Objective:To explore a medical big data algorithm to screen the core indicators in clinical database that can be used to evaluate the prognosis of elderly patients with pneumonia.Methods:Based on the clinical database of a Beijing Chaoyang Hospital Consortium Chaoyang Emergency Ward in Beijing Chaoyang Hospital, Capital Medical University, patients with pulmonary infection were selected through the big data retrieval technology. According to the prognosis at the time of discharge, they were divided into death group and survival group. The general data of patients were collected, including gender, age, blood gas and laboratory indices. A computer language called Python was used to make batch calculations of key indicators that affect mortality in elderly patients with pneumonia. Logistic regression analysis was used to analyze the relationship between laboratory indicators and patients' prognosis. Receiver operating characteristic curve (ROC curve) was drawn to analyze the predictive value of screening method for patients' prognosis.Results:A total of 265 patients were included in the study, 64 died and 201 survived. The data of the first detection indexes of each patient after admission were collected, and 23 key indicators with significant differences were selected from 472 indicators: blood routine indicators ( n = 7), blood gas indicators ( n = 3), tumor markers indicators ( n = 3),coagulation related indicators ( n = 4), and nutrition and organ function indicators ( n = 6). ① The key indicators of blood gas in patients died of pneumonia: Cl - was 97-111 mmol/L in 51.6% (33 cases) of patients, lactic acid (Lac) was 0.5-2.5 mmol/L in 81.2% (52 cases) of patients, and H + was 0-46 mmol/L in 87.5% (56 cases) of patients. ② The key indicators of blood routine of patients died of pneumonia: hemoglobin count (Hb) of 46.9% (30 cases) patients was 80-109 g/L, the eosinophils proportions (EOS%) in 67.2% (43 cases) patients was 0.000-0.009, the lymphocytes proportions (LYM%) in 51.6% (33 cases) patients was 0.00-0.09, the red blood cell count (RBC) in 50.0% (32 cases) patients was (3.0-3.9)×10 12/L, the white blood cell count (WBC) in 54.7% (35 cases) patients was (0.0-9.9)×10 9/L, and the red blood cell volume distribution width coefficientof variability (RDW-CV) in 48.4% (31 cases) patients was 10.0%-14.9%, serum C-reactive protein (CRP) was 0.0-49.9 mg/L in 48.4% (31 cases) patients. ③ The key indicators of tumor markers in patients died of pneumonia: 76.6% (49 cases) of patients had negative free prostate specific antigen/total prostate specific antigen (FPSA/TPSA, the ratio was 0), 92.2% (59 cases) had cytokeratin 19 fragment (CYFRA21-1) between 0.0-11.0 μg/L, and 75.0% (48 cases) had carbohydrate antigen 125 (CA125) between 0-104 kU/L.④ The key coagulation indexes of patients died of pneumonia: 68.8% (44 cases) of patients had activated partial thromboplastin time (APTT) of 57-96 s, 73.4% (47 cases) of patients had D-dimer of 0-6 mg/L, 93.8% (60 cases) of patients had thrombin time (TT) of 14-22 s, and 89.1% (57 cases) of patients had adenosine diphosphate (ADP) inhibition rate of 0%-53%. ⑤ Nutrition and organ function key indicatorsin patients died of pneumonia: 92.2% (59 cases) of brain natriuretic peptide (BNP) in patients with 0, 46.9% (30 cases) of patients had prealbumin (PA) of 71-140 mg/L, 90.6% (58 cases) of the patients with uric acid (UA) for 21-41 μmol/L, 75.0% (48 cases) of the patients with albumin (Alb) to 10-20 g/L, 93.5% (60 cases) of patients had albumin/globulin ratio (A/G ratio) of 0-0.9, 84.4% (54 cases) of the patients with lactate dehydrogenase (LDH) from 0-6.68 μmol/L·s -1·L -1. ⑥ Logistic regression analysis and ROC curve analysis: Logistic regression analysis showed that PA and Lac were the prognostic factors. PA could reduce the risk of death by 0.9%, Lac could increase the risk of death by 69.4%; the area under ROC curve (AUC) between laboratory indicators and the prediction effect of death prediction model for patients' prognosis was 0.80, which showed that the classification effect was better, and this study model could better predict the prognosis of elderly patients with pneumonia. Conclusion:By using big data technology, 23 core indicators for evaluating the prognosis of elderly patients with pneumonia can be screened from the clinical database of emergency ward, which provides a new perspective and method for clinical evaluation of the prognosis of elderly patients with pneumonia.

