ObjectiveThis study systematically analyzed the arginine metabolic dysregulation in the rat model of heart failure （HF）， providing a modern scientific basis for elucidating the pathogenesis of HF and offering new insights for the prevention and treatment of HF with traditional Chinese medicine （TCM）. MethodsA thoracotomy was performed to ligate the left anterior descending coronary artery of rats， which induced acute myocardial ischemia and thus led to the development of post-myocardial infarction heart failure. The rats were divided into a sham surgery group and a model group， with eight rats in each group. Serum targeted metabolomics analysis was performed using ultra-performance liquid chromatography-triple quadrupole mass spectrometry （UPLC-TQ-S）， and the spatial distribution of metabolites in cardiac tissue was observed using airflow-assisted desorption electrospray ionizationmass spectrometry imaging （AFADESI-MSI）. Targets associated with HF and arginine metabolism were screened from databases including GeneCards and the Gene Expression Omnibus （GEO）， a protein-protein interaction （PPI） network was constructed， and enrichment analysis of the Kyoto Encyclopedia of Genes and Genomes （KEGG） pathway and Gene Ontology （GO） was performed. Finally， molecular docking was conducted to verify the binding between core metabolic components and key targets， and potential TCMs were predicted based on the core pathways and targets. ResultsCompared with the sham surgery group， the levels of arginine and citrulline in the serum of model rats were significantly decreased （P<0.01）， while those of proline， ornithine， creatine， creatinine and glutamate were significantly increased （P<0.05， P<0.01）. Cardiac mass spectrometry imaging showed a decreased abundance of arginine in the local myocardial tissue. Bioinformatics analysis identified 24 core functional targets， such as the angiotensin-converting enzyme （ACE）， neuronal nitric oxide synthase （NOS1）， 5-hydroxytryptamine receptor 2A （HTR2A）， and epidermal growth factor receptor （EGFR）， and enrichment analysis indicated that these targets were significantly involved in the calcium signaling pathway， neuroactive ligand-receptor interactions， and phosphatidylinositol signaling pathway. Molecular docking confirmed strong binding activities between arginine， citrulline and HTR2A， as well as between creatine， creatinine and EGFR. Based on pathway-target prediction， potential TCM interventions， such as ginseng and magnolia， were identified. ConclusionThis study revealed characteristic arginine metabolic disorder in HF， and the core targets of HF were closely associated with the phosphatidylinositol signaling pathway. It provides a modern biological interpretation of the pathogenesis of HF in TCM from the perspectives of metabolites and signaling pathways， and offers valuable insights for targeted therapy of HF and the development of TCM.

ObjectiveThis study systematically analyzed the arginine metabolic dysregulation in the rat model of heart failure （HF）， providing a modern scientific basis for elucidating the pathogenesis of HF and offering new insights for the prevention and treatment of HF with traditional Chinese medicine （TCM）. MethodsA thoracotomy was performed to ligate the left anterior descending coronary artery of rats， which induced acute myocardial ischemia and thus led to the development of post-myocardial infarction heart failure. The rats were divided into a sham surgery group and a model group， with eight rats in each group. Serum targeted metabolomics analysis was performed using ultra-performance liquid chromatography-triple quadrupole mass spectrometry （UPLC-TQ-S）， and the spatial distribution of metabolites in cardiac tissue was observed using airflow-assisted desorption electrospray ionizationmass spectrometry imaging （AFADESI-MSI）. Targets associated with HF and arginine metabolism were screened from databases including GeneCards and the Gene Expression Omnibus （GEO）， a protein-protein interaction （PPI） network was constructed， and enrichment analysis of the Kyoto Encyclopedia of Genes and Genomes （KEGG） pathway and Gene Ontology （GO） was performed. Finally， molecular docking was conducted to verify the binding between core metabolic components and key targets， and potential TCMs were predicted based on the core pathways and targets. ResultsCompared with the sham surgery group， the levels of arginine and citrulline in the serum of model rats were significantly decreased （P<0.01）， while those of proline， ornithine， creatine， creatinine and glutamate were significantly increased （P<0.05， P<0.01）. Cardiac mass spectrometry imaging showed a decreased abundance of arginine in the local myocardial tissue. Bioinformatics analysis identified 24 core functional targets， such as the angiotensin-converting enzyme （ACE）， neuronal nitric oxide synthase （NOS1）， 5-hydroxytryptamine receptor 2A （HTR2A）， and epidermal growth factor receptor （EGFR）， and enrichment analysis indicated that these targets were significantly involved in the calcium signaling pathway， neuroactive ligand-receptor interactions， and phosphatidylinositol signaling pathway. Molecular docking confirmed strong binding activities between arginine， citrulline and HTR2A， as well as between creatine， creatinine and EGFR. Based on pathway-target prediction， potential TCM interventions， such as ginseng and magnolia， were identified. ConclusionThis study revealed characteristic arginine metabolic disorder in HF， and the core targets of HF were closely associated with the phosphatidylinositol signaling pathway. It provides a modern biological interpretation of the pathogenesis of HF in TCM from the perspectives of metabolites and signaling pathways， and offers valuable insights for targeted therapy of HF and the development of TCM.

