OBJECTIVE To explore the clinical characteristics of Mycoplasma pneumoniae pneumonia(MPP)after COVID-19 epidemic so as to offer help for early clinical diagnosis and treatment.METHODS The clinical data that were collected from the MPP patients who were treated in the fever clinic of the First Medical Center of Chinese PLA General Hospital from Jul.2023 to Aug.2024 were retrospectively analyzed.The results of laboratory tests for the different age groups of patients complicated with other pathogens were statistically analyzed.RESULTS Of totally 161 MPP patients who were enrolled in the study,78(48.85％)were male,and 83(51.55％)were fe-male;the average age was(32.98±14.35)years old,and the patients aged between 20 and 40 years old accoun-ted for 43.48％(70 cases).The enrolled patients were divided into the simple MPP group with 92(57.14％)ca-ses and the MPP+mixed group with 69(42.86％)cases according to the result of etiological test of sputum;the patients of MPP+mixed group were divided into the MPP+bacteria group with 42(60.87％)cases,the MPP+fungi group with 10(14.49％)cases,and the MPP+viruses group with 17(24.64％)cases.There was significant difference in the age among the groups(P＜0.05);there were no significant differences in the sex,white blood cell counts and percentage of mononuclear cells among the groups,the percentage of lymphocytes was highest in the simple MPP group,the levels of C-reactive protein(CRP)and interleukin-6(IL-6)were highest in the MPP+bacteria group,and there were significant differences(P＜0.05).All of the patients were divided into three groups:the ≤20-year-old group the＞20-40-year old group and the＞40-year-old group.There were no sig-nificant differences in the white blood cell counts,percentage of lymphocytes,percentage of mononuclear cells and IL-6 level among the three groups,and the CRP level was highest in the＞20-40-year old group(P=0.025).Ran-dom forest model analysis showed that the weight of CRP was highest(22.65％)among the clinical characteristics of the MPP patients,which played a key role in construction of model.As for other factors,the weight of age was 17.02％,the percentage of lymphocytes 15.34％,the white blood cells counts 14.86％,the percentage of mono-nuclear cells 14.39％,the IL-6 13.61％,the gender 2.13％.CONCLUSION MPP maintains common among the patients aged less than 40 years old after the COVID-19 epidemic,nearly half of the patients are complicated with the infections of other pathogens,and CRP is more helpful for the clinical diagnosis and treatment of the MPP in early stage.

OBJECTIVE To summarize the clinical characteristics and diagnosis and treatment experiences in dealing with non-severe Chlamydia psittaci pneumonia.METHODS The clinical data were collected from 34 patients who were diagnosed with non-severe C.psittaci pneumonia through quantitative polymerase chain reactiong(qPCR)for sputum in fever clinic of the First Medical Center of Chinese PLA General Hospital from Mar.2023 to Mar.2024 and were retrospectively analyzed.The clinical characteristics and treatment outcomes were evaluated.RESULTS The average age of the patients was(44.82±13.74)years old,the ratio of male to female was 1∶1.83;all of the patients had fever;major symptoms were cough(70.59％),pharyngodynia(44.12％),and flu-like symptoms(41.18％);82.35％of the patients had the history of contact with poultry.The C-reactive pro-tein(CRP)level,interleukin-6(IL-6),systemic inflammatory response index(SIRI)and aggregate index of sys-temic inflammation(AISI)were higher among the patients aged no less than 44 years old than among the patients less than 44 years old(P＜0.05);the percentage of lymphocytes of the patients aged no less than 44 years old was lower than that of the patients aged less than 44 years old(P＜0.05).As for the imaging findings,73.53％of the patients had consolidation shadows,26.47％had ground-glass opacities,and 32.35％involved both lungs.All of the patients received quinolones or tetracyclines for treatment of 7-14 days and all symptoms relieved.CT reexami-nated 1 month after the treatment showed that 55.88％of the cases had complete absorption of pulmonary infec-tious lesions,and 35.29％had partial absorption.CONCLUSIONS The patients with non-severe Chlamydia psitta-ci pneumonia are characterized by the history of contact with poultry,fever complicated with respiratory tract symptoms,rise of inflammatory markers(more significant among patients of advanced age)and lower lobe con-solidation shadow/ground-glass opacities.Early identification and standardized treatment may facilitate the favora-ble treatment outcomes.

