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 systematically evaluate the current status of research on the development of indicators for entrustable professional activities (EPAs) of residents in China.Methods:We searched the China National Knowledge Infrastructure, Wanfang Data, Airiti Library, PubMed, Embase, and Web of Science databases for literature on the development of EPA indicators for residents in China published between January 1, 2005 and February 28, 2025. Two researchers independently screened the literature and extracted data, followed by descriptive analysis. The quality of the studies was assessed using the Joanna Briggs Institute critical appraisal tool for expert opinion. Quantitative data were presented as medians (ranges) and qualitative data were presented as frequencies (percentages).Results:A total of eight articles were included, in which two general EPA indicator systems and six specialty-specific EPA indicator systems were developed for residents. The overall quality of the research was high, with the main shortcomings related to the methods used in the process of constructing the consensus indicators. The number of experts recruited ranged from 22 to 45, with 100.00% response rate, high authority coefficients (0.820-0.914), and high coordination coefficients (0.157-0.741). Most of the studies used literature reviews as one source for the indicator pool (8 studies, 100.00%), employed the Delphi method to reach consensus (6 studies, 75.00%), and provided inclusion criteria for the indicators (7 studies, 87.50%). However, only one study (12.50%) explored the practical application of the developed indicators, and none of the studies set indicator weights or conducted quality assessments. The number of EPA indicators developed ranged from 10 to 38 per study. The reporting of EPA indicators was included in most studies regarding titles (8 studies, 100.00%) and the expected levels of entrustment at various stages of training (6 studies, 75.00%), but the reporting on other aspects was lacking. Among the specialty-specific EPA indicators, 38.39% overlapped with the general EPAs indicators.Conclusions:The research on the development of EPA indicators for residents in China is still in its early stages, and there is room for improvement in methodological quality and reporting coverage. There is partial overlap between specialty-specific and general EPA indicators, failing to fully reflect the unique characteristics of different specialties.

Objective:To compare the accuracy of a Chinese large language model (LLM) and radiologists in Chinese middle level professional qualification examination of radiology, and evaluate the quality of answer reasoning provided by the Chinese LLM.Methods:In this study, 100 high-quality questions were selected using stratified random sampling to form a test set. We asked the ERNIE Bot by dialogues on the website to provide the correct answers and answer reasoning for these questions. These questions were also answered by 15 radiologists with different levels of experience. The accuracy of Chinese LLM and that of radiologists were compared. Two radiologists evaluated the quality of answer reasoning using a 5-point semi-quantitative scale.Results:The accuracy of ERNIE Bot was 60.00%, which was lower than the median (interquartile) accuracy of 67.00% (64.00%, 73.00%) for radiologists, and the difference was statistically significant ( W=2.47, P=0.013). The word count of the reasoning provided by Ernie Bot was (196.44±99.25) words, with no significant difference in word count between correct and incorrect answer reasoning, which were (211.03±107.53) words and (174.55±81.84) words, respectively ( t=1.82, P=0.072). Among the correct answers, the quality of reasoning was scored as follows: 1 point for 3 questions, 2 points for 9 questions, 3 points for 12 questions, and 4 points for 36 questions. No reasoning received a score of 5. Conclusions:Chinese LLM demonstrates a certain level of medical knowledge and clinical reasoning ability, which can assist clinical teachers in educational activities. However, it is not yet able to independently tutor residents and lacks the ability of invitational and heuristic teaching.

Objective:To investigate the current status of Chinese-foreign cooperative education programs for medical majors, and to discuss the potential problems and development trends of this field.Methods:Related data were collected from the information platform of Chinese-Foreign Cooperation in Running Schools by Ministry of Education of the People's Republic of China, and the characteristics of Chinese-foreign cooperative education programs for medical majors were extracted for analysis. Categorical data were expressed as frequency (percentage), and continuous data were expressed as mean±standard deviation.Results:A total of 83 Chinese-foreign cooperative education programs for medical majors were included in the study, accounting for only 3.45% (83/2 406) of all programs. Chinese partners in these cooperative programs were mainly from East China (41 programs, 49.40%), while foreign partners were mainly from Europe (39 programs, 46.99%). The mean duration of these programs was (3.61±0.88) years, with an enrollment of (87.08±35.52) students. Most of the students were included in National General Higher Education Enrollment Plan (79 programs, 95.18%), and the main majors included nursing (39 programs, 46.99%), medical technology (19 programs, 22.89%), and clinical medicine (11 programs, 13.25%), with the main enrollment level of junior college (45 programs, 54.22%). Chinese partners in the cooperative programs mainly issued academic certificate (45 programs, 54.22%) or academic certificate plus degree certificate (36 programs, 43.37%), while most foreign partners did not issue such certificates (44 programs, 53.01%).Conclusions:There are several problems in Chinese-foreign cooperative education programs for medical majors, such as a limited number of programs, a significant regional difference, an imbalanced distribution of specialties, a low level of education, and inconsistency in issuance of certificates, which still requires further improvement and standardization. However, there are also high-level and high-quality programs for reference.