Objective:To investigate the prognostic factors for esophageal cancer after radical resection and the application value of machine learning prediction model.Methods:The retrospective cohort study was conducted. The clinicopatholigical data of 406 esophageal cancer patients who were admitted to Qilu Hospital of Shandong University from January 2018 to March 2022 were collected. There were 357 males and 49 females, aged (64±8)years. All patients underwent radical resection of esophageal cancer. The 406 patients were randomly divided into a training set of 285 cases and a validation set of 121 cases at a 7∶3 ratio based on a random number table. The training set was used to construct prediction model, and the validation set was used to validate prediction model. Patients were divided into high-risk group and low-risk group based on risk scores. Observation indicators: (1) follow-up of patients and analysis of influencing factors for prognosis; (2) construction and validation of machine learning prediction models. Comparison of measurement data with normal distribution between groups was conducted using the independent sample t test. Comparison of measurement data with skewed distribution between groups was conducted using the Mann-Whitney U test. Comparison of count data between groups was conducted using the chi-square test. Comparison of ordinal data between groups was conducted using the rank sum test. The Kaplan-Meier method was used to calculate survival rate and plot survival curve, and the Log-rank test was used for survival analysis. The Cox proportional hazard regression model was used for univariate and multivariate analyses. Independent influencing factors were included, and data processing, machine learning model construction, and visualization were performed using R packages including random survival forest (RSF), gradient boosting machine (GBM), least absolute shrinkage and selection operator Cox regression (LASSO-Cox), Cox proportional hazards model boosting (CoxBoost), survival support vector machine (survivalsvm), extreme gradient boosting (XGBoost), supervised principal component analysis (SuperPC), and Cox partial least squares regression (plsRcox). Receiver operating characteristic (ROC) curves were drawn, and sensitivity, specificity, and area under the curve (AUC) were calculated. The Delong test was used to assess the differences in AUC among different models in the training set, and the time-dependent ROC was used to compare the predictive performance of different models. Calibration curves were used to evaluate model accuracy, and decision curve analysis (DCA) was used to evaluate overall net benefit. Results:(1) Follow-up of patients and analysis of influencing factors for prognosis. All 406 patients were followed up postoperatively for 28(range, 6-36)months, with 1- and 3-year overall survival rate of 86.5% and 40.9%, respectively. The 285 patients in the training set were followed up postoperatively for 30(range, 6-36)months, with 1- and 3-year overall survival rate of 85.1% and 35.5%, respectively. The 121 patients in the validation set were followed up postoperatively for 25(range, 6-36)months, with 1- and 3-year overall survival rate of 87.0% and 43.2%, respectively. There was no significant difference in postoperative overall survival rate between the training set and the validation set ( χ2=3.20, P>0.05). Results of multivariate analysis showed that left thoracic surgical approach, preopera-tive neutrophil count, vascular invasion, perineural invasion, pathological T2-4 stage, pathological N2-3 stage, and postoperative pneumonia were independent risk factors affecting postoperative survival of 285 patients in the training set ( hazard ratio=1.466, 1.037, 1.482, 1.549, 5.268, 7.727, 22.202, 2.539, 2.686, 1.425, 95% confidence interval as 1.026-2.096, 1.003-1.073, 1.008-2.179, 1.105-2.170, 1.201-23.099, 1.833-32.576, 4.734-104.128, 1.577-4.087, 1.631-4.422, 1.018-1.994, P<0.05). (2) Construction and validation of machine learning prediction models. Independent risk factors affecting postoperative survival were included to construct RSF, GBM, LASSO-Cox, CoxBoost, survivalsvm, XGBoost, SuperPC, and plsRcox machine learning prediction models. Results of Delong test showed that there were significant differences in the AUC of RSF and GBM from the other six models ( P<0.05). Results of time-dependent ROC curve showed that all 8 machine learning predic-tion models had good discriminative ability in the training cohort, among which the RSF machine learning prediction model had the best predictive performance. Results of calibration curve showed that the RSF machine learning prediction model fitted well for predicting postoperative 