食管癌新辅助治疗后喉返神经旁淋巴结状态预测模型构建  

Prediction model establishment for the status of recurrent laryngeal nerve lymph node after neoadjuvant therapy in esophageal cancer

作　　者：彭泽学 梁宝丹 吴丰泽 周淑敏 李贻卓[2] 刘立志[2] PENG Zexue;LIANG Baodan;WU Fengze;ZHOU Shumin;LI Yizhuo;LIU Lizhi(Department of Radiology,Xiangya Changde Hospital,Changde,Hu’nan Province 415600,China;Department of Radiology,Sun Yat-Sen University Cancer Center,Guangzhou 510000,China)

机构地区：[1]湘雅常德医院放射科,湖南常德415600 [2]中山大学肿瘤防治中心影像科,广东广州510000

出　　处：《实用放射学杂志》2024年第6期888-892,共5页Journal of Practical Radiology

基　　金：湖南省卫生健康委员会科研计划项目(202209015379);广东省食管癌研究所科技计划项目(M-202016)。

摘　　要：目的应用食管癌新辅助治疗前临床及CT图像数据构建新辅助治疗后喉返神经旁淋巴结(RLN LN)状态预测模型。方法回顾性选取403例接受新辅助治疗以及食管癌根治性切除术的局部晚期食管癌患者,将所有患者以2︰1的比例随机分为训练组(270例)和验证组(133例),采用单因素分析筛选出RLN LN病理阳性相关的临床和影像特征。采用多因素logistic逐步回归模型构建预测模型,计算受试者工作特征(ROC)曲线评估模型预测能力。结果本研究将新辅助治疗方式及RLN LN短径纳入基础模型,训练组和验证组的曲线下面积(AUC)分别为0.7和0.65。将新辅助治疗方式、人血白蛋白、血小板计数、最大淋巴结强化特点、最大淋巴结是否在喉返区、RLN LN短径等因素纳入最终预测模型,训练组和验证组的AUC分别为0.83[95%置信区间(CI)0.768~0.899]、0.76(95%CI 0.645~0.887)。结论基于食管癌新辅助治疗前临床数据及影像学特征的模型可辅助临床预测新辅助治疗后RLN LN状态。Objective To construct a prediction model for post-neoadjuvant therapy recurrent laryngeal nerve lymph node(RLN LN)status via clinical and CT image data in esophageal cancer patients pre-neoadjuvant therapy.Methods A retrospective analysis was conducted on 403 patients with locally advanced esophageal cancer who received neoadjuvant therapy and radical resection for esophageal cancer.All patients were divided into a training cohort(n=270)and a validation cohort(n=133)randomly according to a 2︰1 ratio.Clinical and imaging features associated with positive RLN LN pathology were selected by univariate analysis.Multivariate logistic stepwise regression model was used to construct the prediction model.The prediction ability of the model was evaluated by receiver operating characteristic(ROC)curve.Results The basic model included neoadjuvant therapy and RLN LN short diameter,with an area under the curve(AUC)of 0.7(training cohort)and 0.65(validation cohort).The final prediction model included neoadjuvant therapy,human albumin,platelet count,largest lymph node enhancement characteristics,whether the largest lymph node was in the recurrent laryngeal region,and RLN LN short diameter,with AUC of 0.83[95%confidence interval(CI)0.768-0.899]and 0.76(95%CI 0.645-0.887)for the training and validation cohorts,respectively.Conclusion The model based on clinical data and imaging features pre-neoadjuvant therapy for esophageal cancer can assist in clinically predicting the post-neoadjuvant therapy RLN LN status.

关 键 词：食管癌 新辅助治疗 喉返神经旁淋巴结 计算机体层成像 

分 类 号：R735.1[医药卫生—肿瘤] R730.59[医药卫生—临床医学] R814.42