Jin Hengwei, Sun Xu, Fu Chang, Fan Changqing, Chen Junhong, Zhang Ziyu, Yang Yibo, Fan Xiaoyu, He Ye, Yin Siyuan, Liu Kai
Department of Hepatobiliary and Pancreatic Surgery, General Surgery Center, First Hospital of Jilin University, No. 71, Xinmin Street, Changchun, Jilin Province, China.
Clinical Medical College, Changchun University of Traditional Chinese Medicine, Changchun, Jilin Province, China.
Surg Endosc. 2025 Jul 9. doi: 10.1007/s00464-025-11937-5.
Endoscopic retrograde cholangiopancreatography (ERCP) is the preferred palliative treatment for patients with unresectable malignant biliary obstruction (MBO), which can relieve biliary obstruction and prolong survival. Post-ERCP cholangitis (PEC) affects the survival of MBO patients. Early prediction of PEC risk is crucial for developing individualized treatment plans and improving prognosis. Currently, no predictive models exist for clinical practice. This study aims to develop and validate an interpretable machine learning prediction model using multicenter cohorts to predict the risk of PEC.
We collected data from 2831 unresectable MBO patients who underwent ERCP between January 2011 and December 2023. After screening, data from 1026 patients from the First Hospital of Jilin University served as training and internal test cohorts, while data from 395 patients from the Third Hospital of Jilin University were used as an external validation cohort. Six machine learning methods were employed to construct prediction models. Model performance was compared using various metrics. The SHapley Additive exPlanation (SHAP) method was used to interpret the final model.
Among all MBO patients, the incidence of PEC was 9.5% (135/1421). Multivariate analysis identified radiofrequency ablation (OR = 3.62, 95% CI 1.26-10.36), white blood cell count (OR = 1.34, 95% CI 1.12-1.60), moderate jaundice (OR = 3.57, 95% CI 1.06-12.09), and abnormal serum amylase (OR = 3.05, 95% CI 1.36-6.79) as independent risk factors for PEC. Four important variables were selected through machine learning methods: radiofrequency ablation, white blood cell count, severity of jaundice, and serum amylase. Among the six machine learning models, the XGBoost model performed best (training cohort AUC: 0.9654). This model accurately predicted PEC risk in MBO patients in both the internal test cohort (AUC: 0.7670) and external validation cohort (AUC: 0.7270). Calibration curves showed good consistency between predicted and observed risks. Decision curve analysis indicated that the model provided substantial clinical net benefit.
Based on multicenter, large-sample data, we developed and validated an interpretable XGBoost model for predicting PEC risk in MBO patients. This model helps clinicians identify high-risk patients preoperatively, providing a basis for individualized treatment plans and thereby improving patient prognosis.
内镜逆行胰胆管造影术（ERCP）是不可切除恶性胆管梗阻（MBO）患者的首选姑息治疗方法，可缓解胆管梗阻并延长生存期。ERCP术后胆管炎（PEC）影响MBO患者的生存。早期预测PEC风险对于制定个体化治疗方案和改善预后至关重要。目前，临床实践中尚无预测模型。本研究旨在开发并验证一种可解释的机器学习预测模型，使用多中心队列来预测PEC风险。
我们收集了2011年1月至2023年12月期间接受ERCP的2831例不可切除MBO患者的数据。经过筛选，吉林大学第一医院1026例患者的数据用作训练和内部测试队列，吉林大学第三医院395例患者的数据用作外部验证队列。采用六种机器学习方法构建预测模型。使用各种指标比较模型性能。采用SHapley加性解释（SHAP）方法解释最终模型。
在所有MBO患者中，PEC的发生率为9.5%（135/1421）。多变量分析确定射频消融（OR = 3.62，95%CI 1.26 - 10.36）、白细胞计数（OR = 1.34，95%CI 1.12 - 1.60）、中度黄疸（OR = 3.57，95%CI 1.06 - 12.09）和血清淀粉酶异常（OR = 3.05，95%CI 1.36 - 6.79）为PEC的独立危险因素。通过机器学习方法选择了四个重要变量：射频消融、白细胞计数、黄疸严重程度和血清淀粉酶。在六种机器学习模型中，XGBoost模型表现最佳（训练队列AUC：0.9654）。该模型在内部测试队列（AUC：0.7670）和外部验证队列（AUC：0.7270）中均能准确预测MBO患者的PEC风险。校准曲线显示预测风险与观察到的风险之间具有良好的一致性。决策曲线分析表明该模型提供了显著的临床净效益。
基于多中心、大样本数据，我们开发并验证了一种可解释的XGBoost模型，用于预测MBO患者的PEC风险。该模型有助于临床医生在术前识别高危患者，为个体化治疗方案提供依据，从而改善患者预后。