OBJECTIVETo examine long-term efficacy of percutaneous transluminal coronary angioplasty (PTCA), coronary stenting and to assess the factors affecting its efficacy.

METHODSA total of 790 patients who underwent successful PTCA and PTCA + stent in this hospital were followed by direct interview or letter. The rate of follow-up was 84.2% and the period of follow-up was 0.9 - 12.7 (3.5 +/- 2.4) years.

RESULTSDuring follow-up, 4 (0.5%) patients died, 22 (2.8%) had nonfatal acute myocardial infarction, 10 (1.3%) had coronary artery bypass surgery, and 98 (12.4%) had repeat PTCA. The rate of recurrent angina pectoris was 31.1%. The cardiac event-free survival rate calculated by the Kaplan-Meier method was 88.2% at 1 year and 80.6% at 12.7 years. Cox regression analysis showed that there was a positive correlation between AMI history, stent implantation and the risk of cardiac events, and there was a negative correlation between the number of diseased arteries and the risk of cardiac events. Compared to the PTCA group, patients with PTCA + stent had significantly lower rates of total cardiac events.

CONCLUSIONThe long-term efficacy of PTCA, especially PTCA + stent in Chinese patients was very satisfactory, suggesting that PTCA + stent therapy should be the major treatment for revascularization in patients with coronary heart disease.

Adult ; Aged ; Angina Pectoris ; etiology ; Angioplasty, Balloon, Coronary ; adverse effects ; Coronary Stenosis ; mortality ; therapy ; Female ; Follow-Up Studies ; Humans ; Male ; Middle Aged ; Multivariate Analysis ; Myocardial Infarction ; etiology ; Retrospective Studies ; Stents ; adverse effects ; Survival Rate ; Treatment Outcome

Gallbladder carcinoma (GBC) is the most common malignancy of the biliary tract, radical resection is the only effective treatment for GBC at present. However, the postoperative effect is still poor. Therefore, identifying the key prognostic factors and establishing an individual and accurate survival prediction model for GBC are critical to prognosis assessment, treatment options and clinical decision support in patients with GBC. The prediction value of current commonly used TNM staging system is limited. Cox regression model is the most commonly used classical survival analysis method, but it is difficult to establish the association between prognostic variables. Nomogram and machine learning techniques including Bayesian network have been used to establish survival prediction model of GBC in recent years, which representing a certain degree of advancement, however, the model precision and clinical application still need to be further verified. The establishment of more accurate survival prediction models for GBC based on machine learning algorithm from Chinese multicenter large sample database to guide the clinical decision-making is the main research direction in the future.

Objective:To evaluate the related factors of gallstones related gallbladder intraepithelial neoplasia(GBIN) and establish the prediction models for gallstones related GBIN.Methods:The clinicopathological data of 750 patients who underwent cholecystectomy for gallstones at Department of Hepatobiliary Surgery of the First Affiliated Hospital of Xi′an Jiaotong University from January 2013 to December 2018 and the postoperative pathological examination showed chronic cholecystitis or GBIN were analyzed retrospectively,including 150 cases of gallstones with GBIN and 600 cases of gallstones with chronic cholecystitis.There were 264 males and 486 females with age of (51.3±14.5) years (range: 18 to 90 years).The related factors for gallstones related GBIN were screened by χ 2 test and Logistic regression model,and the prediction models were established based on independent related factors and internal validation was conducted.The original data were randomly divided into a training cohort(526 cases) and a validation cohort(224 cases) at a ratio of 7∶3,and the nomogram and tree augmented na?ve Bayes were conducted to establish the prediction model for gallstones related GBIN.The consistency index(C-index),calibration chart,area under the receiver operating characteristic curve(AUC) and confusion matrix were used to evaluate the prediction performance of the two models. Results:Univariate analysis showed that age,gallstones history(years),gallbladder size,whether the gallbladder mucosa smooth or not,whether the gallbladder wall thickened or not,gallstones diameter,and number of gallstones were related factors for the occurrence of gallstones related GBIN (χ2=19.957,8.599,9.724,9.301,8.341,15.288,9.169,all P<0.05).Multivariate analysis showed that age ( OR=2.23,95% CI:1.50-3.31, P<0.01),gallbladder size ( OR=2.11,95% CI:1.17-3.80, P=0.013),whether the gallbladder mucosa smooth or not ( OR=1.80,95% CI:1.13-2.88, P=0.014),gallstones diameter( OR=2.98,95% CI:1.71-5.21, P<0.01),and number of gallstones ( OR=2.14,95% CI:1.34-3.42, P<0.01) were independent related factors for the occurrence of gallstones related GBIN; the C-index of the nomogram in training cohort and validation cohort were 0.708 and 0.696,respectively.The AUC of the two models in training cohort were 70.60% and 70.73%,and in validation cohort were 68.14% and 67.47%,respectively.The accuracy of the two models in training cohort were 69.96% and 70.72%,and in validation cohort were 66.96% and 67.41%,respectively. Conclusion:Age,gallbladder size,whether the gallbladder mucosa smooth or not,gallstones diameter and number of gallstones are independent related factors for the occurrence of gallstones related GBIN,and the nomogram and tree augmented na?ve Bayes prediction models based on the above factors can be used to predict the occurrence of GBIN.

