ObjectiveThis paper aims to explore the risk factors for chronic atrophic gastritis （CAG） with turbidity toxin accumulation syndrome and establish a prediction model. MethodsClinical data of 180 patients with CAG who participated in the "clinical study of Xianglian Huazhuo Particles blocking CAG cancer transformation" of Hebei Sheng Zhong Yi Yuan from July 2021 to March 2022 were collected. After confounding factors were controlled by propensity score matching， patients were divided into a training set （namely dev） and a validation set （namely vad） in a seven to three ratio. The risk factors for CAG with turbidity toxin accumulation syndrome in the training set were investigated by using univariate Logistic regression analysis and least absolute shrinkage and selection operator （namely Lasso） regression algorithms. Subsequently， a model， named model 1se， was developed by using the training set data to predict the risk factors for CAG with turbidity toxin accumulation syndrome. The accuracy of the prediction model was assessed by using various methods， including the receiver operating characteristic （ROC） curve， Hosmer-Lemeshow test （H-L）， calibration plot， and decision curve analysis （DCA）. ResultsAge， body mass index （BMI）， family history of cancer， job and life satisfaction， yellow and greasy fur with slippery pulse， and heavy body sensation were independent risk factors of the model. The prediction model showed excellent predictive value for both the training and validation sets. ConclusionThe established prediction model for CAG with turbidity toxin accumulation syndrome has high discrimination and excellent calibration， which could provide an excellent clinical basis for disease diagnosis and individualized treatment of patients.

ObjectiveThis paper aims to explore the risk factors for chronic atrophic gastritis （CAG） with turbidity toxin accumulation syndrome and establish a prediction model. MethodsClinical data of 180 patients with CAG who participated in the "clinical study of Xianglian Huazhuo Particles blocking CAG cancer transformation" of Hebei Sheng Zhong Yi Yuan from July 2021 to March 2022 were collected. After confounding factors were controlled by propensity score matching， patients were divided into a training set （namely dev） and a validation set （namely vad） in a seven to three ratio. The risk factors for CAG with turbidity toxin accumulation syndrome in the training set were investigated by using univariate Logistic regression analysis and least absolute shrinkage and selection operator （namely Lasso） regression algorithms. Subsequently， a model， named model 1se， was developed by using the training set data to predict the risk factors for CAG with turbidity toxin accumulation syndrome. The accuracy of the prediction model was assessed by using various methods， including the receiver operating characteristic （ROC） curve， Hosmer-Lemeshow test （H-L）， calibration plot， and decision curve analysis （DCA）. ResultsAge， body mass index （BMI）， family history of cancer， job and life satisfaction， yellow and greasy fur with slippery pulse， and heavy body sensation were independent risk factors of the model. The prediction model showed excellent predictive value for both the training and validation sets. ConclusionThe established prediction model for CAG with turbidity toxin accumulation syndrome has high discrimination and excellent calibration， which could provide an excellent clinical basis for disease diagnosis and individualized treatment of patients.

Imaging examination is a crucial part in diagnosis and treatment of central nervous system infection(CNSI),involving complex imaging sequences and parameters.This consensus was jointly written by multiple CNSI imaging experts in China,aimed to standardize imaging examination of CNSI.

Objective:To construct a predictive model for postoperative delirium (POD) in patients undergoing gastrointestinal surgery using machine learning.Methods:This retrospective study used clinical data from patients who underwent gastrointestinal surgery at Subei People′s Hospital between September 2022 and April 2024. The entire dataset was randomly divided into the training and validation sets in an 8∶2 ratio. Multivariate logistic regression analysis was conducted to identify the factors influencing POD. Eleven machine learning models were established and compared. The performance of the models was validated using metrics, including accuracy, precision, recall, Youden′s index, F1 score, Matthews′ correlation coefficient, Kappa coefficient, log loss, and Brier score. Receiver operating characteristic and calibration curves were plotted to assess the discrimination and consistency of the model. Shapley additive explanations were used in Python for interpretative analysis of the model with the best predictive performance, and the importance of the feature parameters was ranked.Results:A total of 1, 785 patients were ultimately included, of which 833 (46.67%) experienced POD. The results of multivariate logistic regression analysis revealed that advanced age, lower preoperative serum calcium ion concentration, postoperative pulmonary infection, and higher preoperative systolic blood pressure were independent risk factors for POD in patients undergoing gastrointestinal surgery, while laparoscopic surgery was a protective factor ( P<0.05). Among the 11 machine learning models, the categorical feature gradient boosting model exhibited the best performance, with an area under the receiver operating characteristic curve of 0.82 (95% confidence interval 0.77-0.87). The ranking of feature importance indicated that age had the greatest contribution in predicting POD. Conclusions:The predictive model for POD established based on the categorical boosting algorithm has higher predictive efficacy and clinical application value in patients undergoing gastrointestinal surgery.

