Thor Maria, Deasy Joseph O, Hu Chen, Gore Elizabeth, Bar-Ad Voichita, Robinson Clifford, Wheatley Matthew, Oh Jung Hun, Bogart Jeffrey, Garces Yolanda I, Kavadi Vivek S, Narayan Samir, Iyengar Puneeth, Witt Jacob S, Welsh James W, Koprowski Cristopher D, Larner James M, Xiao Ying, Bradley Jeffrey
Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, New York.
NRG Oncology Statistics and Data Management Center, Philadelphia, Pennsylvania.
Clin Cancer Res. 2020 Sep 1;26(17):4643-4650. doi: 10.1158/1078-0432.CCR-19-2627. Epub 2020 May 12.
To quantitatively predict the impact of cardiopulmonary dose on overall survival (OS) after radiotherapy for locally advanced non-small cell lung cancer.
We used the NRG Oncology/RTOG 0617 dataset. The model building procedure was preregistered on a public website. Patients were split between a training and a set-aside validation subset ( = 306/131). The 191 candidate variables covered disease, patient, treatment, and dose-volume characteristics from multiple cardiopulmonary substructures (atria, lung, pericardium, and ventricles), including the minimum dose to the hottest x% volume (Dx%[Gy]), mean dose of the hottest x% (MOHx%[Gy]), and minimum, mean (Mean[Gy]), and maximum dose. The model building was based on Cox regression and given 191 candidate variables; a Bonferroni-corrected value threshold of 0.0003 was used to identify predictors. To reduce overreliance on the most highly correlated variables, stepwise multivariable analysis (MVA) was repeated on 1000 bootstrapped replicates. Multivariate sets selected in ≥10% of replicates were fit to the training subset and then averaged to generate a final model. In the validation subset, discrimination was assessed using Harrell -index, and calibration was tested using risk group stratification.
Four MVA models were identified on bootstrap. The averaged model included atria D45%[Gy], lung Mean[Gy], pericardium MOH55%[Gy], and ventricles MOH5%[Gy]. This model had excellent performance predicting OS in the validation subset ( = 0.89).
The risk of death due to cardiopulmonary irradiation was accurately modeled, as demonstrated by predictions on the validation subset, and provides guidance on the delivery of safe thoracic radiotherapy.
定量预测局部晚期非小细胞肺癌放疗后心肺剂量对总生存期（OS）的影响。
我们使用了NRG肿瘤学/RTOG 0617数据集。模型构建过程已在公共网站上预先注册。患者被分为训练子集和预留验证子集（n = 306/131）。191个候选变量涵盖了来自多个心肺亚结构（心房、肺、心包和心室）的疾病、患者、治疗和剂量体积特征，包括最热x%体积的最小剂量（Dx%[Gy]）、最热x%的平均剂量（MOHx%[Gy]）以及最小、平均（Mean[Gy]）和最大剂量。模型构建基于Cox回归并给定191个候选变量；使用经Bonferroni校正的P值阈值0.0003来识别预测因子。为减少对相关性最高变量的过度依赖，在1000次自抽样重复样本上重复进行逐步多变量分析（MVA）。在≥10%的重复样本中选择的多变量集拟合训练子集，然后求平均值以生成最终模型。在验证子集中，使用Harrell C指数评估辨别力，并使用风险组分层测试校准。
在自抽样中确定了四个MVA模型。平均模型包括心房D45%[Gy]、肺Mean[Gy]、心包MOH55%[Gy]和心室MOH5%[Gy]。该模型在验证子集中预测OS具有出色的性能（C = 0.89）。
如在验证子集上的预测所示，心肺照射导致的死亡风险得到了准确建模，并为安全的胸部放疗提供了指导。