Gallbladder carcinoma (GBC) is the most common malignancy of the biliary tract, radical resection is the only effective treatment for GBC at present. However, the postoperative effect is still poor. Therefore, identifying the key prognostic factors and establishing an individual and accurate survival prediction model for GBC are critical to prognosis assessment, treatment options and clinical decision support in patients with GBC. The prediction value of current commonly used TNM staging system is limited. Cox regression model is the most commonly used classical survival analysis method, but it is difficult to establish the association between prognostic variables. Nomogram and machine learning techniques including Bayesian network have been used to establish survival prediction model of GBC in recent years, which representing a certain degree of advancement, however, the model precision and clinical application still need to be further verified. The establishment of more accurate survival prediction models for GBC based on machine learning algorithm from Chinese multicenter large sample database to guide the clinical decision-making is the main research direction in the future.

Objective:To evaluate the related factors of gallstones related gallbladder intraepithelial neoplasia(GBIN) and establish the prediction models for gallstones related GBIN.Methods:The clinicopathological data of 750 patients who underwent cholecystectomy for gallstones at Department of Hepatobiliary Surgery of the First Affiliated Hospital of Xi′an Jiaotong University from January 2013 to December 2018 and the postoperative pathological examination showed chronic cholecystitis or GBIN were analyzed retrospectively,including 150 cases of gallstones with GBIN and 600 cases of gallstones with chronic cholecystitis.There were 264 males and 486 females with age of (51.3±14.5) years (range: 18 to 90 years).The related factors for gallstones related GBIN were screened by χ 2 test and Logistic regression model,and the prediction models were established based on independent related factors and internal validation was conducted.The original data were randomly divided into a training cohort(526 cases) and a validation cohort(224 cases) at a ratio of 7∶3,and the nomogram and tree augmented na?ve Bayes were conducted to establish the prediction model for gallstones related GBIN.The consistency index(C-index),calibration chart,area under the receiver operating characteristic curve(AUC) and confusion matrix were used to evaluate the prediction performance of the two models. Results:Univariate analysis showed that age,gallstones history(years),gallbladder size,whether the gallbladder mucosa smooth or not,whether the gallbladder wall thickened or not,gallstones diameter,and number of gallstones were related factors for the occurrence of gallstones related GBIN (χ2=19.957,8.599,9.724,9.301,8.341,15.288,9.169,all P<0.05).Multivariate analysis showed that age ( OR=2.23,95% CI:1.50-3.31, P<0.01),gallbladder size ( OR=2.11,95% CI:1.17-3.80, P=0.013),whether the gallbladder mucosa smooth or not ( OR=1.80,95% CI:1.13-2.88, P=0.014),gallstones diameter( OR=2.98,95% CI:1.71-5.21, P<0.01),and number of gallstones ( OR=2.14,95% CI:1.34-3.42, P<0.01) were independent related factors for the occurrence of gallstones related GBIN; the C-index of the nomogram in training cohort and validation cohort were 0.708 and 0.696,respectively.The AUC of the two models in training cohort were 70.60% and 70.73%,and in validation cohort were 68.14% and 67.47%,respectively.The accuracy of the two models in training cohort were 69.96% and 70.72%,and in validation cohort were 66.96% and 67.41%,respectively. Conclusion:Age,gallbladder size,whether the gallbladder mucosa smooth or not,gallstones diameter and number of gallstones are independent related factors for the occurrence of gallstones related GBIN,and the nomogram and tree augmented na?ve Bayes prediction models based on the above factors can be used to predict the occurrence of GBIN.