Background and Aims:Intrahepatic cholangiocarcinoma(ICC)is a highly malignant liver tumor,with an increasing incidence worldwide,particularly in Asia.Although radical surgical resection is currently the only potentially curative treatment,the high recurrence rate and low postoperative overall survival(OS)rate of ICC remain major clinical challenges.Adjuvant therapy(AT)and neoadjuvant therapy(NAT)are important strategies to reduce postoperative recurrence and prolong OS.Several studies have shown certain efficacy of these treatments.However,the specific efficacy and safety of combined NAT and AT in ICC treatment require further validation.This study was conducted to evaluate the value of combining NAT and AT in improving the therapeutic outcomes of ICC patients through a multicenter retrospective analysis,so as to provide scientific evidence for optimizing treatment strategies.Methods:The clinicopathologic data of 576 patients with ICC who underwent radical resection and were pathologically confirmed from 13 hospitals in China between December 2011 and December 2017 were retrospectively collected.Patients were grouped based on their treatment modality:NAT+AT group,AT group,and non-NAT/AT group.The three patient groups were matched pairwise in a 1∶1 ratio using propensity score matching(PSM)to balance baseline data.The Kaplan-Meier method was used to analyze OS and disease-free survival(DFS),and subgroup analyses were conducted according to the 8th edition of the AJCC TNM staging system.Results:A total of 395 ICC patients were included in the final analysis,with 42 patients(10.6%)in the NAT+AT group,62 patients(15.7%)in the AT group,and 291 patients(73.7%)in the non-NAT/AT group.Before PSM,significant differences were observed between groups in terms of CA19-9,liver function Child-Pugh classification,intraoperative blood loss,surgical margin,differentiation grade,vascular invasion,ECOG score,and lymph node dissection ratio(all P<0.05).After PSM,there were no significant differences in baseline characteristics between the groups(all P>0.05).After matching,the median OS and DFS in the NAT+AT group were significantly better than in the AT and non-NAT/AT groups(both P<0.05),while there were no significant differences in OS and DFS between the AT and non-NAT/AT groups(both P>0.05).Subgroup analysis showed that in TNM stage I patients,DFS in the NAT+AT group was significantly better than in the non-NAT/AT group(P<0.05),but OS was not significantly different(P>0.05).In TNM stage Ⅱ and Ⅲ patients,both OS and DFS in the NAT+AT and AT groups were significantly better than in the non-NAT/AT group(both P<0.05),and DFS in the NAT+AT group was significantly better than in the AT group in TNM stage Ⅲ patients(P<0.05).Conclusion:NAT combined with AT provides better survival benefits for patients with locally advanced ICC,but its benefit for early-stage ICC patients is limited.However,the retrospective design and sample size limitations of this study may affect the stability of the results,and future large-sample,multicenter,prospective studies are needed for further validation.

Objective To retrospectively analyze multicenter data from domestic sources, aiming to explore the link between intrahepatic cholangiocarcinoma (ICC) tumor size and prognosis, establishing a classification system based on tumor size. Methods Between December 2011 and September 2018, 280 ICC patients from 13 hospitals were included. The tumor size prognosis cutoff was identified by the minimum P-value method, and the classification's overall survival related effectiveness was assessed by Kaplan-Meier analysis. Results All 280 patients were divided into the group of tumor maximum diameter ≤4 cm and >4 cm. Tumor size was confirmed as an independent prognosis factor by multivariate COX regression analysis (HR=2.110, 95% CI: 1.358-3.280). Conclusions The tumor size dichotomy classification system based on the Chinese patient group can expediently predict ICC prognosis and offers an important basis for selecting post-operative individualized adjuvant therapy and follow up plans.

