Objective:To develop and validate a clinical warning model for severe pediatric community-acquired pneumonia (CAP) using electronic health records.Methods:A retrospective cohort study was conducted, analyzing clinical data of 15 750 children hospitalized for CAP at Wuhan Children′s Hospital between January 1, 2019, and December 31, 2023. Patient data were randomly split into training and testing sets at a 7∶3 ratio. Six supervised machine learning models were constructed in the training set, optimized using five-fold cross-validation, and evaluated in the testing set. Model performance was assessed using ROC-AUC, sensitivity, specificity, positive predictive value, negative predictive value, calibration curves, and clinical decision curve analysis at optimal thresholds. The best-performing model was selected, and SHapley Additive exPlanations (SHAP) were used to interpret feature importance. A program interface was developed based on the model results, enabling integration into clinical decision support systems for automated early warning.Results:A total of 15 750 participants, ranging in age from 28 days to 18 years, were included in the study. The median age was 2 years [interquartile range (IQR): 0-4 years], with 9 555 males (60.67%) and 6 195 females (39.33%). Among them, 2 211 (14.04%) developed severe pneumonia. In the prediction models, XGB outperformed other models with an ROC-AUC of 0.884 (95% CI: 0.870-0.898), sensitivity (0.803, 95% CI: 0.772-0.832), specificity (0.828, 95% CI: 0.816-0.839). Calibration analysis showed strong agreement between predicted and observed risks (Brier score: 0.081, 95% CI: 0.075-0.086). The analysis based on the SHAP method revealed that respiratory rate, heart rate, T-lymphocyte subsets, and red blood cell volume distribution width-SD are predictive factors for severe progression of community-acquired pneumonia (CAP) in children. Conclusion:An interpretable machine learning model was developed for the early detection and personalized treatment planning of severe CAP in children, providing valuable support to clinicians.

Objective:To develop and validate a clinical warning model for severe pediatric community-acquired pneumonia (CAP) using electronic health records.Methods:A retrospective cohort study was conducted, analyzing clinical data of 15 750 children hospitalized for CAP at Wuhan Children′s Hospital between January 1, 2019, and December 31, 2023. Patient data were randomly split into training and testing sets at a 7∶3 ratio. Six supervised machine learning models were constructed in the training set, optimized using five-fold cross-validation, and evaluated in the testing set. Model performance was assessed using ROC-AUC, sensitivity, specificity, positive predictive value, negative predictive value, calibration curves, and clinical decision curve analysis at optimal thresholds. The best-performing model was selected, and SHapley Additive exPlanations (SHAP) were used to interpret feature importance. A program interface was developed based on the model results, enabling integration into clinical decision support systems for automated early warning.Results:A total of 15 750 participants, ranging in age from 28 days to 18 years, were included in the study. The median age was 2 years [interquartile range (IQR): 0-4 years], with 9 555 males (60.67%) and 6 195 females (39.33%). Among them, 2 211 (14.04%) developed severe pneumonia. In the prediction models, XGB outperformed other models with an ROC-AUC of 0.884 (95% CI: 0.870-0.898), sensitivity (0.803, 95% CI: 0.772-0.832), specificity (0.828, 95% CI: 0.816-0.839). Calibration analysis showed strong agreement between predicted and observed risks (Brier score: 0.081, 95% CI: 0.075-0.086). The analysis based on the SHAP method revealed that respiratory rate, heart rate, T-lymphocyte subsets, and red blood cell volume distribution width-SD are predictive factors for severe progression of community-acquired pneumonia (CAP) in children. Conclusion:An interpretable machine learning model was developed for the early detection and personalized treatment planning of severe CAP in children, providing valuable support to clinicians.

This paper analyzed the articles from the journal of Chinese Medical Ethics published for 30 years. The results showed that the development of medical ethics in China can be divided into four stages, the incubation period, the slow growth period, the rapid growth period and the stable period;regional distribution was affected by economic development, and the development of medical ethics was also relatively backward in areas where econom-ic development was relatively backward;the number of columns was increasing year by year, the classification tend to be refined, the proportion of each column was fluctuating with the change of the social hotspot, and in recent years, the doctor -patient relationship and medical management and system construction had received more and more attention;and the paper cooperation degree need to be improved, the number of quotations and cited quota-tions steadily improved, and the quality of the paper was improved. Therefore, the government should strengthen policy guidance and standardize the development of medical ethics; the academic level should focus on regional differences and promote academic communication and disciplinary development; and on the individual level, the new medical ethics problem should be concerned, and the research on the hotspots of medical ethics should be car-ried out.

Objective To discuss the informatization of multi hospitals. Methods Considering about the current situation of in‐formation construction to the First Affiliated Hospital of Chongqing Medical University, a set of solution was put forward based on the all in one card together with the two level information platform. Results Initial trials proved the feasibility of the solution. Con‐clusion The informatization of the multi hospitals contributes a lot to the source sharing between the regional hospitals, the im‐provement of hospital management and a better medical service.

Objective To identify and analyze the effective compositions of Schistosoma japonicum 31-32 kDa proteins by using the techniques of proteomics.Methods The total proteins were prepared from 32-day adult worms of Schistosoma japonicum.After two-dimensional(2-D)gel electrophoresis,the distinct protein spots from 2-D gels were isolated and analyzed by MALDI-TOF-MS.Results A total of 13 protein spots,within the range of 31-32 kDa,were detected in the 2-D gels.Three of them had high homology with Actine-2 of S.mansoni,glycerol-3-phosphate dehydrogenase of S.japonicum and cathepsin B endopeptidase of S.mansoni.Conclusions The 31-32 kDa antigens contain 3 important antigens:actine-2,glycerol-3-phosphate dehydrogenase and cathepsin B endopeptidase,which have been demonstrated to have certain protective effect against S.japonicum.Our findings can facilitate the development of multi-epitope vaccine against S.japonicum.