Objective To comprehensively investigate the subcomponent characteristics of inhibitory control for children with autism spectrum disorder(ASD)aged 4-5 years under experimental and natural environments.Methods Thirty children with ASD aged 4-5 years and 30 chronological-age and intellectual level-matched typically developing children were recruited.The Simon task,Go/nogo task,and Stroop task were used to examine the conflict response inhibition,prepotent response inhibition,and interference control subcomponents of inhibitory control,respectively.The inhibit subscale of the behavior rating inventory of executive function-preschool version was employed to assess children's inhibition in daily natural situations.Results Under the incongruent condition of the Simon task,there were no significant differences in mean reaction time and accuracy between ASD group and the control group(P>0.05).In the Go/nogo task,the ASD group demonstrated elevated false positive errors compared to the controls[3.10%(0,6.20%)vs.0(0,0.78%),P=0.005].However,there were no significant differences in mean reaction time and false alarm error between ASD group and the control group(P>0.05).In the Stroop task,there were no significant differences in the accuracy and mean reaction time between ASD group and the control group(P>0.05).Additionally,the ASD group scored significantly worse than the controls in the inhibit subscale of BRIEF-P[(60.47±9.63)vs.(54.23±7.45),P=0.007].Conclusions The inhibitory control of children with ASD aged 4-5 years are partially impaired in a structural experimental setting while severely deficient in a natural environment.

Objective:To evaluate the efficacy of lamb′s tripe extract and vitamin B 12 capsule (LTEVB 12C) on chronic atrophic gastritis (CAG) at different locations (antrum lesser curvature, antrum greater curvature, gastric angle, corpus lesser curvature, and corpus greater curvature). Methods:From August 2011 to January 2013, 715 patients with CAG in a multicenter, randomized, double-blind, placebo-controlled trial were enrolled from 16 tertiary first-class hospitals across the country, including the First Affiliated Hospital of Air Force Medical University, Nanfang Hospital of Southern Medical University, the First Hospital of Jilin University, West China Hospital of Sichuan University, etc., there were 476 cases in the LTEVB 12C group and 239 cases in the placebo group. The patients of the LTEVB 12C group received LTEVB 12C, and the patients of placebo group received LTEVB 12C mimetic, all the medications were taken 3 capsules each time and 3 times a day after meals, and the treatment course of 2 groups were both 6 months. The efficacy evaluation criteria included the effective rate (a decrease of ≥1 in histopathological score compared with baseline after 6 months of treatment) and the reversal rate (a decrease of ≥ 2 in histopathological score compared with baseline after 6 months of treatment in the patients with moderate to severe CAG). The impact of lesion sites on the therapeutic effects of LTEVB 12C was analyzed by logistic regression analysis. The two-way unordered Cochran-Mantel-Haenszel chi-square test considering the center effect and Pearson chi-square test were used for statistical analysis. Results:The effective rates of chronic inflammation at the antrum greater curvature and corpus greater curvature (23.3%, 110/473 vs. 13.0%, 31/239; 20.3%, 96/472 vs. 12.6%, 30/239), the effective rates of atrophy at the antrum lesser curvature, antrum greater curvature, gastric angle, corpus lesser curvature, and the corpus greater curvature (27.0%, 118/437 vs. 15.7%, 34/216; 29.2%, 126/432 vs. 18.5%, 38/205; 27.8%, 121/435 vs. 16.7%, 36/216; 32.5%, 127/391 vs. 19.8%, 37/187; 33.0%, 119/361 vs. 21.8%, 39/179), and the effective rates of intestinal metaplasia at the antrum lesser curvature, antrum greater curvature, gastric angle, and the corpus lesser curvature (45.0%, 112/249 vs. 29.8%, 31/104; 53.8%, 86/160 vs. 33.9%, 21/62; 45.8%, 103/225 vs. 24.0%, 25/104; 51.9%, 83/160 vs. 28.3%, 17/60) of the LTEVB 12C group were all higher than those of the placebo group, and the differences were statistically significant ( χ2=10.76, 6.39, 9.69, 7.91, 11.05, 9.62, 8.57, 5.20, 7.11, 12.45, and 6.73; all P<0.05). The reversal rates of chronic inflammation at the corpus lesser curvature and corpus greater curvature (5.2%, 12/231 vs. 0, 0/123; 4.7%, 8/170 vs. 0, 0/88), the reversal rates of atrophy at the antrum lesser curvature, antrum greater curvature, corpus lesser curvature, and the corpus greater curvature (6.8%, 22/323 vs. 1.3%, 2/151; 9.2%, 29/315 vs. 1.4%, 2/144; 14.2%, 38/267 vs. 2.5%, 3/121; 20.8%, 35/168 vs. 5.8%, 4/69), and the reversal rates of