To analyze the epidemiological characteristics of COVID-19 in Fujian Province from the 49th week of 2022 to the 5th week of 2023,after further optimization of China's COVID-19 prevention and control measures on December 7,2022(the 49th week of 2022),this study used multi-dimensional surveillance data to dynamically assess population infection levels and their changing trends.The aim of the study was to provide a scientific basis for early warning of epidemic risk,medical resource allocation,and evalu-ation of socio-economic impact.A multi-source data surveillance system was constructed,encompassing surveillance of fever clinics at medical institutions(weekly collection of visits,positive nucleic acid and antigen test results,inpatients,and severe cases in sec-ondary or above hospitals),population nucleic acid test monitoring(weekly person-times and positivity rates of single-tube tests from the provincial system),sentinel hospital monitoring(weekly proportion of influenza-like illness visits at 18 sentinel hospitals and re-lated viral testing data),and monitoring of novel coronavirus variants(weekly systematic collection of genomic sequences of local and imported cases).Line charts were plotted weekly,and time series analysis,molecular epidemiological methods,and an improved SEIAR model were used to simulate epidemic spread.During the study period,the COVID-19 epidemic in Fujian Province exhibited three distinct stages.In the infection peak stage(52nd week of 2022),the provincial fever clinic visits reached 606 893 person-times,and a 49.2%positivity rate in population single-tube nucleic acid tests and 63.8%positivity rate in sentinel hospital monitoring were observed.In the medical load peak stage(2nd week of 2023),274 460 inpatients and 28 487 severe cases were recorded.In the epidemic decline stage(4th to 5th weeks of 2023),fever clinic visits decreased by 96.3%with respect to the peak,the single-tube nucleic acid test positivity rate decreased to 6.3%,and the sentinel hospital COVID-19 nucleic acid test positivity rate was 6.4%.All 508 sequenced local cases were Omicron variants,predominantly BA.5.2 and its sub-lineages(67.4%).Among 56 imported se-quenced cases,BA.5.2 and its sub-lineages accounted for 50.0%,and 16.1%comprised nine variants of interest including XBB and BQ.The model predicted the infection peak in the 52nd week of 2022,whereas the hospitalization peak lagged by approximately 10.6 days.Multi-source data monitoring revealed a three-stage development of the COVID-19 epidemic in Fujian.The BA.5.2 strain was dominant during the epidemic.The combination of multi-source monitoring data and modeling provides important references for epi-demic prevention and control,and highlights the need to improve the monitoring system in follow-up.

Background and Aims:Intrahepatic cholangiocarcinoma(ICC)is a highly malignant liver tumor,with an increasing incidence worldwide,particularly in Asia.Although radical surgical resection is currently the only potentially curative treatment,the high recurrence rate and low postoperative overall survival(OS)rate of ICC remain major clinical challenges.Adjuvant therapy(AT)and neoadjuvant therapy(NAT)are important strategies to reduce postoperative recurrence and prolong OS.Several studies have shown certain efficacy of these treatments.However,the specific efficacy and safety of combined NAT and AT in ICC treatment require further validation.This study was conducted to evaluate the value of combining NAT and AT in improving the therapeutic outcomes of ICC patients through a multicenter retrospective analysis,so as to provide scientific evidence for optimizing treatment strategies.Methods:The clinicopathologic data of 576 patients with ICC who underwent radical resection and were pathologically confirmed from 13 hospitals in China between December 2011 and December 2017 were retrospectively collected.Patients were grouped based on their treatment modality:NAT+AT group,AT group,and non-NAT/AT group.The three patient groups were matched pairwise in a 1∶1 ratio using propensity score matching(PSM)to balance baseline data.The Kaplan-Meier method was used to analyze OS and disease-free survival(DFS),and subgroup analyses were conducted according to the 8th edition of the AJCC TNM staging system.Results:A total of 395 ICC patients were included in the final analysis,with 42 patients(10.6%)in the NAT+AT group,62 patients(15.7%)in the AT group,and 291 patients(73.7%)in the non-NAT/AT group.Before PSM,significant differences were observed between groups in terms of CA19-9,liver function Child-Pugh classification,intraoperative blood loss,surgical margin,differentiation grade,vascular invasion,ECOG score,and lymph node dissection ratio(all P<0.05).After PSM,there were no significant differences in baseline characteristics between the groups(all P>0.05).After matching,the median OS and DFS in the NAT+AT group were significantly better than in the AT and non-NAT/AT groups(both P<0.05),while there were no significant differences in OS and DFS between the AT and non-NAT/AT groups(both P>0.05).Subgroup analysis showed that in TNM stage I patients,DFS in the NAT+AT group was significantly better than in the non-NAT/AT group(P<0.05),but OS was not significantly different(P>0.05).In TNM stage Ⅱ and Ⅲ patients,both OS and DFS in the NAT+AT and AT groups were significantly better than in the non-NAT/AT group(both P<0.05),and DFS in the NAT+AT group was significantly better than in the AT group in TNM stage Ⅲ patients(P<0.05).Conclusion:NAT combined with AT provides better survival benefits for patients with locally advanced ICC,but its benefit for early-stage ICC patients is limited.However,the retrospective design and sample size limitations of this study may affect the stability of the results,and future large-sample,multicenter,prospective studies are needed for further validation.