OBJECTIVE To explore the clinical characteristics of Mycoplasma pneumoniae pneumonia(MPP)after COVID-19 epidemic so as to offer help for early clinical diagnosis and treatment.METHODS The clinical data that were collected from the MPP patients who were treated in the fever clinic of the First Medical Center of Chinese PLA General Hospital from Jul.2023 to Aug.2024 were retrospectively analyzed.The results of laboratory tests for the different age groups of patients complicated with other pathogens were statistically analyzed.RESULTS Of totally 161 MPP patients who were enrolled in the study,78(48.85％)were male,and 83(51.55％)were fe-male;the average age was(32.98±14.35)years old,and the patients aged between 20 and 40 years old accoun-ted for 43.48％(70 cases).The enrolled patients were divided into the simple MPP group with 92(57.14％)ca-ses and the MPP+mixed group with 69(42.86％)cases according to the result of etiological test of sputum;the patients of MPP+mixed group were divided into the MPP+bacteria group with 42(60.87％)cases,the MPP+fungi group with 10(14.49％)cases,and the MPP+viruses group with 17(24.64％)cases.There was significant difference in the age among the groups(P＜0.05);there were no significant differences in the sex,white blood cell counts and percentage of mononuclear cells among the groups,the percentage of lymphocytes was highest in the simple MPP group,the levels of C-reactive protein(CRP)and interleukin-6(IL-6)were highest in the MPP+bacteria group,and there were significant differences(P＜0.05).All of the patients were divided into three groups:the ≤20-year-old group the＞20-40-year old group and the＞40-year-old group.There were no sig-nificant differences in the white blood cell counts,percentage of lymphocytes,percentage of mononuclear cells and IL-6 level among the three groups,and the CRP level was highest in the＞20-40-year old group(P=0.025).Ran-dom forest model analysis showed that the weight of CRP was highest(22.65％)among the clinical characteristics of the MPP patients,which played a key role in construction of model.As for other factors,the weight of age was 17.02％,the percentage of lymphocytes 15.34％,the white blood cells counts 14.86％,the percentage of mono-nuclear cells 14.39％,the IL-6 13.61％,the gender 2.13％.CONCLUSION MPP maintains common among the patients aged less than 40 years old after the COVID-19 epidemic,nearly half of the patients are complicated with the infections of other pathogens,and CRP is more helpful for the clinical diagnosis and treatment of the MPP in early stage.

Objective To explore the predictive efficacy of several multimodal MRI-based machine learning models for the promoter methylation states of O6-methylguanine-DNA methyltransferase(MGMT)of glioblastoma muliforme(GBM)patients in terms of the GBM heterogeneity and the complexity of the tumor microenvironment.Methods Firstly,the multimodal MRI images of 317 GBM patients from The University of Pennsylvania Glioblastoma(UPENN-GBM)dataset were pre-processed,with four sequences involved in including T1-weighted imaging(T1WI)sequence,T1-weighted contrast-enhanced imaging(T1CE)sequence,T2-weighted imaging(T2WI)sequence and fluid-attenuated inversion recovery(FLAIR)sequence,and the radiomics features were extracted for two regions of interest(ROIs)such as the tumor core region and the tumor edema region.Secondly,the data of the 317 GBM patients were randomly divided into a training set(254 cases)and a test set(63 cases),which underwent normalization with Z-scores and feature selection and dimensionality reduction with Lasso regression.Finally,three models were established respectively with particle swarm optimization-support vector machine(PSO-SVM),C-support vector classification(C-SVC)and adaptive boosting(adaptive boosting(Adaboost)algorithms,and the predictive efficacy of the three models for glioblastoma multiforme MGMT promoter methylation states were evaluated in terms of accuracy and AUC.Results The Adaboost model based on T2WI sequence and radiomics features of the tumor core region had the highest predictive efficacy with accuracy and AUC values of 67％and 0.74,respectively,higher than those of other combinations of sequences,models and regions of interest.Conclusion The multimodal MRI-based machine learning models can be used for the prediction of glioblastoma multiforme MGMT promoter methylation states,which provides powerful support for personalized treatment and prognostic assessment of GBM.[Chinese Medical Equipment Journal,2025,46(6):7-13]

