Objective To compare the performance and efficacy of prognostic models constructed by different machine learning algorithms in predicting the survival period of lung transplantation (LTx) recipients. Methods Data from 483 recipients who underwent LTx were retrospectively collected. All recipients were divided into a training set and a validation set at a ratio of 7:3. The 24 collected variables were screened based on variable importance (VIMP). Prognostic models were constructed using random survival forest (RSF) and extreme gradient boosting tree (XGBoost). The performance of the models was evaluated using the integrated area under the curve (iAUC) and time-dependent area under the curve (tAUC). Results There were no significant statistical differences in the variables between the training set and the validation set. The top 15 variables ranked by VIMP were used for modeling and the length of stay in the intensive care unit (ICU) was determined as the most important factor. Compared with the XGBoost model, the RSF model demonstrated better performance in predicting the survival period of recipients (iAUC 0.773 vs. 0.723). The RSF model also showed better performance in predicting the 6-month survival period (tAUC _{6 months} 0.884 vs. 0.809, P = 0.009) and 1-year survival period (tAUC _{1 year} 0.896 vs. 0.825, P = 0.013) of recipients. Based on the prediction cut-off values of the two algorithms, LTx recipients were divided into high-risk and low-risk groups. The survival analysis results of both models showed that the survival rate of recipients in the high-risk group was significantly lower than that in the low-risk group (P<0.001). Conclusions Compared with XGBoost, the machine learning prognostic model developed based on the RSF algorithm may preferably predict the survival period of LTx recipients.

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 explore the impact of socioeconomic status on disability among middle-aged and elderly individuals in China.Methods:This was a retrospective cohort study. At the baseline year of 2011, 14 213 individuals aged 45 years and above from the China Health and Retirement Longitudinal Study were consecutively selected, and their repeated measurement data with complete information from the 4 rounds of follow-up from 2013 to 2020 were consecutively selected, with a total of 67 355 cases included in the analysis. The principal component analysis was used to construct a socioeconomic status index (SESI) and the generalized estimating equation was employed to analyze the association between the SESI and disability in the participants. And the impact of SESI on disability in different age subgroups was further analyzed.Results:Among the 14 213 participants included in the 2011 baseline sample for analysis, there were 6 833 males and 7 380 females, 7 953 aged 45-60 years, 5 156 aged 61-75 years, and 1 104 aged over 75 years. Additionally, there were 3 812 with high SESI, 4 526 with medium SESI, and 5 875 with low SESI. The incidences of disability were greater in the individuals aged>75 years, females, and those with a low SESI (all P<0.05). The risk of incidence of disability in the middle-aged and elderly population increased with decrease of SESI (medium SESI: OR=1.47, 95% CI: 1.39-1.55; low SESI: OR=1.79, 95% CI: 1.69-1.89) (all P<0.001). The difference in the risk of disability in the middle-aged and elderly individuals across the different SESI was greatest at 45-60 years ( OR=2.08, 95% CI: 1.91-2.26), which gradually decreased with increasing age and was smallest at>75 years (OR=1.33, 95% CI: 1.09-1.61) (all P<0.001). Conclusions:The lower the socioeconomic status of China′s middle-aged and elderly individuals, the higher the incidence of disability; the impact of socioeconomic status on risk of disability is more pronounced in the early years of middle and old age and gradually decreases with age.

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 explore the impact of socioeconomic status on disability among middle-aged and elderly individuals in China.Methods:This was a retrospective cohort study. At the baseline year of 2011, 14 213 individuals aged 45 years and above from the China Health and Retirement Longitudinal Study were consecutively selected, and their repeated measurement data with complete information from the 4 rounds of follow-up from 2013 to 2020 were consecutively selected, with a total of 67 355 cases included in the analysis. The principal component analysis was used to construct a socioeconomic status index (SESI) and the generalized estimating equation was employed to analyze the association between the SESI and disability in the participants. And the impact of SESI on disability in different age subgroups was further analyzed.Results:Among the 14 213 participants included in the 2011 baseline sample for analysis, there were 6 833 males and 7 380 females, 7 953 aged 45-60 years, 5 156 aged 61-75 years, and 1 104 aged over 75 years. Additionally, there were 3 812 with high SESI, 4 526 with medium SESI, and 5 875 with low SESI. The incidences of disability were greater in the individuals aged>75 years, females, and those with a low SESI (all P<0.05). The risk of incidence of disability in the middle-aged and elderly population increased with decrease of SESI (medium SESI: OR=1.47, 95% CI: 1.39-1.55; low SESI: OR=1.79, 95% CI: 1.69-1.89) (all P<0.001). The difference in the risk of disability in the middle-aged and elderly individuals across the different SESI was greatest at 45-60 years ( OR=2.08, 95% CI: 1.91-2.26), which gradually decreased with increasing age and was smallest at>75 years (OR=1.33, 95% CI: 1.09-1.61) (all P<0.001). Conclusions:The lower the socioeconomic status of China′s middle-aged and elderly individuals, the higher the incidence of disability; the impact of socioeconomic status on risk of disability is more pronounced in the early years of middle and old age and gradually decreases with age.