1-, 2-, and 3-year overall survival in the training cohort, with high consistency with actual results. Results of decision curve analysis showed that within a threshold range of 0-0.80, the RSF machine learning prediction model provided a better overall net benefit. Further analysis showed that in the validation set, the AUC of RSF machine learning prediction model for postoperative 1-, 2-, and 3-year survival prediction were 0.786 (95% confidence interval as 0.609-0.962), 0.774 (95% confidence interval as 0.676-0.873), and 0.750 (95% confidence interval as 0.652-0.848), respectively. Results of calibration curve showed that the RSF machine learning prediction model fitted well for predicting postopera-tive 1-, 2-, and 3-year overall survival in the validation set, with high consistency with actual results. In the training set, the optimal cutoff value of the RSF machine learning prediction model risk score was 11.7. Patients with risk score ≥11.7 were classified as the high-risk group, and those with risk score <11.7 as the low-risk group. The median survival times of the two groups were 18.0 months and >36.0 months, respectively, showing a significant difference between them ( χ2=73.30, P<0.05). In the validation set, the optimal cutoff value of the RSF machine learning prediction model risk score was 11.7. Patients with risk score ≥11.7 were classified as the high-risk group, and those with risk score<11.7 as the low-risk group. The median survival times of the two groups were 17.0 months and>36.0 months for the high-risk and low-risk groups, respectively, showing a significant difference between them ( χ2=35.20, P<0.05). Conclusions:Left thoracic surgical approach, preoperative neutrophil count, vascular invasion, perineural invasion, pathological T2-4 stage, pathological N2-3 stage, and postoperative pneumonia are independent risk factors affecting survival of esophageal cancer patients after radical resection. The RSF machine learning prediction model constructed based on these factors can effectively distinguish the survival prognosis of high-risk and low-risk patients.

Objective:To summarize the clinical features of Chlamydia pneumoniae pneumonia (CPP) in children. Methods:Case series study. Clinical data of 10 children with CPP hospitalized in Department No.2 of Respiratory Medicine of Beijing Children′s Hospital, Capital Medical University from January 2019 to August 2024 were retrospectively collected, including general information, clinical manifestations, chest imaging, laboratory examination and treatment. The clinical features and prognosis were summarized.Results:Among the 10 children with CPP, 7 were male and 3 were female. The age of onset was 11.2 (10.3, 13.1) years. The course were 17 (7, 23) days. Cough occurred in 9 cases with wet cough in 7 cases, while moderate and high fever occurred in 6 cases. Besides, chest pain occurred in 4 cases, rash and hemoptysis occurred in 1 case respectively. High density mass shadow was found in 7 cases chest CT imaging, accompanied by air bronchogram sign, surrounded by halo sign, 6 cases of which were distributed under the pleura, while patchy consolidation in the remaining 3 cases. Pulmonary embolism was present in 2 cases. Among the 10 children with CPP, bilateral lung involvement was found in 3 cases and unilateral lung involvement in 7 cases. The white blood cell count was 10.21 (7.45, 11.64)×10 9/L and the proportion of neutrophils was 0.69 (0.63, 0.71). C-reactive protein increased in 7 cases, with the level of 33 (16, 77) mg/L. D-dimer increased slightly in 3 cases (0.393, 0.396, 0.739 mg/L). Serum Chlamydia pneumoniae-IgM antibody test was positive in 6 cases. Chlamydia pneumoniae nucleic acid test by bronchoalveolar lavage fluid (BALF) next-generation sequencing was positive in 6 cases. Both serum IgM antibody and BALF nucleic acid tests were positive in 2 cases. Among the 10 children with CPP, azithromycin alone was used in 5 cases, while glucocorticoid was added in 1 case. Due to poor response to azithromycin in 4 cases, doxycycline was replaced in 3 cases and minocycline was replaced in 1 case, while glucocorticoid was added in 2 cases. Moxifloxacin combined with glucocorticoid therapy was adopted in 1 case with long course after the poor response to azithromycin and doxycycline. All patients were cured finally. Conclusions:CPP mostly occurs in elderly children. The main clinical manifestations include cough, fever and chest pain. The common chest imaging feature is subpleural high-density mass shadow with halo sign. Pulmonary embolism is present in a few cases. Nucleic acid detection and (or) serology is helpful for etiological diagnosis. Some cases need glucocorticoid therapy.