OBJECTIVE To summarize the clinical characteristics and diagnosis and treatment experiences in dealing with non-severe Chlamydia psittaci pneumonia.METHODS The clinical data were collected from 34 patients who were diagnosed with non-severe C.psittaci pneumonia through quantitative polymerase chain reactiong(qPCR)for sputum in fever clinic of the First Medical Center of Chinese PLA General Hospital from Mar.2023 to Mar.2024 and were retrospectively analyzed.The clinical characteristics and treatment outcomes were evaluated.RESULTS The average age of the patients was(44.82±13.74)years old,the ratio of male to female was 1∶1.83;all of the patients had fever;major symptoms were cough(70.59％),pharyngodynia(44.12％),and flu-like symptoms(41.18％);82.35％of the patients had the history of contact with poultry.The C-reactive pro-tein(CRP)level,interleukin-6(IL-6),systemic inflammatory response index(SIRI)and aggregate index of sys-temic inflammation(AISI)were higher among the patients aged no less than 44 years old than among the patients less than 44 years old(P＜0.05);the percentage of lymphocytes of the patients aged no less than 44 years old was lower than that of the patients aged less than 44 years old(P＜0.05).As for the imaging findings,73.53％of the patients had consolidation shadows,26.47％had ground-glass opacities,and 32.35％involved both lungs.All of the patients received quinolones or tetracyclines for treatment of 7-14 days and all symptoms relieved.CT reexami-nated 1 month after the treatment showed that 55.88％of the cases had complete absorption of pulmonary infec-tious lesions,and 35.29％had partial absorption.CONCLUSIONS The patients with non-severe Chlamydia psitta-ci pneumonia are characterized by the history of contact with poultry,fever complicated with respiratory tract symptoms,rise of inflammatory markers(more significant among patients of advanced age)and lower lobe con-solidation shadow/ground-glass opacities.Early identification and standardized treatment may facilitate the favora-ble treatment outcomes.

Objective To explore the predictive efficacy of several multimodal MRI-based machine learning models for the promoter methylation states of O6-methylguanine-DNA methyltransferase(MGMT)of glioblastoma muliforme(GBM)patients in terms of the GBM heterogeneity and the complexity of the tumor microenvironment.Methods Firstly,the multimodal MRI images of 317 GBM patients from The University of Pennsylvania Glioblastoma(UPENN-GBM)dataset were pre-processed,with four sequences involved in including T1-weighted imaging(T1WI)sequence,T1-weighted contrast-enhanced imaging(T1CE)sequence,T2-weighted imaging(T2WI)sequence and fluid-attenuated inversion recovery(FLAIR)sequence,and the radiomics features were extracted for two regions of interest(ROIs)such as the tumor core region and the tumor edema region.Secondly,the data of the 317 GBM patients were randomly divided into a training set(254 cases)and a test set(63 cases),which underwent normalization with Z-scores and feature selection and dimensionality reduction with Lasso regression.Finally,three models were established respectively with particle swarm optimization-support vector machine(PSO-SVM),C-support vector classification(C-SVC)and adaptive boosting(adaptive boosting(Adaboost)algorithms,and the predictive efficacy of the three models for glioblastoma multiforme MGMT promoter methylation states were evaluated in terms of accuracy and AUC.Results The Adaboost model based on T2WI sequence and radiomics features of the tumor core region had the highest predictive efficacy with accuracy and AUC values of 67％and 0.74,respectively,higher than those of other combinations of sequences,models and regions of interest.Conclusion The multimodal MRI-based machine learning models can be used for the prediction of glioblastoma multiforme MGMT promoter methylation states,which provides powerful support for personalized treatment and prognostic assessment of GBM.[Chinese Medical Equipment Journal,2025,46(6):7-13]

Objective To establish a reliable prediction model for radiation pneumonitis(RP)based on multi-regional radiomics analysis of localizable CT images.Methods A retrospective analysis was conducted on 185 patients who received radiotherapy from January 2021 to June 2023 in the Department of Radiotherapy,Xuzhou Cancer Hospital.Patients were classified as having RP or not based on imaging combined with clinical diagnosis.Three regions of interest(ROI)were defined in the localizable CT images:Lung,Lung-PTV and PTV,and their radiomics features were extracted.After feature screening using methods such as Mann-Whitney Utest,recursive feature elimination,and Lasso,a prediction model was established using support vector machine classification algorithm.The model performance was validated using 6 evaluation metrics:the area under the receiver operating characteristic curve(AUC),accuracy,specificity,sensitivity,positive predictive value,and negative predictive value.Results The prediction model consisted of 7 radiomics features.The clinical model of target-to-lung ratio,PTV model,Lung model,and Lung-PTV model achieved AUC values of 0.535,0.801,0.672,and 0.706 in the test set,respectively.The AUC value and accuracy of PTV model reached 0.843 and 0.775 in the training set,while 0.801 and 0.750 in the test set.PTV model was superior to Lung model,Lung-PTV model,and clinical model in predictive performance.The AUC values of the combined PTV+(Lung-PTV)model in the training and test sets were 0.867 and 0.806,respectively,higher than those of PTV model and Lung-PTV model.Conclusion The predictive ability of the prediction models constructed from radiomics features in different ROI for symptomatic RP varies.The radiomics prediction model using PTV as ROI exhibits superior predictive performance,and the combined multi-regional radiomics model can further improve the predictive ability for RP.

