正常肺体积定义对局部晚期非小细胞肺癌放疗放射性肺炎风险预测的影响
本研究基于NRG Oncology RTOG 0617试验中442例局部晚期非小细胞肺癌患者的治疗计划,评估三种正常肺体积定义对放射性肺炎(RP)风险预测的影响。统计分析显示V20和平均肺剂量(MLD)与≥2级RP显著相关,而不同肺体积定义间差异无统计学意义;机器学习和SHAP分析表明以总肺减计划靶体积(TL-PTV)定义时预测性能最高。
要点
- V20和MLD与≥2级放射性肺炎显著相关,为最具影响力的预测因子。
- 三种肺体积定义对RP2预测的统计学差异不显著。
- 机器学习模型显示TL-PTV定义下RP2预测的AUC最高。
核心结论
- 统计分析和SHAP解释均证实V20和MLD与≥2级放射性肺炎相关。
- 机器学习模型提示以总肺减计划靶体积(TL-PTV)定义正常肺体积时RP2风险预测性能最高。
研究设计与样本
- 回顾性分析NRG Oncology RTOG 0617试验中442例局部晚期非小细胞肺癌患者的治疗计划。
- 评估三种正常肺体积定义:总肺减大体肿瘤靶区、总肺减临床靶体积、总肺减计划靶体积(TL-PTV)。
- 患者分为无RP2组(N=377,RP分级≤1级)和RP2组(N=65,RP分级≥2级)。
- 采用逻辑回归、k近邻(kNN)和极端梯度提升三种监督机器学习模型评估预测性能。
- 模型性能以受试者工作特征曲线下面积量化,并通过bootstrap分析检验统计学显著性。
主要发现
- 统计分析显示V20和MLD与RP2显著相关。
- 不同肺体积定义之间的差异无统计学意义。
- kNN和极端梯度提升分类器在TL-PTV定义下 consistently 获得更高的AUC值,bootstrap分析支持该发现。
- SHAP分析表明V20和MLD是RP2最具影响力的预测因子。
临床怎么用
- 在局部晚期非小细胞肺癌放疗中,V20和MLD可作为放射性肺炎风险预测的关键剂量学指标。
- 机器学习模型提示以TL-PTV定义正常肺体积可能提高RP2风险预测性能,但需外部数据验证。
局限性
- 研究基于NRG Oncology RTOG 0617试验数据,需外部数据集进一步验证以确认发现。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
PURPOSE: This study aims to evaluate the impact of varying definitions of normal lung volume on the prediction of radiation pneumonitis (RP) risk in patients with locally advanced non-small cell lung cancer undergoing radiation therapy. METHODS AND MATERIALS: Dosimetric variables V20, V5, and mean lung dose (MLD) were extracted from the treatment plans of 442 patients enrolled in the NRG Oncology Radiation Therapy Oncology Group 0617 trial. Three different definitions of lung volume were evaluated: total lung excluding gross tumor target, total lung excluding clinical target volume, and total lung excluding planning target volume (TL-PTV). Patients were grouped as "no-RP2" (N = 377, grade ≤1 RP) and "RP2" (N = 65, grade ≥2 RP). Statistical analyses were performed to assess the effect of lung volume definition on RP2 prediction. Three supervised machine learning models-logistic regression, k-nearest neighbor (kNN), and eXtreme Gradient Boosting-were used to evaluate predictive performance. Model performance was quantified using the area under the receiver operating characteristic curve, and statistical significance was tested via a bootstrap analysis. Shapley Additive Explanations (SHAP) were applied to interpret feature contributions to model predictions. RESULTS: Statistical analyses showed that V20 and MLD were significantly associated with RP2, while differences among the lung volume definitions were not statistically significant. Both k-nearest neighbor and eXtreme Gradient Boosting classifiers consistently yielded higher area under the receiver operating characteristic curve values for the TL-PTV definition compared to the other definitions, a finding supported by bootstrap analysis. SHAP analysis further indicated that V20 and MLD were the most influential predictors of RP2. CONCLUSIONS: In line with previous studies, both statistical analysis and SHAP interpretation confirmed that V20 and MLD were associated with RP2. The machine learning models indicated that defining normal lung volume as TL-PTV yielded the highest predictive performance for RP2 risk. Further validation using external data sets are warranted to confirm these findings.
引用
- Gadsby A, Liu T, Samstein R, et al. Impact of Normal Lung Volume Choices on Radiation Pneumonitis Risk Prediction in Locally Non-small Cell Lung Cancer Radiation Therapy. Adv Radiat Oncol. 2025. PMID: 40686740. doi:10.1016/j.adro.2025.101825
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。