Objective To analyze the influencing factors of survival of patients with airway stenosis requiring clinical interventions after lung transplantation. Methods Clinical data of 66 patients with airway stenosis requiring clinical interventions after lung transplantation were retrospectively analyzed. Univariate and multivariate Cox’s regression models were adopted to analyze the influencing factors of survival of all patients with airway stenosis and those with early airway stenosis. Kaplan-Meier method was used to calculate the overall survival and delineate the survival curve. Results For 66 patients with airway stenosis, the median airway stenosis-free time was 72 (52,102) d, 27% (18/66) for central airway stenosis and 73% (48/66) for distal airway stenosis. Postoperative mechanical ventilation time [hazard ratio (HR) 1.037, 95% confidence interval (CI) 1.005-1.070, P=0.024] and type of surgery (HR 0.400, 95%CI 0.177-0.903, P=0.027) were correlated with the survival of patients with airway stenosis after lung transplantation. The longer the postoperative mechanical ventilation time, the higher the risk of mortality of the recipients. The overall survival of airway stenosis recipients undergoing bilateral lung transplantation was better than that of their counterparts after single lung transplantation. Subgroup analysis showed that grade 3 primary graft dysfunction (PGD) (HR 4.577, 95%CI 1.439-14.555, P=0.010) and immunosuppressive drugs (HR 0.079, 95%CI 0.022-0.287, P<0.001) were associated with the survival of patients with early airway stenosis after lung transplantation. The overall survival of patients with early airway stenosis after lung transplantation without grade 3 PGD was better compared with that of those with grade 3 PGD. The overall survival of patients with early airway stenosis after lung transplantation treated with tacrolimus was superior to that of their counterparts treated with cyclosporine. Conclusions Long postoperative mechanical ventilation time, single lung transplantation, grade 3 PGD and use of cyclosporine may affect the survival of patients with airway stenosis after lung transplantation.

Patient safety is the cornerstone of medical quality and an important foundation for a healthy China.In May 2023,the National Health Commission and the National Administration of Traditional Chinese Medicine jointly is-suedthe Action Plan for Comprehensively Improving Medical Quality(2023-2025),which identified patient safety as an important task and special action.It introduces the concept of patient safety,the status quo of patient safety ac-tions at home and abroad,and the research trend of patient safety,and compares the work requirements of patient safety management and special actions in the Action Plan for Comprehensively Improving Medical Quality(2023-2025),and finally puts forward a series of suggestions for formulating the Implementation Plan of Special Ac-tions for Patient Safetywith Chinese characteristics.

This article reviews the overview of digital integration of geriatric patients and related influencing factors, the current situation of smart outpatient service, and the aging measures of smart outpatient service, with a view to providing reference for Chinese scholars to further study digital integration of geriatric patients.

Lung transplantation is the only effective treatment of most end-stage lung diseases. Airway anastomotic complications are the main obstacles affecting the postoperative survival and quality of life of lung transplant recipients. Airway anastomotic stenosis is the most common airway anastomotic complication after lung transplantation. In recent years, improvements in the recipient selection, organ preservation, surgical techniques, postoperative intensive care management, immunosuppression, antifungal and endoscopic treatment have decreased the incidence of airway anastomotic stenosis and improved the surgical efficacy of lung transplantation and the survival of the recipients. In this article, the pathogenesis, risk factors, diagnosis and treatment of airway anastomotic stenosis after lung transplantation were reviewed, aiming to provide novel ideas for clinical research, diagnosis and treatment of airway anastomotic stenosis following lung transplantation.

Objective To evaluate the effect of interleukin (IL)-10 on donor lung function after ex vivo lung perfusion (EVLP) in rats of cardiac death. Methods Twenty adult male SD rats were randomly divided into the simple perfusion group (group A, n=10) and modified perfusion group (group B, n=10). Perfusate A (without IL-10) and perfusate B (supplemented with IL-10) was administered in group A and B, respectively. The EVLP rat models of cardiac death were established. The appearance of donor lung, dry-to-wet (D/W) ratio of donor lung tissues, the function and metabolism of donor lung, the morphology of donor lung and the levels of inflammatory markers of donor lung were statistically compared between two groups. Results After perfusion, evident edema of the whole donor lung, poor compliance and a large amount of edema fluid discharged from the airway were observed in group A, whereas no obvious edema and good compliance were found in group B. Compared with group A, the D/W ratio of lung tissues in group B was higher (P < 0.05). In both groups, the pulmonary vein partial pressure of oxygen reached the peak at 2 h after perfusion, which did not significantly differ between two groups (P > 0.05). In group B, the pulmonary artery pressure was increased at a lower speed and significantly lower after perfusion, and the lactic acid level in the perfusate was significantly lower than those in group A (all P < 0.05). In group A, the alveolar structure was largely destroyed and the cells was rare. In group B, the alveolar structure was relatively normal without evident cell edema. The incidence of cell apoptosis of donor lung was high in group A, whereas no obvious cell apoptosis of donor lung was noted in group B. After perfusion for 4 h, the levels of monocyte chemoattractant protein (MCP)-1 and IL-6 were significantly increased, the IL-4 levels were remarkably decreased (all P < 0.05), but the levels of tumor necrosis factor (TNF)-α, IL-1α and inducible nitric oxide synthase (iNOS) did not significantly change in both groups (all P > 0.05). Conclusions IL-10 may improve the function of donor lung after EVLP in rat of cardiac death by reducing cell apoptosis.