Intestinal fibrosis is a major complication of inflammatory bowel disease (IBD), leading to a high incidence of surgical interventions and significant disability. Despite its clinical relevance, no targeted pharmacological therapies are currently available. This review aims to explore the underlying mechanisms driving intestinal fibrosis and address unresolved scientific questions, offering insights into potential future therapeutic strategies. We conducted a literature review using data from PubMed up to October 2024, focusing on studies related to IBD and fibrosis. Intestinal fibrosis results from a complex network involving stromal cells, immune cells, epithelial cells, and the gut microbiota. Chronic inflammation, driven by factors such as dysbiosis, epithelial injury, and immune activation, leads to the production of cytokines like interleukin (IL)-1β, IL-17, and transforming growth factor (TGF)-β. These mediators activate various stromal cell populations, including fibroblasts, pericytes, and smooth muscle cells. The activated stromal cells secrete excessive extracellular matrix components, thereby promoting fibrosis. Additionally, stromal cells influence the immune microenvironment through cytokine production. Future research would focus on elucidating the temporal and spatial relationships between immune cell-driven inflammation and stromal cell-mediated fibrosis. Additionally, investigations are needed to clarify the differentiation origins of excessive extracellular matrix-producing cells, particularly fibroblast activation protein (FAP) + fibroblasts, in the context of intestinal fibrosis. In conclusion, aberrant stromal cell activation, triggered by upstream immune signals, is a key mechanism underlying intestinal fibrosis. Further investigations into immune-stromal cell interactions and stromal cell activation are essential for the development of therapeutic strategies to prevent, alleviate, and potentially reverse fibrosis.
Humans ; Fibrosis/metabolism* ; Inflammatory Bowel Diseases/pathology* ; Animals ; Transforming Growth Factor beta/metabolism* ; Intestines/pathology*

Objective:To explore the risk factors for bronchiolitis obliterans (BO) after Mycoplasma pneumoniae bronchiolitis in children. Methods:A retrospective cohort study was conducted on 122 children diagnosed with Mycoplasma pneumoniae bronchiolitis in Department No.2 of Respiratory Medicine of Beijing Children′s Hospital, Capital Medical University, from March 2017 to December 2024. Clinical data, including general information, clinical manifestations, imaging findings, laboratory tests, and outcomes, were analyzed. Patients were divided into BO and non-BO groups based on the presence of BO. Differences between groups were assessed using Mann-Whitney U test, χ2 test, or Fisher exact test. Logistic regression and receiver operating characteristic (ROC) curve analysis were employed to identify risk factors and evaluate predictive performance. Results:Among 122 children (73 males, 49 females), the age at onset was 5.0 (2.4, 7.1) years. The BO group included 21 patients, and the non-BO group 101. The BO group exhibited significantly longer durations of persistent high fever and higher peak levels of C-reactive protein, lactate dehydrogenase, and D-dimer compared to the non-BO group (9 (7, 11) vs. 4 (2, 6) d, 19 (7, 35) vs. 10 (7, 18) mg/L, 438 (337, 498) vs. 315 (274, 351) U/L, 0.36 (0.27, 0.91) vs. 0.21 (0.15, 0.29) mg/L, U=295.00, 743.50, 463.50, 470.50, all P<0.05). The BO group also had higher proportions of resting oxygen saturation <0.95 on room air (100.0% (21/21) vs. 43.6% (44/101)), inspiratory retractions (57.1% (12/21) vs. 18.8% (19/101), χ2=11.53), and adenovirus co-infection (38.1% (8/21) vs. 5.0% (5/101)) (all P<0.05). Multivariate Logistic regression identified prolonged high fever ( OR=1.83, 95% CI 1.31-2.58, P<0.001), inspiratory retractions ( OR=10.48, 95% CI 1.72-63.85, P=0.011), and adenovirus co-infection ( OR=42.47, 95% CI 4.04-446.87, P=0.002) as independent risk factors for BO. ROC curve analysis revealed that a fever duration cutoff of 7.5 days predicted BO with 0.71 sensitivity and 0.92 specificity. Conclusions:Prolonged high fever (≥7.5 days), inspiratory retractions, and adenovirus co-infection are significant predictors of BO after Mycoplasma pneumoniae bronchiolitis in children, which are helpful for early clinical identification.

