.75,226.25)d.Eosinophil count was significantly higher only in other maligment tumor group(P=0.009).After hormonal therapy 18 patients improved,8 were stable and 8 progressed or even died.CT signs were prevalent in ground glass shadow(70.59％)and solid shadow(76.47％),and the imaging pattern was dominated by organic pneumonia pattern(47.6％),which was not related to type of primary tumor,and some of them could show nodular granulomatous reaction.Compared to lung cancer group,the other maligment tumor group was more likely to exhibit symmetrical infiltration(58.33％)distribution.Conclusion The clinical features of CIP are nonspecific,compared with other patients with primary malignancies,lung cancer patients are more likely to develop CIP,which is difficult to relieve after treatment,and are easy to develop severe disease.

Objective To investigate the possible mechanism of myocardial protective effect of Yixin formula in rats with myocardial ischemia-reperfusion injury.Methods Sixty-five rats were randomly divided into 10 in the sham-operated group and 55 in the modeling group;the modeling group was constructed by ligating the left anterior descending branch of the coronary artery,and the sham-operated group was only threaded without ligation.The modeling group was randomly divided into model group,Yixin formula low,medium and high dose group and trimetazidine group after membrane creation.The low,medium and high dose groups of Yixin formula were given 6.84 g·kg-1,13.68 g·kg-1 and 27.36 g·kg-1 of Yixin formula and 5.4 mg·kg-1 of Trimetazidine respectively,and the sham-operated group and the model group were given equal volume of saline by gavage for 7 days in each group.Echocardiography was used to detect the cardiac function of rats;biochemical methods were used to detect serum creatine kinase(CK),lactate dehydrogenase(LDH)and glutamate transaminase(AST);hematoxylin-eosin(HE)staining was used to observe the histopathological changes of rat myocardium;Masson staining was used to observe the degree of myocardial fibrosis;TUNEL staining for myocardial cell apoptosis index;Western blot was performed to detect NLRP3,pro-Caspase-1 and GSDMD-FL、GSDMD-N protein expression in myocardial tissue.Results Compared with the sham-operated group,the model rats showed significantly lower left ventricular ejection fraction(LVEF)and LV short-axis shortening percentage(FS)(P＜0.001),significantly higher myocardial injury markers CK,AST,and LDH(P＜0.001),pathological findings showed myocardial structural damage,interstitial edema with inflammatory cell infiltration,disorganized myocardial fiber arrangement,larger myocardial cell cross-sectional The pathological results showed that myocardial structure was damaged,interstitial edema with inflammatory cell infiltration,disorganized myocardial fiber arrangement,large cross-sectional area of myocardial cells(P＜0.001),significant myocardial collagen fibrosis(P＜0.001),the pyroptosis index of myocardial cells was increased(P＜0.001),and significantly increased NLRP3,pro-Caspase-1,GSDMD-FL,and GSDMD-N protein expression in myocardial tissues(P＜0.001).Compared with the model group,LVE and FS were significantly higher in each dose group of Yixin formula and trimetazidine group(P＜0.05,P＜0.001),myocardial injury markers CK,AST and LDH were significantly decreased(P＜0.05,P＜0.01,P＜0.001),myocardial cell cross-sectional area was reduced(P＜0.05,P＜0.001),myocardial fibrosis was reduced to different degrees(P＜0.001),the apoptosis index of cardiomyocytes was decreased(P＜0.05,P＜0.001),and NLRP3,pro-Caspase-1,and GSDMD protein expression in myocardial tissue was reduced(P＜0.001).Conclusion Yixin formula can reduce myocardial injury and the degree of myocardial fibrosis,and thus improve the cardiac function in rats.and its mechanism may be related to down regulating NLRP3/Caspase-1/GSDMD signaling pathway and inhibiting cardiomyocyte pyroptosis.