Objective To investigate the association between gut microbiota metabolite,trimethy-lamine-N-oxide(TMAO),and total imaging burden in diabetic patients with cerebral small vessel disease(CSVD).Methods A prospective study was conducted on 112 elderly diabetic patients with CSVD admitted in our hospital from June 2022 to May 2024.According to the total imaging burden score,they were divided into a high burden group(burden score≥2,57 cases)and a low burden group(burden score＜2,55 cases).High-performance liquid chromatography with online electrospray ionization tandem mass spectrometry was applied to detect the plasma level of TMAO.Then based on the tertile of plasma TMAO level,the patients were also assigned into low(＜2.44 μmol/L,38 cases),median(2.44 μmol/L≤TMAO＜5.18 μmol/L,37 cases)and high TMAO(≥5.18 μmol/L,37 cases)groups.ROC curve analysis was used to assess the predictive value of plasma TMAO level for high imaging burden in diabetic patients with CSVD.Binary logistic regression analysis was employed to analyze the correlation between plasma TMAO level and high imaging burden.Results The high burden group exhibited significantly higher plasma TMAO level than the low burden group(P=0.002).The AUC value of plasma TMAO level in predicting high imaging burden was 0.669(95％CI:0.569-0.769,P=0.002).The percentage of high imaging burden was 34.2％,54.1％and 64.9％,respectively among the low,median and high TMAO groups,with significant differences among them(Chi-square=7.270,P=0.026).Binary logistic regression analysis indicated the correlation between TMAO and high imaging burden(OR=1.178,95％CI:1.019-1.364,P=0.027).Conclusion In elderly diabetic patients with CSVD,plasma TMAO level is closely associated with high imaging burden,with higher TMAO level,higher risk for high imaging burden.

Objective To investigate the clinical application of ceftazidime/avibactam(CAZ/AVI)in lung trans-plant recipients with pulmonary infection caused by carbapenem-resistant Gram-negative bacilli(CRGNB),and ana-lyze the factors affecting the prognosis.Methods Lung transplant recipients who had CRGNB pulmonary infection and were treated with CAZ/AVI were included in the analysis.Based on 14-day clinical response,14-day microbial response,and 30-day survival status,the recipients were divided into a clinical response group and a clinical failure group,a microbial response group and a microbial failure group,as well as a survival group and a death group,re-spectively.Univariate analysis was conducted on various data from the two groups.Factors affecting therapeutic ef-ficacy and survival were included in a binary logistic regression model.Independent risk factors for CAZ/AVI anti-infective efficacy and all-cause mortality outcomes were analyzed.Results A total of 43 recipients were included.After 14-day anti-infective treatment,32 recipients(74.42％)achieved clinical response,and 30 recipients(69.77％)achieved microbial response.34 recipients(79.07％)survived 30 days after CAZ/AVI treatment.The Charlson comorbidity index(CCI),proportion of renal dysfunction,and incidence of shock in recipients in the clini-cal response group were all lower than those in the clinical failure group(P＜0.05),while the serum albumin(ALB)level was higher(P＜0.05).The incidence of shock in recipients in the microbial response group was lower than that in the microbial failure group(P＜0.05).CCI,proportion of renal dysfunction,and incidence of shock in recipients in the survival group were all lower than those in the death group(all P＜0.05),while ALB level was higher during treatment period(P＜0.05).Multivariate analysis of 14-day clinical response and 30-day survival showed that higher CCI was an independent risk factor affecting 14-day clinical response of recipients(OR=2.22,95％CI:1.07-4.63),while lower ALB levels(OR=0.72,95％CI:0.54-0.98)and higher CCI(OR=5.27,95％CI:1.18-23.58)were independent risk factors for 30-day all-cause mortality in recipients with pulmonary in-fection after lung transplant.Conclusion CAZ/AVI may be an effective drug for treating pulmonary infection caused by CRGNB in lung transplant recipients.Higher CCI is an independent risk factor for 14-day clinical failure in recipients after CAZ/AVI treatment.Lower ALB level and higher CCI are independent risk factors for increased 30-day mortality in recipients.