OBJECTIVE To establish the an optimal prediction model for carbapenem-resistant Acinetobacter bau-mannii(CRAB)infection in ICU patients based on machine learning(ML)so as to help clinicians to diagnose and make decisions.METHODS The clinical data were collected from the patients who were hospitalized in ICUs of a three-A hospital from Jan.1,2017 to Dec.31,2024 and were randomly divided into the training set and the test set in a 7∶3 ratio.The characteristic variables were selected by means of LASSO regression analysis in combina-tion with multivariate logistic regression analysis.Five types of M L classification models were integrated,the opti-mal model was analyzed and identified.The performance of the prediction model for CRAB infection in the ICU patients was evaluated with the use of sensitivity,specificity,accuracy,areas under receiver operating characteris-tic curves(AUCs),calibration curves,Hosmer-Lemeshow test and decision curve analysis(DCA).The outputs of the ML models were interpreted by Shapley additive explanations(SHAP)and permutation importance.RESULTS A total of 2 904 patients were enrolled in the study,695(23.93％)of whom had CRAB infection.The AUC of XGBoost model was highest in the training set and the test set,respectively(0.994 and 0.907).The result of Hosmer-Lemeshow test showed that the calibration curves of the XGBoost model indicated that the predicated risk was highly con-sistent with the observed risk(x2=7.323 and 4.609,P=0.513 and 0.764,respectively).The DCA curves showed that the XGBoost model performed best within the whole range of threshold,with the highest net profit.The length of ICU stay,use of tigecycline,central venous catheterization,use of carbapenems and use of ventilator were determined as the major predictive factors by means of SHAP.CONCLUSIONS The XGBoost model is established and interpreted by SHAP.It provides bases for screening of the ICU patients at high risk of CRAB infection.

OBJECTIVE To establish the an optimal prediction model for carbapenem-resistant Acinetobacter bau-mannii(CRAB)infection in ICU patients based on machine learning(ML)so as to help clinicians to diagnose and make decisions.METHODS The clinical data were collected from the patients who were hospitalized in ICUs of a three-A hospital from Jan.1,2017 to Dec.31,2024 and were randomly divided into the training set and the test set in a 7∶3 ratio.The characteristic variables were selected by means of LASSO regression analysis in combina-tion with multivariate logistic regression analysis.Five types of M L classification models were integrated,the opti-mal model was analyzed and identified.The performance of the prediction model for CRAB infection in the ICU patients was evaluated with the use of sensitivity,specificity,accuracy,areas under receiver operating characteris-tic curves(AUCs),calibration curves,Hosmer-Lemeshow test and decision curve analysis(DCA).The outputs of the ML models were interpreted by Shapley additive explanations(SHAP)and permutation importance.RESULTS A total of 2 904 patients were enrolled in the study,695(23.93％)of whom had CRAB infection.The AUC of XGBoost model was highest in the training set and the test set,respectively(0.994 and 0.907).The result of Hosmer-Lemeshow test showed that the calibration curves of the XGBoost model indicated that the predicated risk was highly con-sistent with the observed risk(x2=7.323 and 4.609,P=0.513 and 0.764,respectively).The DCA curves showed that the XGBoost model performed best within the whole range of threshold,with the highest net profit.The length of ICU stay,use of tigecycline,central venous catheterization,use of carbapenems and use of ventilator were determined as the major predictive factors by means of SHAP.CONCLUSIONS The XGBoost model is established and interpreted by SHAP.It provides bases for screening of the ICU patients at high risk of CRAB infection.

