基于LASSO-Logistic回归构建Siewert Ⅱ/Ⅲ型食管胃结合部腺癌术后早期复发预测模型  

Establishment of a LASSO⁃Logistic Regression⁃based Risk Prediction Model for Early Recurrence of SiewertⅡ/ⅢAdenocarcinoma of Esophagogastric Junction Post⁃Surgery

作　　者：张祖禹 魏红 刘倩[1] 王耀强 樊雪雁 罗瑞英 罗长江[1] ZHANG Zuyu;WEI Hong;LIU Qian;WANG Yaoqiang;FAN Xueyan;LUO Ruiying;LUO Changjiang(Department of General Surgery,Lanzhou University Second Hospital,Lanzhou 730030,China)

机构地区：[1]兰州大学第二医院普通外科,兰州730030

出　　处：《协和医学杂志》2024年第3期604-615,共12页Medical Journal of Peking Union Medical College Hospital

基　　金：甘肃省科技计划(21JR1RA139,21JR11RA113);萃英博导培育计划(CYDSPY202004)。

摘　　要：目的 探讨SiewertⅡ/Ⅲ型食管胃结合部腺癌(adenocarcinoma of esophagogastric junction, AEG)根治术后早期复发的危险因素,构建可视化预测模型。方法 回顾性分析2016年1月至2021年3月兰州大学第二医院诊断为SiewertⅡ/Ⅲ型AEG且接受根治性切除术患者的临床病理资料,将样本以7∶3的比例随机分为建模组与验证组。采用LASSO-Logistic回归分析法筛选出预测SiewertⅡ/Ⅲ型AEG早期复发的变量,并构建早期复发预测模型。基于Bootstrap法进行1000次重复抽样验证模型。绘制受试者工作特征(receiver operating characteristic, ROC)曲线,计算曲线下面积(area under curve, AUC),绘制校准曲线和决策曲线(decision curve analysis, DCA)对模型的稳定性进行评估。结果根据纳入与排除标准,共320例SiewertⅡ/Ⅲ型AEG患者最终纳入分析,其中2年内复发者122例;LASSO-Logistic回归分析显示,AJCC分期、分化程度、糖类抗原199、癌胚抗原、中性粒细胞与淋巴细胞比值及肿瘤长径是SiewertⅡ/Ⅲ型AEG早期复发的独立预测因素,依此构建预测模型并绘制列线图。绘制ROC曲线得到建模组AUC为0.836(95%CI:0.785~0.887),灵敏度为81.4%,特异度为85.6%;验证组AUC为0.812(95%CI:0.711~0.912),灵敏度为80.6%,特异度为87.7%。建模组与验证组的校准曲线显示拟合曲线与参考曲线接近,表明模型具有较高稳定性。DCA曲线显示阈值概率在0.05~0.75时模型具有良好的净收益。结论 基于LASSO-Logistic回归分析法构建的预测SiewertⅡ/Ⅲ型AEG早期复发的多因素模型,有助于判断患者临床预后,为术后病情监测与管理提供参考依据。Objective To investigate the risk factors for early relapse after curative resection of Siewert typeⅡ/Ⅲadenocarcinoma of esophagogastric junction(AEG)and construct a visual predictive model.Methods A retrospective analysis was conducted on the clinicopathological data of patients diagnosed with Siewert typeⅡ/ⅢAEG who underwent curative resection at the Second Hospital of Lanzhou University from January 2016 to March 2021.The samples were randomly divided into a training group and a validation group in a 7∶3 ra-tio.The LASSO-Logistic regression method was used to select variables predictive of early recurrence of Siew-ert typeⅡ/ⅢAEG and construct a predictive model for early recurrence.The model was validated through 1000 bootstrap resampling.Receiver operating characteristic(ROC)curves were drawn,and area under the curve(AUC),calibration curves,and decision curve analysis(DCA)were used to evaluate the models stability.Results According to the inclusion and exclusion criteria of this study,a total of 320 Siewert typeⅡ/ⅢAEG patients were included,with 122 experiencing recurrence within two years.LASSO-Logistic re-gression analysis revealed AJCC staging,degree of differentiation,CA199,CEA,NLR,and tumor maxi-mum diameter as independent predictive factors for early recurrence of Siewert typeⅡ/ⅢAEG.A predictive model was constructed with these factors and depicted as a nomogram.For the training group,the AUC of the ROC curve was 0836(95%CI:0785-0887),with a sensitivity of 814%and a specificity of 856%;for the validation group,the AUC was 0812(95%CI:0711-0912),with a sensitivity of 806%and a specificity of 877%.Calibration curves for both the training and validation groups displayed curves close to the reference line,indicating high model stability.The DCA curve showed that the model pro-vided a good net benefit with threshold probabilities between 005 and 075.Conclusions A multivariate model developed using LASSO-Logistic regression could predict early relapse in patients with Siewert typeⅡ/ⅢA

关 键 词：SiewertⅡ/Ⅲ型食管胃结合部腺癌 复发 预测模型 LASSO-Logistic回归 列线图 

分 类 号：R619[医药卫生—外科学] R735[医药卫生—临床医学]