Zhang Chufan, Song Qian, Zhang Lanlin, Wu Xianghua
Departmemt of Medical Oncology, Fudan University Shanghai Cancer Center, Shanghai, China.
Department of Oncology, Shanghai Medical College, Fudan University, Shanghai, China.
J Thorac Dis. 2020 Jul;12(7):3651-3662. doi: 10.21037/jtd-20-601.
Lymph node dissection is an important part of lung cancer surgery. Preoperational evaluation of lymph node metastases decides which dissection pattern should be chosen. The present study aimed to develop a nomogram to predict lymph node metastases on the basis of clinicopathological features of non-small cell lung cancer (NSCLC) patients.
A total of 35,138 patients diagnosed with NSCLC from 2010-2015 were selected from the Surveillance, Epidemiology, and End Results (SEER) database. Patients were randomly divided into training cohort and validation cohort. Possible risk factors were included and analyzed by logistic regression models. A nomogram was then constructed and validated.
21.83% of all patients were confirmed with positive lymph node metastasis. Age at diagnosis, sex, stage, T status, tumor size, grade and laterality were identified as predicting factors for lymph node involvement. These variables were included to build the nomogram. The AUC of the model was 0.696 (95% CI, 0.617 to 0.775). The model was further validated in the validation set with AUC 0.693 (95% CI, 0.628 to 0.758). The model presented with good prediction accuracy in both training cohort and validation cohort.
We developed a convenient clinical prediction model for regional lymph node metastases in NSCLC patients. The nomogram will help physicians to determine which patients will receive the most benefit from lymph node dissection.
淋巴结清扫是肺癌手术的重要组成部分。术前对淋巴结转移情况进行评估可决定应选择何种清扫方式。本研究旨在基于非小细胞肺癌（NSCLC）患者的临床病理特征开发一种列线图，以预测淋巴结转移情况。
从监测、流行病学和最终结果（SEER）数据库中选取了2010年至2015年期间共35138例诊断为NSCLC的患者。将患者随机分为训练队列和验证队列。纳入可能的危险因素并通过逻辑回归模型进行分析。随后构建并验证了列线图。
所有患者中21.83%被证实存在阳性淋巴结转移。确诊年龄、性别、分期、T状态、肿瘤大小、分级和左右侧别被确定为淋巴结受累的预测因素。将这些变量纳入以构建列线图。该模型的曲线下面积（AUC）为0.696（95%置信区间，0.617至0.775）。该模型在验证集中进一步验证，AUC为0.693（95%置信区间，0.628至0.758）。该模型在训练队列和验证队列中均表现出良好的预测准确性。
我们为NSCLC患者区域淋巴结转移开发了一种便捷的临床预测模型。该列线图将有助于医生确定哪些患者将从淋巴结清扫中获益最大。