intestinal metaplasia at the antrum lesser curvature, antrum greater curvature, gastric angle, and the corpus lesser curvature (29.8%, 39/131 vs. 9.1%, 4/44; 41.0%, 32/78 vs. 12.5%, 3/24; 33.3%, 44/132 vs. 4.8%, 3/63; 50.0%, 37/74 vs. 8.7%, 2/23) of the LTEVB 12C group were all higher than those of the placebo group, and the differences were statistically significant ( χ2=6.58, 5.12, 5.60, 8.61, 11.43, 6.59, 7.30, 4.95, 15.92, 7.62; all P<0.05). There were no statistically significant differences in the effective rates and reversal rates of active inflammation at different locations between the LTEVB 12C group and the placebo group (all P>0.05). The results of logistic regression analysis (taking the antrum lesser curvature as the reference) further confirmed that the reversal rates of chronic inflammation ( OR=0.22, 95% confidence interval (95% CI): 0.07 to 0.67; OR=0.24, 95% CI: 0.07 to 0.80), atrophy ( OR=0.28, 95% CI: 0.16 to 0.49; OR=0.28, 95% CI: 0.16 to 0.49), and intestinal metaplasia ( OR=0.42, 95% CI: 0.24 to 0.77; OR=0.20, 95% CI: 0.08 to 0.52) at the corpus lesser curvature and corpus greater curvature were all higher than those at the antrum lesser curvature, and the differences were statistically significant (all P<0.05). There were no statistically siginificant differences in the reversal rates of the aforementioned pathological features between the antrum greater curvature, gastric angle, and the antrum lesser curvature (all P>0.05). Conclusion:LTEVB 12C can achieve good efficacy in the treatment of CAG, and the chronic inflammation, atrophy, and intestinal metaplasia at multiple locations are improved, especially at the corpus lesser curvature and the corpus greater curvature.

Objective To develop the Children's Screen Interaction Quality Questionnaire(CSIQ)suit-able for measuring Chinese children aged 0 to 4 years,and to test its reliability and validity.Methods The purposive sampling method was used,and the guardians of 30 normal children aged 0 to 4 years undergoing physical examinations in the Department of Child Health Care of Guiyang Maternal and Child Health Care Hospital from February to April 2023 were selected as the interview objects.25 initial items were constructed through literature review,semi-structured interviews,and the Delphi expert consultation method.With the convenience sampling method,2 242 guardians of children aged 0 to 4 years old in the small and middle classes of 9 kindergartens in Guiyang City,Zunyi City,and Renhuai City were surveyed for item analysis,exploratory factor analysis,confirmatory factor analysis,and reliability and validity analysis.Results Exploratory factor a-nalysis extracted three factors,namely screen content interaction,reality interaction,and media interaction,with a total of 12 items.The cumulative variance explained rate of the 3-factor model was 69.829％.Confirma-tory factor analysis supported the three-factor model of CSIQ:x2/df=4.424,root mean square error of ap-proximation(RMSEA)=0.066,normed fit index(NFI)=0.955,comparative fit index(CFI)=0.965,incre-mental fit index(IFI)=0.965,Tucker-Lewis index(TLI)=0.955,goodness-of-fit index(GFI)=0.955,and the CSIQ had good convergent validity and discriminant validity.Conclusion The CSIQ has good reliability and validity.

Objective To explore the correlation between stroke etiology and clinical and imaging features in patients with acute ischemic stroke(AIS)due to large vessel occlusion treated by intravascular thrombectomy.Methods A total of 213 patients with AIS and endovascular embolectomy in our hospital from Oct.2016 to Jun.2018 were enrolled retrospectively.According to the etiological classification criteria of Trial of Org 10172 in Acute Stroke Treatment(TOAST),there were 116 cases of cardioembolism and 97 cases of non-cardioembolism.Multivariate logistic regression analysis was used to screen the clinical and imaging characteristics for identifying cardioembolism and non-cardioembolism.Results Compared with non-cardioembolism AIS,cardioembolism AIS was associated with higher NIHSS scores(adjusted odds ratio[OR]=1.09,95%confidence interval[95%CI]1.01-1.18,P=0.02),atrial fibrillation(adjusted OR=76.46,95%CI 26.75-218.51,P＜0.01),absence of hypertension(adjusted OR=0.32,95%CI 0.12-0.84,P=0.02),antiplatelet drug use(adjusted OR=5.03,95%CI 1.22-20.63,P=0.03),shorter onset-to-puncture time(adjusted OR=0.998,95%CI 0.996-1.000,P=0.04),and presence of hyperdense artery sign(HAS)(adjusted OR=4.45,95%CI 1.47-13.49,P=0.01).Conclusion There are some differences in clinical and imaging characteristics between patients with cardioembolism and non-cardioembolism AIS.The occurrence of HAS suggests a higher probability of cardioembolism in AIS patients.

