肺癌脑转移立体定向放疗:基于生物效应剂量的剂量优化与预后预测
本研究回顾性纳入449例2006年6月至2025年3月接受射波刀治疗的肺癌脑转移患者,建立基于BED的分层经验剂量反应模型分析BED10与局部控制关系,并采用XGBoost机器学习模型预测早期KPS下降和肿瘤控制,结合SHAP实现可解释性。结果显示剂量反应存在体积依赖性,2-3cm肿瘤TCD50最高(1年62.52 Gy,2年62.48 Gy),ML模型预测早期KPS下降AUC达0.874,BED10对神经功能结局的影响受基线功能调节,持续靶向治疗联合高BED10对肿瘤控制显示最有利协同效应。
要点
- 2-3cm脑转移瘤TCD50最高,1年62.52 Gy、2年62.48 Gy
- ML模型预测早期KPS下降AUC为0.874
- 低BED10(30-60 Gy)增加基线神经功能差者KPS下降风险
核心结论
- 肺癌脑转移射波刀治疗中剂量反应存在体积依赖性异质性。
- BED10对功能结局的影响呈基线依赖的双重效应。
- ML结合BED经验剂量反应模型可为个体化剂量处方和联合策略提供依据。
研究设计与样本
- 回顾性研究纳入449例2006年6月至2025年3月接受射波刀治疗的肺癌脑转移患者。
- 按最大肿瘤直径(≤2 cm、2-3 cm、>3 cm)建立分层BED经验剂量反应模型分析BED10与局部控制关系。
- 采用XGBoost算法构建预测早期KPS下降和肿瘤控制的模型,纳入BED10、基线神经状态和靶向治疗模式。
- 使用SHAP实现模型可解释性。
主要发现
- BED经验剂量反应模型显示剂量反应存在显著体积依赖性。
- 2-3 cm肿瘤获得50%控制所需剂量最高,1年TCD50为62.52 Gy,2年TCD50为62.48 Gy。
- ML模型预测早期KPS下降的AUC为0.874。
- SHAP分析显示低BED10(30-60 Gy)增加基线神经功能差(grade ≥2)患者KPS下降风险。
- 高BED10(60-90 Gy)对基线功能好(grade <2)患者具保护作用,持续靶向治疗联合高BED10对肿瘤控制协同最优。
关键数值与推荐
- 2-3 cm肿瘤1年TCD50为62.52 Gy。
- 2-3 cm肿瘤2年TCD50为62.48 Gy。
- 低BED10范围为30-60 Gy,高BED10范围为60-90 Gy。
- 基线神经功能差定义为grade ≥2,功能好定义为grade <2。
- ML模型预测早期KPS下降的AUC为0.874。
临床怎么用
- 可参考体积分层TCD50值(2-3 cm者1年62.52 Gy、2年62.48 Gy)辅助个体化剂量处方。
- 对基线神经功能差(grade ≥2)者需警惕低BED10(30-60 Gy)增加KPS下降风险。
- 对基线功能好(grade <2)者高BED10(60-90 Gy)可能具神经功能保护作用。
- 持续靶向治疗联合高BED10可作为优化局部控制的联合策略。
- 可利用XGBoost结合SHAP模型辅助预测早期KPS下降和肿瘤控制。
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 aimed to integrate BED-based empirical dose-response modeling (logistic regression-derived tumor control probability) with interpretable machine learning (ML) to investigate the complex interactions among biologically effective dose (BED10), tumor volume, neurologic function, and targeted therapy patterns in stereotactic radiosurgery (SRS) for lung cancer brain metastases (BM), thereby optimizing personalized treatment strategies. METHODS AND MATERIALS: In this retrospective study, 449 lung cancer patients with BM treated with CyberKnife between June 2006 and March 2025 were enrolled. Stratified BED-based empirical dose-response models based on maximum tumor diameter (≤2 cm, 2-3 cm, >3 cm) were established to analyze BED10 and local control relationship. The extreme gradient boosting (XGBoost) algorithm was employed to build predictive models for early Karnofsky performance status (KPS) decline and tumor control, incorporating BED10, baseline neurologic status, and targeted therapy patterns. Model interpretability was achieved using SHapley Additive exPlanations (SHAP). RESULTS: BED-based empirical dose-response modeling revealed significant volume dependence in dose response. Tumors of 2 to 3 cm required the highest dose for 50% control (dose required for 50% tumor control [TCD50]: 62.52 Gy for 1-year; 62.48 Gy for 2-year). The ML model excellently predicted early KPS decline (area under the curve, 0.874). SHAP analysis demonstrated that BED10 effect on neurologic outcomes was modulated by baseline function: lower BED10 (30-60 Gy) increased KPS decline risk in patients with poor baseline neurologic function (grade ≥2), whereas higher BED10 (60-90 Gy) was protective in those with good function (grade <2). Continuous targeted therapy combined with high BED10 showed the most favorable synergistic effect on tumor control. CONCLUSIONS: This study confirms volume-dependent heterogeneity in dose response for BM and reveals a dual, baseline-dependent impact of BED10 on functional outcomes. The integration of ML with BED-based empirical dose-response modeling provides valuable insights for individualized dose prescription and combined modality strategies, supporting continuous targeted therapy with high BED10 as a key approach for optimizing local control.
引用
- Wu F, Shi J, He W, et al. Stereotactic Radiation Therapy for Lung Cancer Brain Metastases: Dose Optimization and Prognostic Prediction via Biologically Effective Dose-Based Empirical Dose-Response Modeling and Extreme Gradient Boosting-SHapley Additive Explanations Machine Learning. Adv Radiat Oncol. 2026. PMID: 42644064. doi:10.1016/j.adro.2026.102147
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。