To analyze the epidemiological characteristics of COVID-19 in Fujian Province from the 49th week of 2022 to the 5th week of 2023,after further optimization of China's COVID-19 prevention and control measures on December 7,2022(the 49th week of 2022),this study used multi-dimensional surveillance data to dynamically assess population infection levels and their changing trends.The aim of the study was to provide a scientific basis for early warning of epidemic risk,medical resource allocation,and evalu-ation of socio-economic impact.A multi-source data surveillance system was constructed,encompassing surveillance of fever clinics at medical institutions(weekly collection of visits,positive nucleic acid and antigen test results,inpatients,and severe cases in sec-ondary or above hospitals),population nucleic acid test monitoring(weekly person-times and positivity rates of single-tube tests from the provincial system),sentinel hospital monitoring(weekly proportion of influenza-like illness visits at 18 sentinel hospitals and re-lated viral testing data),and monitoring of novel coronavirus variants(weekly systematic collection of genomic sequences of local and imported cases).Line charts were plotted weekly,and time series analysis,molecular epidemiological methods,and an improved SEIAR model were used to simulate epidemic spread.During the study period,the COVID-19 epidemic in Fujian Province exhibited three distinct stages.In the infection peak stage(52nd week of 2022),the provincial fever clinic visits reached 606 893 person-times,and a 49.2%positivity rate in population single-tube nucleic acid tests and 63.8%positivity rate in sentinel hospital monitoring were observed.In the medical load peak stage(2nd week of 2023),274 460 inpatients and 28 487 severe cases were recorded.In the epidemic decline stage(4th to 5th weeks of 2023),fever clinic visits decreased by 96.3%with respect to the peak,the single-tube nucleic acid test positivity rate decreased to 6.3%,and the sentinel hospital COVID-19 nucleic acid test positivity rate was 6.4%.All 508 sequenced local cases were Omicron variants,predominantly BA.5.2 and its sub-lineages(67.4%).Among 56 imported se-quenced cases,BA.5.2 and its sub-lineages accounted for 50.0%,and 16.1%comprised nine variants of interest including XBB and BQ.The model predicted the infection peak in the 52nd week of 2022,whereas the hospitalization peak lagged by approximately 10.6 days.Multi-source data monitoring revealed a three-stage development of the COVID-19 epidemic in Fujian.The BA.5.2 strain was dominant during the epidemic.The combination of multi-source monitoring data and modeling provides important references for epi-demic prevention and control,and highlights the need to improve the monitoring system in follow-up.

Objective:To construct a predictive model for postoperative delirium (POD) in patients undergoing gastrointestinal surgery using machine learning.Methods:This retrospective study used clinical data from patients who underwent gastrointestinal surgery at Subei People′s Hospital between September 2022 and April 2024. The entire dataset was randomly divided into the training and validation sets in an 8∶2 ratio. Multivariate logistic regression analysis was conducted to identify the factors influencing POD. Eleven machine learning models were established and compared. The performance of the models was validated using metrics, including accuracy, precision, recall, Youden′s index, F1 score, Matthews′ correlation coefficient, Kappa coefficient, log loss, and Brier score. Receiver operating characteristic and calibration curves were plotted to assess the discrimination and consistency of the model. Shapley additive explanations were used in Python for interpretative analysis of the model with the best predictive performance, and the importance of the feature parameters was ranked.Results:A total of 1, 785 patients were ultimately included, of which 833 (46.67%) experienced POD. The results of multivariate logistic regression analysis revealed that advanced age, lower preoperative serum calcium ion concentration, postoperative pulmonary infection, and higher preoperative systolic blood pressure were independent risk factors for POD in patients undergoing gastrointestinal surgery, while laparoscopic surgery was a protective factor ( P<0.05). Among the 11 machine learning models, the categorical feature gradient boosting model exhibited the best performance, with an area under the receiver operating characteristic curve of 0.82 (95% confidence interval 0.77-0.87). The ranking of feature importance indicated that age had the greatest contribution in predicting POD. Conclusions:The predictive model for POD established based on the categorical boosting algorithm has higher predictive efficacy and clinical application value in patients undergoing gastrointestinal surgery.