Objective:To investigate the impact of tumor origin (ventral pancreatic origin and dorsal pancreatic origin) on prognosis in patients with pancreatic head cancer.Methods:A retrospective analysis was performed on the clinical data of 150 patients with pancreatic head cancer who received surgical treatment at the First Affiliated Hospital of the Naval Medical University from October 2014 to December 2017. Among these patients, 92 were male and 58 were female, aged (61.2±8.8) years. The 150 patients were divided into two groups based on tumor origin: the ventral pancreatic cancer group ( n=72) and the dorsal pancreatic cancer group ( n=78). A comparative analysis of clinical, pathological, and imaging charac-teristics was conducted between the two groups. Univariate and multivariable Cox proportional hazards models were used to analyze the association between pancreatic head cancer origin and overall survival (OS). Results:Patients with pancreatic head carcinoma arising from the ventral and dorsal pancreas accounted for 48%(72/150) and 52%(78/150) of the study cohort, respectively. Pancreatic head carcinoma arising from the dorsal pancreas were more likely to show pathological features of pancreatic parenchymal atrophy [73.1%(57/78) vs. 47.2%(34/72), χ2=10.49, P=0.001] and pancreatitis [44.9%(35/78) vs. 29.2%(21/72), χ2=3.95, P=0.047]. In contrast, patients with pancreatic head carcinoma arising from the ventral pancreas was more frequently associated with contact with the superior mesenteric artery [25.0%(18/72) vs. 1.3%(1/78), χ2=19.04, P<0.001], perineural invasion [100%(72/72) vs. 88.5%(69/78), χ2=8.84, P=0.003], and positive surgical margins [15.3%(11/72) vs. 2.6%(2/78), χ2=7.65, P=0.006], with all differences statistically significant. The ventral pancreatic cancer group demonstrated cumulative survival rates of 33.2% and 0 at 1-year and 2-year postoperative intervals, respectively, while the dorsal pancreatic cancer group exhibited rates of 56.7% and 24.8% at the corresponding timepoints. Comparison of Kaplan-Meier survival curves between the two groups showed a statistically significant difference ( χ2=6.00, P=0.014). Multivariable Cox proportional hazards analysis identified dorsal pancreatic origin pancreatic head cancer as an independent predictor of increased mortality risk compared to ventral origin tumors ( HR=2.75, 95% CI: 1.52-4.98, P=0.001). Conclusion:The embryonic origin of pancreatic head cancer determines its clinical, pathological, and imaging heterogeneity, and pancreatic head cancer arising from the ventral pancreas demonstrates significantly worse prognostic outcomes compared to dorsal pancreatic origin.