Objective To establish a reliable prediction model for radiation pneumonitis(RP)based on multi-regional radiomics analysis of localizable CT images.Methods A retrospective analysis was conducted on 185 patients who received radiotherapy from January 2021 to June 2023 in the Department of Radiotherapy,Xuzhou Cancer Hospital.Patients were classified as having RP or not based on imaging combined with clinical diagnosis.Three regions of interest(ROI)were defined in the localizable CT images:Lung,Lung-PTV and PTV,and their radiomics features were extracted.After feature screening using methods such as Mann-Whitney Utest,recursive feature elimination,and Lasso,a prediction model was established using support vector machine classification algorithm.The model performance was validated using 6 evaluation metrics:the area under the receiver operating characteristic curve(AUC),accuracy,specificity,sensitivity,positive predictive value,and negative predictive value.Results The prediction model consisted of 7 radiomics features.The clinical model of target-to-lung ratio,PTV model,Lung model,and Lung-PTV model achieved AUC values of 0.535,0.801,0.672,and 0.706 in the test set,respectively.The AUC value and accuracy of PTV model reached 0.843 and 0.775 in the training set,while 0.801 and 0.750 in the test set.PTV model was superior to Lung model,Lung-PTV model,and clinical model in predictive performance.The AUC values of the combined PTV+(Lung-PTV)model in the training and test sets were 0.867 and 0.806,respectively,higher than those of PTV model and Lung-PTV model.Conclusion The predictive ability of the prediction models constructed from radiomics features in different ROI for symptomatic RP varies.The radiomics prediction model using PTV as ROI exhibits superior predictive performance,and the combined multi-regional radiomics model can further improve the predictive ability for RP.

Objective To investigate the impact of county-level"Unified ECG Network"construction on the treatment efficiency and clinical outcomes of patients with acute ST-segment elevation myocardial infarction(STEMI).Methods A retrospective analysis was conducted on the clinical data of STEMI patients from Beichuan County and Yanting County in Mianyang City,and Jiange County in Guangyuan City,Sichuan Province,during the 18 months before(128 cases)and 18 months after(187 cases)the establishment of the"Unified ECG Network."Differences in demographic characteristics,treatment efficiency,therapeutic methods,and clinical outcomes between the two groups were compared.Results There was no statistically significant difference in general demographic characteristics between the two groups(all P＞0.05).Compared with the pre-construction group,the post-construction group showed significantly shorter times in initial ECG completion[5(3,7)min vs.6(4,8)min],initial ECG diagnosis[3(2,4)min vs.5(2,6)min],first medical contact to preliminary diagnosis[10(9,12)min vs.13(11,15)min],network hospital door-in-door-out time[21(19,23)min vs.26(23,30)min],and first medical contact to wire-crossing time[(94.82±11.87)min vs.(107.97±18.39)min](allP＜0.001).The proportion of patients bypassing the emergency department and coronary care unit significantly increased(64.17％vs.32.81％,P＜0.001).The proportion of patients undergoing emergency percutaneous coronary intervention significantly increased(72.73％vs.51.56％,P＜0.001),while the proportions of thrombolytic therapy and non-reperfusion therapy significantly decreased(both P＜0.05).Additionally,in-hospital mortality rate,Killip class≥Ⅱ proportion,incidence of major adverse cardiovascular events,and average length of hospital stay were all significantly reduced(all P＜0.05).There were no statistically significant differences among the three county-level chest pain centers in terms of major treatment efficiency,therapeutic strategies,or clinical outcomes(all P＞0.05).Conclusions The construction of the county-level"Unified ECG Network"can significantly improve the treatment efficiency of STEMI patients,optimize reperfusion therapy strategies,improve clinical outcomes,and demonstrate substantial clinical promotion value.

Objective:Previous studies have shown that insomnia is closely related to erectile dysfunction(ED).However,the causal relationship between them is still unclear.Mendelian randomization(MR)provides a new method for studying the relationship between the two,and the theory of heart-kidney interaction in TCM provides a new idea for exploring the causal relationship between them.Methods:Based on the statistical data collected by genome-wide association studies(GWAS),the causal relationship be-tween insomnia and ED was discussed by MR.Inverse variance weighted(IVW)is the main analysis method,and weighted median(WME),simple mode(SM),weighted mode(WM)and MR Egger method were the supplementary analysis to evaluate the causal effect.MR-Egger intercept test,Cochran Q test and leave-one-out method were used in sensitivity analysis to verify the reliability of MR results.Results:Thirty-nine SNPs significantly related to insomnia were finally included for MR analysis.The results of IVW method in MR analysis showed that insomnia had a significant causal relationship with the increased risk of ED(OR=3.111,95％CI=1.566-6.181,P=1.193 × 10-3).The results obtained by MR-Egger method,WME method,WM method and SM method were consistent with IVW method in the direction of effect.The sensitivity results suggested that the results of this study were robust.Conclusion:Our study reveals the causal relationship between insomnia and ED,which provides a new basis for future clinical practice and prevention and treatment of ED.