Objective:To investigate the establishment and application value of a radio-mics prediction model for lymph node metastasis of gallbladder carcinoma based on dual-phase enhanced computed tomography (CT).Methods:The retrospective cohort study was conducted. The clinicopathological data of 194 patients with gallbladder carcinoma who were admitted to the First Affiliated Hospital of Xi'an Jiaotong University from January 2012 to December 2020 were collected. There were 70 males and 124 females, aged (64±10)years. All patients underwent curative-intent resection of gallbladder carcinoma. A total of 194 patients were randomly divided into 156 cases in training set and 38 cases in test set according to the ratio of 8:2 based on random number method in R software. The training set was used to establish a diagnostic model, and the test set was used to validate the diagnostic model. After the patients undergoing CT examination, image analysis was performed, radiomics features were extracted, and a radiomics model was established. Based on clinicopathological data, a nomogram prediction model was established. Observation indicators: (1) lymph node dissection and histopathological examination results; (2) establishment and characteristic analysis of a radiomics prediction model; (3) analysis of influencing factors for lymph node metastasis of gallbladder carcinoma; (4) establishment of a nomogram prediction model for lymph node metastasis; (5) comparison of the predictive ability between the radiomics prediction model and nomogram prediction model for lymph node metastasis. Measurement data with normal distribution were represented as Mean± SD, and measurement data with skewed distribution were represented as M(range). Count data were expressed as absolute numbers, and comparison between groups was performed by the chi-square test. Univariate analysis was conducted by the chi-square test, and multivariate analysis was performed by the Logistic regression model forward method. The receiver operating characteristic curve was drawn, and the area under curve, decision curve, confusion matrix were used to evaluate the predictive ability of prediction models. Results:(1) Lymph node dissection and histopathological examination results. Of the 194 patients, 182 cases underwent lymph node dissection, with the number of lymph node dissected as 8(range, 1?34) per person and the number of positive lymph node as 0(range, 0?11) per person. Postoperative histopathological examination results of 194 patients: 122 patients were in stage N0, with the number of lymph node dissected as 7(range, 0?27) per person, 48 patients were in stage N1, with the number of lymph node dissected as 8(range, 2?34) per person and the number of positive lymph node as 1(range, 1?3) per person, 24 patients were in stage N2, with the number of lymph node dissected as 11(range, 2?20) per person and the number of positive lymph node as 5(range, 4?11) per person. (2) Establishment and characteristic analysis of a radiomics prediction model. There were 107 radiomics features extracted from 194 patients, including 18 first-order features, 14 shape features and 75 texture features. According to the intra-group correlation coefficient and absolute median difference of each radiomics feature, mutual information, Select K-Best, least absolute shrinkage and selection operator regression were conducted to further reduce dimensionality. By further combining 5 different machine learning algorithms including random forest, gradient boosting secession tree, support vector machine (SVM), K-Nearest Neighbors and Logistic regression, the result showed that the Select K-Best_SVM model had the best predictive performance after analysis, with the area under receiver operating characteristic curve as 0.76 in the test set. (3) Analysis of influencing factors for lymph node metastasis of gallbladder carcinoma. Results of univariate analysis showed that systemic inflammation response index, carcinoembryonic antigen (CEA), CA19-9, CA125, radiological T staging and radiological lymph node status were related factors for lymph node metastasis of patients with gallbladder cancer ( χ2=4.20, 11.39, 5.68, 11.79, 10.83, 18.58, P<0.05). Results of multivariate analysis showed that carcinoembryonic antigen, CA125, radiological T staging (stage T3 versus stage T1?2, stage T4 versus stage T1?2), radiological lymph node status were independent influencing factors for lymph node metastasis of patients with gallbladder carcinoma [ hazard ratio=2.79, 4.41, 5.62, 5.84, 3.99, 95% confidence interval ( CI) as 1.20?6.47, 1.81?10.74, 1.50?21.01, 1.02?33.31, 1.87?8.55, P<0.05]. (4) Establishment of a nomogram prediction model for lymph node metastasis. A nomogram prediction model was established based on the 4 independent influencing factors for lymph node metastasis of gallbladder carcinoma, including CEA, CA125, radiological T staging and radiological lymph node status. The concordance index of the nomogram model was 0.77 (95% CI as 0.75?0.79) in the training set and 0.73 (95% CI as 0.68?0.72) in the test set, respectively. (5) Comparison of the predictive ability between the radiomics predic-tion model and nomogram prediction model for lymph node metastasis. The receiver operating characteristic curve showed that the areas under the curve of Select K-Best_SVM radiomics model were 0.75 (95% CI as 0.74?0.76) in the training set and 0.76 (95% CI as 0.75?0.78) in the test set, respectively. The areas under the curve of nomogram prediction model were 0.77 (95% CI as 0.76?0.78) in the training set and 0.70 (95% CI as 0.68?0.72) in the test set, respectively. The decision curve analysis showed that Select K-Best_SVM radiomics model and nomogram prediction model had a similar ability to predict lymph node metastasis. The confusion matrix showed that Select K-Best_SVM radiomics model had the sensitivity as 64.29% and 75.00%, the specificity as 73.00% and 59.09% in the training set and test set, respectively. The nomogram had the sensitivity as 51.79% and 50.00%, the specificity as 80.00% and 72.27% in the training set and test set, respectively. Conclusion:A dual-phase enhanced CT imaging radiomics prediction model for lymph node metastasis of gallbladder carcinoma is successfully established, and its predictive ability is good and consistent with that of nomogram.

