直肠癌术后淋巴结转移Nomogram预测模型的构建:基于SEER数据库  

Nomogram predicting postoperative lymph node metastasis in patients with rectal cancer:an analysis using the SEER database

作　　者：刘小双 史俊[3] 闫飞虎 史晓辉 Liu Xiaoshuang;Shi Jun;Yan Feihu;Shi Xiaohui(Department of Colorectal Surgery,The First Affiliated Hospital of Naval Medical University,Shanghai 200433,China;Department of General Surgery,Shuguang Affiliated Hospital of Shanghai University of Traditional Chinese Medicine,Shanghai 200021,China;Department of Gastrointestinal Surgery,Yixing People’s Hospital—Affiliated Hospital of Jiangsu University,Wuxi 214200,Jiangsu China)

机构地区：[1]海军军医大学第一附属医院肛肠外科,上海200433 [2]上海中医药大学附属曙光医院普外科,上海200021 [3]江苏大学附属宜兴人民医院胃肠外科,江苏无锡214200

出　　处：《结直肠肛门外科》2021年第3期231-235,共5页Journal of Colorectal & Anal Surgery

摘　　要：目的构建直肠癌术后淋巴结转移的Nomogram预测模型。方法通过筛选SEER数据库中3405例直肠癌患者的临床资料,按照7:3比例分为训练集和验证集。通过LASSO回归分析和多因素Logistic回归分析筛选出临床因素,构建Nomogram预测模型,并进行验证。结果Nomogram预测模型含有年龄、肿瘤分化程度、T分期、cN分期、CEA等5个因素。该模型具有良好的预测性能,其C-index为0.761(95%CI:0.742~0.780),并且获得了良好的校准图。验证集获得了较高的C-index为0.758(95%CI:0.729~0.787),同时也获得贴合良好的校准图。结论该Nomogram预测模型可较好地预测直肠癌术后淋巴结转移的情况。Objectives To construct a Nomogram predicting postoperative lymph node metastasis in patients with rectal cancer.Methods A total of 3,405 patients with rectal cancer were selected from SEER database.Patients were allocated to the training set and validation set with a ratio of 7:3.Clinical factors were selected with LASSO regression analyses and multivariate Logistic regression analyses.A Nomogram was constructed and validated.Results Factors included in the Nomogram included age,tumor differentiation,T stage,cN stage,and carcinoembryonic antigen.This Nomogram has satisfactory predictive ability with a C-index of 0.761(95%CI:0.742~0.780)and a well-fitted calibration diagram.C-index for the validation set was 0.758(95%CI:0.729~0.787),and calibration diagram for the validation set was also well-fitted.Conclusion This Nomogram can reliably predict postoperative lymph node metastasis in patients with rectal cancer.

关 键 词：直肠癌 术后淋巴结转移 预测模型 

分 类 号：R735.37[医药卫生—肿瘤] TP311.13[医药卫生—临床医学]