Objective:A prognosis prediction model for pancreatic cancer was constructed based on multi-scale radiomics combined with deep learning, and the prediction effect of the model was evaluated.Methods:A retrospective analysis was conducted on the clinical data of 215 patients who underwent radical resection of pancreatic cancer at the First Affiliated Hospital of Naval Medical University from January 2017 to December 2017. Among them, 134 were male and 81 were female, with an age of (61.9±9.2) years. Patients were randomly divided into the training set ( n=151) and the test set ( n=64) in a ratio of 7: 3. Habitat features, peritumoral radiomics features, 3D radiomics features, and 2.5D deep learning features were extracted from preoperative CT images respectively. After feature screening, a survival prediction model was constructed using the CoxBoost machine learning algorithm that integrated the Boosting algorithm and the Cox proportional hazards model. The performance of the model was evaluated using the area under the time-dependent receiver operating characteristic curve and the consistency index. The clinical benefits of the model were evaluated using decision curve analysis. The survival curves were plotted using the Kaplan-Meier method, and the log-rank test was used for the comparison of survivals between groups. Results:The LASSO, random forest and extreme gradient boosting models were each used to screen out the top 10 most important features and take the union, ultimately obtaining 20 radiomics features for modeling. In the training set and test set, the consistency index of the CoxBoost model in predicting overall survival was 0.717 (95% CI: 0.669-0.765) and 0.688 (95% CI: 0.610-0.766), respectively, and the area under the curve for predicting overall survival at 1, 2, and 3 years after surgery was 0.830 (95% CI: 0.752-0.898), 0.753 (95% CI: 0.665-0.833), 0.828 (95% CI: 0.735-0.908) and 0.690 (95% CI: 0.549-0.824), 0.780 (95% CI: 0.649-0.887 and 0.793 (95% CI: 0.660-0.897), respectively. The area under the curve for predicting long-term survival after surgery (≥40 months) was above 0.8. Based on the optimal cutoff value of -0.19 for the predicted value of the CoxBoost model calculated by the R package " survminer", the patients were divided into high-risk (predicted value >-0.19) and low-risk (predicted value <-0.19) groups. In both the training set and the test set, the survival of patients in the low-risk group was better than that in the high-risk group (training set: χ2=39.01, P<0.001; test set: χ2=12.34, P<0.001). The median survival period of patients in the high-risk group was lower than that in the low-risk group (training set: 15.80 vs 34.07 months; test set: 16.87 vs 43.07; months). Decision curve analysis shows that patients obtain survival benefit when the threshold probability of the training set is greater than 0.25 and that of the test set is greater than 0.45. Conclusion:The CoxBoost model has a good predictive ability for the overall survival of pancreatic cancer patients after surgery and can effectively screen out patient subgroups that may significantly benefit from surgical treatment.

Objective To comprehensively investigate the subcomponent characteristics of inhibitory control for children with autism spectrum disorder(ASD)aged 4-5 years under experimental and natural environments.Methods Thirty children with ASD aged 4-5 years and 30 chronological-age and intellectual level-matched typically developing children were recruited.The Simon task,Go/nogo task,and Stroop task were used to examine the conflict response inhibition,prepotent response inhibition,and interference control subcomponents of inhibitory control,respectively.The inhibit subscale of the behavior rating inventory of executive function-preschool version was employed to assess children's inhibition in daily natural situations.Results Under the incongruent condition of the Simon task,there were no significant differences in mean reaction time and accuracy between ASD group and the control group(P>0.05).In the Go/nogo task,the ASD group demonstrated elevated false positive errors compared to the controls[3.10%(0,6.20%)vs.0(0,0.78%),P=0.005].However,there were no significant differences in mean reaction time and false alarm error between ASD group and the control group(P>0.05).In the Stroop task,there were no significant differences in the accuracy and mean reaction time between ASD group and the control group(P>0.05).Additionally,the ASD group scored significantly worse than the controls in the inhibit subscale of BRIEF-P[(60.47±9.63)vs.(54.23±7.45),P=0.007].Conclusions The inhibitory control of children with ASD aged 4-5 years are partially impaired in a structural experimental setting while severely deficient in a natural environment.