Objective: To investigate the clinical value of Bayesian network in predicting survival of patients with advanced gallbladder cancer(GBC)who underwent curative intent surgery. Methods: The clinical data of patients with advanced GBC who underwent curative intent surgery in 9 institutions from January 2010 to December 2015 were analyzed retrospectively.A median survival time model based on a tree augmented naïve Bayes algorithm was established by Bayesia Lab software.The survival time, number of metastatic lymph nodes(NMLN), T stage, pathological grade, margin, jaundice, liver invasion, age, sex and tumor morphology were included in this model.Confusion matrix, the receiver operating characteristic curve and area under the curve were used to evaluate the accuracy of the model.A priori statistical analysis of these 10 variables and a posterior analysis(survival time as the target variable, the remaining factors as the attribute variables)was performed.The importance rankings of each variable was calculated with the polymorphic Birnbaum importance calculation based on the posterior analysis results.The survival probability forecast table was constructed based on the top 4 prognosis factors. The survival curve was drawn by the Kaplan-Meier method, and differences in survival curves were compared using the Log-rank test. Results: A total of 316 patients were enrolled, including 109 males and 207 females.The ratio of male to female was 1.0∶1.9, the age was (62.0±10.8)years.There was 298 cases(94.3%) R0 resection and 18 cases(5.7%) R1 resection.T staging: 287 cases(90.8%) T3 and 29 cases(9.2%) T4.The median survival time(MST) was 23.77 months, and the 1, 3, 5-year survival rates were 67.4%, 40.8%, 32.0%, respectively.For the Bayesian model, the number of correctly predicted cases was 121(≤23.77 months) and 115(>23.77 months) respectively, leading to a 74.86% accuracy of this model.The prior probability of survival time was 0.503 2(≤23.77 months) and 0.496 8(>23.77 months), the importance ranking showed that NMLN(0.366 6), margin(0.350 1), T stage(0.319 2) and pathological grade(0.258 9) were the top 4 prognosis factors influencing the postoperative MST.These four factors were taken as observation variables to get the probability of patients in different survival periods.Basing on these results, a survival prediction score system including NMLN, margin, T stage and pathological grade was designed, the median survival time(month) of 4-9 points were 66.8, 42.4, 26.0, 9.0, 7.5 and 2.3, respectively, there was a statistically significant difference in the different points(P<0.01). Conclusions The survival prediction model of GBC based on Bayesian network has high accuracy.NMLN, margin, T staging and pathological grade are the top 4 risk factors affecting the survival of patients with advanced GBC who underwent curative resection.The survival prediction score system based on these four factors could be used to predict the survival and to guide the decision making of patients with advanced GBC.