Objective:To investigate the prognostic factors for esophageal cancer after radical resection and the application value of machine learning prediction model.Methods:The retrospective cohort study was conducted. The clinicopatholigical data of 406 esophageal cancer patients who were admitted to Qilu Hospital of Shandong University from January 2018 to March 2022 were collected. There were 357 males and 49 females, aged (64±8)years. All patients underwent radical resection of esophageal cancer. The 406 patients were randomly divided into a training set of 285 cases and a validation set of 121 cases at a 7∶3 ratio based on a random number table. The training set was used to construct prediction model, and the validation set was used to validate prediction model. Patients were divided into high-risk group and low-risk group based on risk scores. Observation indicators: (1) follow-up of patients and analysis of influencing factors for prognosis; (2) construction and validation of machine learning prediction models. Comparison of measurement data with normal distribution between groups was conducted using the independent sample t test. Comparison of measurement data with skewed distribution between groups was conducted using the Mann-Whitney U test. Comparison of count data between groups was conducted using the chi-square test. Comparison of ordinal data between groups was conducted using the rank sum test. The Kaplan-Meier method was used to calculate survival rate and plot survival curve, and the Log-rank test was used for survival analysis. The Cox proportional hazard regression model was used for univariate and multivariate analyses. Independent influencing factors were included, and data processing, machine learning model construction, and visualization were performed using R packages including random survival forest (RSF), gradient boosting machine (GBM), least absolute shrinkage and selection operator Cox regression (LASSO-Cox), Cox proportional hazards model boosting (CoxBoost), survival support vector machine (survivalsvm), extreme gradient boosting (XGBoost), supervised principal component analysis (SuperPC), and Cox partial least squares regression (plsRcox). Receiver operating characteristic (ROC) curves were drawn, and sensitivity, specificity, and area under the curve (AUC) were calculated. The Delong test was used to assess the differences in AUC among different models in the training set, and the time-dependent ROC was used to compare the predictive performance of different models. Calibration curves were used to evaluate model accuracy, and decision curve analysis (DCA) was used to evaluate overall net benefit. Results:(1) Follow-up of patients and analysis of influencing factors for prognosis. All 406 patients were followed up postoperatively for 28(range, 6-36)months, with 1- and 3-year overall survival rate of 86.5% and 40.9%, respectively. The 285 patients in the training set were followed up postoperatively for 30(range, 6-36)months, with 1- and 3-year overall survival rate of 85.1% and 35.5%, respectively. The 121 patients in the validation set were followed up postoperatively for 25(range, 6-36)months, with 1- and 3-year overall survival rate of 87.0% and 43.2%, respectively. There was no significant difference in postoperative overall survival rate between the training set and the validation set ( χ2=3.20, P>0.05). Results of multivariate analysis showed that left thoracic surgical approach, preopera-tive neutrophil count, vascular invasion, perineural invasion, pathological T2-4 stage, pathological N2-3 stage, and postoperative pneumonia were independent risk factors affecting postoperative survival of 285 patients in the training set ( hazard ratio=1.466, 1.037, 1.482, 1.549, 5.268, 7.727, 22.202, 2.539, 2.686, 1.425, 95% confidence interval as 1.026-2.096, 1.003-1.073, 1.008-2.179, 1.105-2.170, 1.201-23.099, 1.833-32.576, 4.734-104.128, 1.577-4.087, 1.631-4.422, 1.018-1.994, P<0.05). (2) Construction and validation of machine learning prediction models. Independent risk factors affecting postoperative survival were included to construct RSF, GBM, LASSO-Cox, CoxBoost, survivalsvm, XGBoost, SuperPC, and plsRcox machine learning prediction models. Results of Delong test showed that there were significant differences in the AUC of RSF and GBM from the other six models ( P<0.05). Results of time-dependent ROC curve showed that all 8 machine learning predic-tion models had good discriminative ability in the training cohort, among which the RSF machine learning prediction model had the best predictive performance. Results of calibration curve showed that the RSF machine learning prediction model fitted well for predicting postoperative 