Objective:To evaluate the efficacy of lamb′s tripe extract and vitamin B 12 capsule (LTEVB 12C) on chronic atrophic gastritis (CAG) at different locations (antrum lesser curvature, antrum greater curvature, gastric angle, corpus lesser curvature, and corpus greater curvature). Methods:From August 2011 to January 2013, 715 patients with CAG in a multicenter, randomized, double-blind, placebo-controlled trial were enrolled from 16 tertiary first-class hospitals across the country, including the First Affiliated Hospital of Air Force Medical University, Nanfang Hospital of Southern Medical University, the First Hospital of Jilin University, West China Hospital of Sichuan University, etc., there were 476 cases in the LTEVB 12C group and 239 cases in the placebo group. The patients of the LTEVB 12C group received LTEVB 12C, and the patients of placebo group received LTEVB 12C mimetic, all the medications were taken 3 capsules each time and 3 times a day after meals, and the treatment course of 2 groups were both 6 months. The efficacy evaluation criteria included the effective rate (a decrease of ≥1 in histopathological score compared with baseline after 6 months of treatment) and the reversal rate (a decrease of ≥ 2 in histopathological score compared with baseline after 6 months of treatment in the patients with moderate to severe CAG). The impact of lesion sites on the therapeutic effects of LTEVB 12C was analyzed by logistic regression analysis. The two-way unordered Cochran-Mantel-Haenszel chi-square test considering the center effect and Pearson chi-square test were used for statistical analysis. Results:The effective rates of chronic inflammation at the antrum greater curvature and corpus greater curvature (23.3%, 110/473 vs. 13.0%, 31/239; 20.3%, 96/472 vs. 12.6%, 30/239), the effective rates of atrophy at the antrum lesser curvature, antrum greater curvature, gastric angle, corpus lesser curvature, and the corpus greater curvature (27.0%, 118/437 vs. 15.7%, 34/216; 29.2%, 126/432 vs. 18.5%, 38/205; 27.8%, 121/435 vs. 16.7%, 36/216; 32.5%, 127/391 vs. 19.8%, 37/187; 33.0%, 119/361 vs. 21.8%, 39/179), and the effective rates of intestinal metaplasia at the antrum lesser curvature, antrum greater curvature, gastric angle, and the corpus lesser curvature (45.0%, 112/249 vs. 29.8%, 31/104; 53.8%, 86/160 vs. 33.9%, 21/62; 45.8%, 103/225 vs. 24.0%, 25/104; 51.9%, 83/160 vs. 28.3%, 17/60) of the LTEVB 12C group were all higher than those of the placebo group, and the differences were statistically significant ( χ2=10.76, 6.39, 9.69, 7.91, 11.05, 9.62, 8.57, 5.20, 7.11, 12.45, and 6.73; all P<0.05). The reversal rates of chronic inflammation at the corpus lesser curvature and corpus greater curvature (5.2%, 12/231 vs. 0, 0/123; 4.7%, 8/170 vs. 0, 0/88), the reversal rates of atrophy at the antrum lesser curvature, antrum greater curvature, corpus lesser curvature, and the corpus greater curvature (6.8%, 22/323 vs. 1.3%, 2/151; 9.2%, 29/315 vs. 1.4%, 2/144; 14.2%, 38/267 vs. 2.5%, 3/121; 20.8%, 35/168 vs. 5.8%, 4/69), and the reversal rates of intestinal metaplasia at the antrum lesser curvature, antrum greater curvature, gastric angle, and the corpus lesser curvature (29.8%, 39/131 vs. 9.1%, 4/44; 41.0%, 32/78 vs. 12.5%, 3/24; 33.3%, 44/132 vs. 4.8%, 3/63; 50.0%, 37/74 vs. 8.7%, 2/23) of the LTEVB 12C group were all higher than those of the placebo group, and the differences were statistically significant ( χ2=6.58, 5.12, 5.60, 8.61, 11.43, 6.59, 7.30, 4.95, 15.92, 7.62; all P<0.05). There were no statistically significant differences in the effective rates and reversal rates of active inflammation at different locations between the LTEVB 12C group and the placebo group (all P>0.05). The results of logistic regression analysis (taking the antrum lesser curvature as the reference) further confirmed that the reversal rates of chronic inflammation ( OR=0.22, 95% confidence interval (95% CI): 0.07 to 0.67; OR=0.24, 95% CI: 0.07 to 0.80), atrophy ( OR=0.28, 95% CI: 0.16 to 0.49; OR=0.28, 95% CI: 0.16 to 0.49), and intestinal metaplasia ( OR=0.42, 95% CI: 0.24 to 0.77; OR=0.20, 95% CI: 0.08 to 0.52) at the corpus lesser curvature and corpus greater curvature were all higher than those at the antrum lesser curvature, and the differences were statistically significant (all P<0.05). There were no statistically siginificant differences in the reversal rates of the aforementioned pathological features between the antrum greater curvature, gastric angle, and the antrum lesser curvature (all P>0.05). Conclusion:LTEVB 12C can achieve good efficacy in the treatment of CAG, and the chronic inflammation, atrophy, and intestinal metaplasia at multiple locations are improved, especially at the corpus lesser curvature and the corpus greater curvature.