Objective:To examine the role of the number of lymph nodes examined(NLNE) on the prognosis of patients with curatively resected gallbladder carcinoma(GBC).Methods:The clinicopathological data and prognosis of 401 patients with GBC who underwent radical surgery from six institutions of China from January 2013 to December 2017 were analyzed retrospectively. There were 153 males(38.2%) and 248 females(61.8%), with age of (62.0±10.5) years (range: 30-88 years). Fifty-three patients(22.2%) were accompanied by jaundice. All patients underwent radical resection+regional lymphadenectomy.R0 or R1 resection was confirmed by postoperative pathological examination.The different cut-off values of NLNE were determined by the X-tile software, the optimal cut-off values were identified by analyzing the relationship between different cut-off values of NLNE with survival rate. Kaplan-Meier method was used for survival analysis. Univariate and multivariate analysis were implemented respectively using the Log-rank test and Cox proportional hazard model.Results:Among the 401 patients enrolled, 135 cases (33.6%) had lymphatic metastasis, of which 98 cases were in N1 stage(24.4%) and 37 cases were in N2 stage(9.2%).A total of 2 794 NLNE were retrieved, with a median count of 6 (5).The median positive lymph nodes count was 0 (1), and the median positive lymph nodes ratio was 0 (IQR, 0-0.2). Since the 12 and 15 were determined as the cut-off values by X-tile, all patients were divided into three groups of 1-11, 12-15 and ≥16.The 3-year survival rate of the three groups was 45.2%, 74.5%, 12.0% respectively, with statistically significant difference between three groups (χ 2=10.94, P<0.01). The results of multivariate analysis showed that NLNE was an independent prognostic factor for overall survival ( P<0.05). Further analysis was performed specifically for subgroup of T stages. For T1b patients, the prognosis of the NLNE with 1-7 group was significantly better than that of the ≥8 group(χ 2=4.610, P<0.05). For T2 patients, the prognosis of the TLNE ≥7 group was significantly better than that of 1 -6 group (χ 2=4.287, P<0.05). For T3 and T4 patients, the prognosis of the TLNE with 12 - 15 group was significantly better than that of 1 -11 group (χ 2=5.007, P<0.01) and ≥16 group (χ 2=10.158, P<0.01). Conclusions:The NLNE is an independent factor affecting the prognosis of patients with GBC.For patients with stage T1b,8 lymph nodes should be retrieved; for patients with stage T2,extensive dissection of more than 6 lymph nodes can significantly improve the prognosis.For advanced patients (stages T3 and T4), extensive dissection with 12-15 lymph nodes is recommended. However, it fails to get more survival benefits by dissecting more than 16 lymph nodes.

Objective:To examine a survival prognostic model applicable for patients with intrahepatic cholangiocarcinoma (ICC) based on Bayesian network.Methods:The clinical and pathological data of ICC patients who underwent curative intent resection in ten Chinese hepatobiliary surgery centers from January 2010 to December 2018 were collected.A total of 516 patients were included in the study. There were 266 males and 250 females.The median age( M( Q R)) was 58(14) years.One hundred and sixteen cases (22.5%) with intrahepatic bile duct stones,and 143 cases (27.7%) with chronic viral hepatitis.The Kaplan-Meier method was used for survival analysis.The univariate and multivariate analysis were implemented respectively using the Log-rank test and Cox proportional hazard model.One-year survival prediction models based on tree augmented naive Bayesian (TAN) and na?ve Bayesian algorithm were established by Bayesialab software according to different variables,a nomogram model was also developed based on the independent predictors.The receiver operating characteristic curve and the area under curve (AUC) were used to evaluate the prediction effect of the models. Results:The overall median survival time was 25.0 months,and the 1-,3-and 5-year cumulative survival rates was 76.6%,37.9%,and 21.0%,respectively.Univariate analysis showed that gender,preoperative jaundice,pathological differentiation,vascular invasion,microvascular invasion,liver capsule invasion,T staging,N staging,margin,intrahepatic bile duct stones,carcinoembryonic antigen,and CA19-9 affected the prognosis(χ 2=5.858-54.974, all P<0.05).The Cox multivariate model showed that gender,pathological differentiation,liver capsule invasion, T stage,N stage,intrahepatic bile duct stones,and CA19-9 were the independent predictive factors(all P<0.05). The AUC of the TAN model based on all 19 clinicopathological factors was 74.5%,and the AUC of the TAN model based on the 12 prognostic factors derived from univariate analysis was 74.0%,the AUC of the na?ve Bayesian model based on 7 independent prognostic risk factors was 79.5%,the AUC and C-index of the nomogram survival prediction model based on 7 independent prognostic risk factors were 78.8% and 0.73,respectively. Conclusion:The Bayesian network model may provide a relatively accurate prognostic prediction for ICC patients after curative intent resection and performed superior to the nomogram model.