1-, 2-, and 3-year overall survival in the training cohort, with high consistency with actual results. Results of decision curve analysis showed that within a threshold range of 0-0.80, the RSF machine learning prediction model provided a better overall net benefit. Further analysis showed that in the validation set, the AUC of RSF machine learning prediction model for postoperative 1-, 2-, and 3-year survival prediction were 0.786 (95% confidence interval as 0.609-0.962), 0.774 (95% confidence interval as 0.676-0.873), and 0.750 (95% confidence interval as 0.652-0.848), respectively. Results of calibration curve showed that the RSF machine learning prediction model fitted well for predicting postopera-tive 1-, 2-, and 3-year overall survival in the validation set, with high consistency with actual results. In the training set, the optimal cutoff value of the RSF machine learning prediction model risk score was 11.7. Patients with risk score ≥11.7 were classified as the high-risk group, and those with risk score <11.7 as the low-risk group. The median survival times of the two groups were 18.0 months and >36.0 months, respectively, showing a significant difference between them ( χ2=73.30, P<0.05). In the validation set, the optimal cutoff value of the RSF machine learning prediction model risk score was 11.7. Patients with risk score ≥11.7 were classified as the high-risk group, and those with risk score<11.7 as the low-risk group. The median survival times of the two groups were 17.0 months and>36.0 months for the high-risk and low-risk groups, respectively, showing a significant difference between them ( χ2=35.20, P<0.05). Conclusions:Left thoracic surgical approach, preoperative neutrophil count, vascular invasion, perineural invasion, pathological T2-4 stage, pathological N2-3 stage, and postoperative pneumonia are independent risk factors affecting survival of esophageal cancer patients after radical resection. The RSF machine learning prediction model constructed based on these factors can effectively distinguish the survival prognosis of high-risk and low-risk patients.

Objective:To summarize the clinical features of Chlamydia pneumoniae pneumonia (CPP) in children. Methods:Case series study. Clinical data of 10 children with CPP hospitalized in Department No.2 of Respiratory Medicine of Beijing Children′s Hospital, Capital Medical University from January 2019 to August 2024 were retrospectively collected, including general information, clinical manifestations, chest imaging, laboratory examination and treatment. The clinical features and prognosis were summarized.Results:Among the 10 children with CPP, 7 were male and 3 were female. The age of onset was 11.2 (10.3, 13.1) years. The course were 17 (7, 23) days. Cough occurred in 9 cases with wet cough in 7 cases, while moderate and high fever occurred in 6 cases. Besides, chest pain occurred in 4 cases, rash and hemoptysis occurred in 1 case respectively. High density mass shadow was found in 7 cases chest CT imaging, accompanied by air bronchogram sign, surrounded by halo sign, 6 cases of which were distributed under the pleura, while patchy consolidation in the remaining 3 cases. Pulmonary embolism was present in 2 cases. Among the 10 children with CPP, bilateral lung involvement was found in 3 cases and unilateral lung involvement in 7 cases. The white blood cell count was 10.21 (7.45, 11.64)×10 9/L and the proportion of neutrophils was 0.69 (0.63, 0.71). C-reactive protein increased in 7 cases, with the level of 33 (16, 77) mg/L. D-dimer increased slightly in 3 cases (0.393, 0.396, 0.739 mg/L). Serum Chlamydia pneumoniae-IgM antibody test was positive in 6 cases. Chlamydia pneumoniae nucleic acid test by bronchoalveolar lavage fluid (BALF) next-generation sequencing was positive in 6 cases. Both serum IgM antibody and BALF nucleic acid tests were positive in 2 cases. Among the 10 children with CPP, azithromycin alone was used in 5 cases, while glucocorticoid was added in 1 case. Due to poor response to azithromycin in 4 cases, doxycycline was replaced in 3 cases and minocycline was replaced in 1 case, while glucocorticoid was added in 2 cases. Moxifloxacin combined with glucocorticoid therapy was adopted in 1 case with long course after the poor response to azithromycin and doxycycline. All patients were cured finally. Conclusions:CPP mostly occurs in elderly children. The main clinical manifestations include cough, fever and chest pain. The common chest imaging feature is subpleural high-density mass shadow with halo sign. Pulmonary embolism is present in a few cases. Nucleic acid detection and (or) serology is helpful for etiological diagnosis. Some cases need glucocorticoid therapy.