Objective:To investigate the impact of tumor origin (ventral pancreatic origin and dorsal pancreatic origin) on prognosis in patients with pancreatic head cancer.Methods:A retrospective analysis was performed on the clinical data of 150 patients with pancreatic head cancer who received surgical treatment at the First Affiliated Hospital of the Naval Medical University from October 2014 to December 2017. Among these patients, 92 were male and 58 were female, aged (61.2±8.8) years. The 150 patients were divided into two groups based on tumor origin: the ventral pancreatic cancer group ( n=72) and the dorsal pancreatic cancer group ( n=78). A comparative analysis of clinical, pathological, and imaging charac-teristics was conducted between the two groups. Univariate and multivariable Cox proportional hazards models were used to analyze the association between pancreatic head cancer origin and overall survival (OS). Results:Patients with pancreatic head carcinoma arising from the ventral and dorsal pancreas accounted for 48%(72/150) and 52%(78/150) of the study cohort, respectively. Pancreatic head carcinoma arising from the dorsal pancreas were more likely to show pathological features of pancreatic parenchymal atrophy [73.1%(57/78) vs. 47.2%(34/72), χ2=10.49, P=0.001] and pancreatitis [44.9%(35/78) vs. 29.2%(21/72), χ2=3.95, P=0.047]. In contrast, patients with pancreatic head carcinoma arising from the ventral pancreas was more frequently associated with contact with the superior mesenteric artery [25.0%(18/72) vs. 1.3%(1/78), χ2=19.04, P<0.001], perineural invasion [100%(72/72) vs. 88.5%(69/78), χ2=8.84, P=0.003], and positive surgical margins [15.3%(11/72) vs. 2.6%(2/78), χ2=7.65, P=0.006], with all differences statistically significant. The ventral pancreatic cancer group demonstrated cumulative survival rates of 33.2% and 0 at 1-year and 2-year postoperative intervals, respectively, while the dorsal pancreatic cancer group exhibited rates of 56.7% and 24.8% at the corresponding timepoints. Comparison of Kaplan-Meier survival curves between the two groups showed a statistically significant difference ( χ2=6.00, P=0.014). Multivariable Cox proportional hazards analysis identified dorsal pancreatic origin pancreatic head cancer as an independent predictor of increased mortality risk compared to ventral origin tumors ( HR=2.75, 95% CI: 1.52-4.98, P=0.001). Conclusion:The embryonic origin of pancreatic head cancer determines its clinical, pathological, and imaging heterogeneity, and pancreatic head cancer arising from the ventral pancreas demonstrates significantly worse prognostic outcomes compared to dorsal pancreatic origin.

Objective:A prognosis prediction model for pancreatic cancer was constructed based on multi-scale radiomics combined with deep learning, and the prediction effect of the model was evaluated.Methods:A retrospective analysis was conducted on the clinical data of 215 patients who underwent radical resection of pancreatic cancer at the First Affiliated Hospital of Naval Medical University from January 2017 to December 2017. Among them, 134 were male and 81 were female, with an age of (61.9±9.2) years. Patients were randomly divided into the training set ( n=151) and the test set ( n=64) in a ratio of 7: 3. Habitat features, peritumoral radiomics features, 3D radiomics features, and 2.5D deep learning features were extracted from preoperative CT images respectively. After feature screening, a survival prediction model was constructed using the CoxBoost machine learning algorithm that integrated the Boosting algorithm and the Cox proportional hazards model. The performance of the model was evaluated using the area under the time-dependent receiver operating characteristic curve and the consistency index. The clinical benefits of the model were evaluated using decision curve analysis. The survival curves were plotted using the Kaplan-Meier method, and the log-rank test was used for the comparison of survivals between groups. Results:The LASSO, random forest and extreme gradient boosting models were each used to screen out the top 10 most important features and take the union, ultimately obtaining 20 radiomics features for modeling. In the training set and test set, the consistency index of the CoxBoost model in predicting overall survival was 0.717 (95% CI: 0.669-0.765) and 0.688 (95% CI: 0.610-0.766), respectively, and the area under the curve for predicting overall survival at 1, 2, and 3 years after surgery was 0.830 (95% CI: 0.752-0.898), 0.753 (95% CI: 0.665-0.833), 0.828 (95% CI: 0.735-0.908) and 0.690 (95% CI: 0.549-0.824), 0.780 (95% CI: 0.649-0.887 and 0.793 (95% CI: 0.660-0.897), respectively. The area under the curve for predicting long-term survival after surgery (≥40 months) was above 0.8. Based on the optimal cutoff value of -0.19 for the predicted value of the CoxBoost model calculated by the R package " survminer", the patients were divided into high-risk (predicted value >-0.19) and low-risk (predicted value <-0.19) groups. In both the training set and the test set, the survival of patients in the low-risk group was better than that in the high-risk group (training set: χ2=39.01, P<0.001; test set: χ2=12.34, P<0.001). The median survival period of patients in the high-risk group was lower than that in the low-risk group (training set: 15.80 vs 34.07 months; test set: 16.87 vs 43.07; months). Decision curve analysis shows that patients obtain survival benefit when the threshold probability of the training set is greater than 0.25 and that of the test set is greater than 0.45. Conclusion:The CoxBoost model has a good predictive ability for the overall survival of pancreatic cancer patients after surgery and can effectively screen out patient subgroups that may significantly benefit from surgical treatment.