Perioperative rehabilitation aims to alleviate symptoms,restore function,and improve quality of life.These goals largely involve subjective patient experiences,which are not fully captured by traditional outcome measures.In recent years,patient-reported outcomes(PROs)have emerged as essential tools to quantify patients'perceptions of health and have been widely used in drug and device clinical trials.This review summarizes the current applications of PROs in general surgery,including symptom description,comparison of surgical methods,complication warning,and patient management.Practical cases and evidence from domestic and international studies are discussed.With the integration of electronic PROs(ePROs),artificial intelligence,and natural language processing,future efforts should focus on developing localized,specialty-specific tools and establishing stronger correlations between PROs and clinical outcomes to support the transition from disease-centered to patient-centered surgical care.

Objective To explore the application of artificial intelligence quantitative analysis in the prognostic assessment of patients with connective tissue disease-associated interstitial lung disease(CTD-ILD).Methods A total of 67 patients with CTD-ILD were retrospectively selected.All subjects underwent high-resolution computed tomography(HRCT)scanning and were categorized into three groups,namely mild,moderate and severe groups,based on the results of pulmonary function tests.The survival rates of patients in each group were compared using Kaplan-Meier curves and analysis of variance.The univariate analysis was employed to assess the rela-tionships between artificial intelligence parameters and patient prognosis.Significant results were then incorporated into a multifacto-rial Cox regression model to construct the most accurate predictive model.Results A significant difference in survival rate was observed among the three groups(P<0.05).Univariate analysis revealed that the volume and percentage of lung infection in deceased patients were significantly greater than those in surviving patients,while the lung volume in deceased patients was significantly smaller than that in surviving patients.The analysis showed left lung volume and the percentage of lesion components CT value≤-750 HU as risk factors for prognosis,and the combination of these two factors as the most effective predictive model.Conclusion The artificial intelligence analysis system for lung lesions provides a new systematic and quantitative method for the prognostic assessment of CTD-ILD patients,which can be used for the prognostic assessment and follow-up of CTD-ILD patients.

Perioperative rehabilitation aims to alleviate symptoms,restore function,and improve quality of life.These goals largely involve subjective patient experiences,which are not fully captured by traditional outcome measures.In recent years,patient-reported outcomes(PROs)have emerged as essential tools to quantify patients'perceptions of health and have been widely used in drug and device clinical trials.This review summarizes the current applications of PROs in general surgery,including symptom description,comparison of surgical methods,complication warning,and patient management.Practical cases and evidence from domestic and international studies are discussed.With the integration of electronic PROs(ePROs),artificial intelligence,and natural language processing,future efforts should focus on developing localized,specialty-specific tools and establishing stronger correlations between PROs and clinical outcomes to support the transition from disease-centered to patient-centered surgical care.

Objective To explore the application of artificial intelligence quantitative analysis in the prognostic assessment of patients with connective tissue disease-associated interstitial lung disease(CTD-ILD).Methods A total of 67 patients with CTD-ILD were retrospectively selected.All subjects underwent high-resolution computed tomography(HRCT)scanning and were categorized into three groups,namely mild,moderate and severe groups,based on the results of pulmonary function tests.The survival rates of patients in each group were compared using Kaplan-Meier curves and analysis of variance.The univariate analysis was employed to assess the rela-tionships between artificial intelligence parameters and patient prognosis.Significant results were then incorporated into a multifacto-rial Cox regression model to construct the most accurate predictive model.Results A significant difference in survival rate was observed among the three groups(P<0.05).Univariate analysis revealed that the volume and percentage of lung infection in deceased patients were significantly greater than those in surviving patients,while the lung volume in deceased patients was significantly smaller than that in surviving patients.The analysis showed left lung volume and the percentage of lesion components CT value≤-750 HU as risk factors for prognosis,and the combination of these two factors as the most effective predictive model.Conclusion The artificial intelligence analysis system for lung lesions provides a new systematic and quantitative method for the prognostic assessment of CTD-ILD patients,which can be used for the prognostic assessment and follow-up of CTD-ILD patients.