基于SEER数据库胆囊癌远处转移风险列线图的构建  

Construction of risk nomogram of distant metastasis in gallbladder cancer based on the SEER database

作　　者：蔚应飞 王梦成 孟涛 童钟[1] WEI Yingfei;WANG Mengcheng;MENG Tao;TONG Zhong(Hepatopancreatobiliary Surgery Department,Hefei First People’s Hospital,Hefei 230001,Anhui,China)

机构地区：[1]合肥市第一人民医院肝胆胰外科,安徽合肥2300011

出　　处：《中国现代医生》2025年第9期15-19,28,共6页China Modern Doctor

摘　　要：目的探讨影响胆囊癌(gallbladder carcinoma,GBC)患者远处转移风险的临床因素,并构建转移风险预测模型。方法回顾性纳入2000年1月至2021年12月监测、流行病学和最终结果(surveillance,epidemiology,and end results,SEER)数据库4979例GBC患者,按7∶3比例分为训练集(n=3485)和内部验证集(n=1494)。收集合肥市第一人民医院2009年1月至2024年12月47例GBC患者作为外部验证集。在训练集中,通过单因素、多因素分析确定GBC远处转移的独立预测因子并构建预测模型,使用受试者操作特征曲线下面积(area under the curve,AUC)评估预测能力,通过校准曲线和临床决策曲线评估模型的校准性和临床实用性。结果单因素、多因素分析结果显示,白种人、肿瘤大小、T分期和N分期是GBC患者远处转移的独立危险因素(P<0.05),基于以上因素构建的预测模型AUC为0.727,显示有良好的预测能力。在训练集、内部验证集、外部验证集中,该预测模型的预测结果和实际情况有良好的一致性。结论通过SEER数据库所建立的列线图可较为准确地预测GBC患者的远处转移情况且具有良好的临床应用性,可帮助临床医师直观评价GBC患者的远处转移率,从而制订个性化治疗方案。Objective To investigate the clinical factors affecting the risk of distant metastasis in patients with gallbladder carcinoma(GBC)and to construct a predictive model for metastasis risk.Methods Retrospective analysis was conducted on 4979 GBC patients from the surveillance,epidemiology,and end results(SEER)database from January 2000 to December 2021,which were divided into a training set(n=3485)and an internal validation set(n=1494)in a 7:3 ratio.Additionally,47 GBC patients from Hefei First People’s Hospital from January 2009 to December 2024 were collected as an external validation set.In the training set,univariate and multivariate analyses were performed to identify independent predictors of distant metastasis in GBC and to construct a predictive model.The predictive ability of the model was assessed by using area under the receiver operating characteristic curve.The model’s calibration and clinical utility were evaluated through calibration curves and decision curve analysis.Results The results of univariate and multivariate analyses revealed that Caucasian,tumor size,T stage,and N stage were independent risk factors for distant metastasis in patients with GBC(P<0.05).The predictive model constructed based on these factors had an AUC of 0.727,indicating good predictive performance.In the training set,internal validation set,and external validation set,the predictive results of this model showed good consistency with the actual situation.Conclusion The nomogram established by using SEER database can accurately predict the distant metastasis status in patients with GBC and demonstrates good clinical applicability.It assists clinicians in intuitively assessing the distant metastasis rate in GBC patients,thereby facilitating the formulation of personalized treatment plans.

关 键 词：胆囊癌 远处转移 影响因素 预测模型 

分 类 号：R735.8[医药卫生—肿瘤]