头颈癌放疗下颌骨放射性骨坏死的经验相对生物效应因果机器学习分析
该研究纳入1266例头颈癌患者(335例PBSPT,931例VMAT),采用倾向评分1:1匹配后各335例,并以因果森林评估剂量学因素与下颌骨ORN的因果关系。结果显示PBSPT的DVC体积阈值低于VMAT,经验RBE在中等剂量区超过1.1(40 Gy[RBE]为1.61、50 Gy[RBE]为1.30、60 Gy[RBE]为1.13),提示PBSPT计划需考虑终点特异性可变RBE。
要点
- PBSPT下颌骨ORN的DVC体积阈值低于VMAT。
- 经验RBE在40-60 Gy[RBE]中等剂量区超过1.1。
- 因果森林识别的DVC阈值属假设生成,需前瞻性验证。
核心结论
- 质子RBE在中等剂量区(40-60 Gy[RBE])可能超过1.1,PBSPT计划应纳入终点特异性可变RBE。
研究设计与样本
- 多中心(原文未明说)回顾性队列纳入1266例头颈癌患者,PBSPT组335例、VMAT组931例。
- 采用1:1倾向评分匹配,以标准化均数差评估残余临床因素失衡,并采用因果森林分析剂量学因素与ORN的因果关系。
主要发现
- 匹配后各组仍存在协变量失衡,提示残余混杂影响。
- 因果森林识别的PBSPT下颌骨ORN候选DVC体积阈值低于VMAT。
- 阈值稳定性分析支持经验RBE分析所用DVC阈值的稳健性。
- 经验RBE在40 Gy[RBE]为1.61、50 Gy[RBE]为1.30、60 Gy[RBE]为1.13。
关键数值与推荐
- 对每种模态和每个预设DVH指标系统评估候选剂量-体积阈值,选取CF估计平均治疗效应最大的体积阈值作为DVC体积阈值。
- 经验RBE由模态特异性体积-耐受曲线在等体积交点处、将PBSPT Gy[RBE]转换为物理剂量后推导。
临床怎么用
- PBSPT计划设计时可参考中等剂量区RBE可能>1.1的经验值,关注下颌骨DVC体积阈值。
- 因果森林识别的DVC体积阈值应视为假设生成的风险区域,而非确定性临床 cutoff。
局限性
- 匹配后仍存在协变量失衡,提示残余混杂。
- CF识别的DVC体积阈值需独立前瞻性验证。
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: Osteoradionecrosis (ORN) of the mandible is one of the most severe adverse events for head and neck (H&N) cancer radiation therapy. Previous retrospective investigations on real-world data relied heavily on conventional statistical models that primarily elucidate correlation rather than establishing causal relationships. Through the novel causal machine learning method, we aim to obtain empirical relative biological effectiveness (RBE) for mandible ORN in patients with H&N cancer treated with pencil-beam-scanning proton therapy (PBSPT). METHODS AND MATERIALS: A total of 1266 patients with H&N cancer were included: 335 patients treated by PBSPT and 931 patients treated by volumetric modulated arc therapy (VMAT). We used 1:1 propensity-score case matching to minimize imbalance in clinical factors between patients treated with PBSPT and VMAT. Standardized mean differences were used to assess residual clinical-factor imbalance within the case-matched cohorts. Causal forest (CF) was adopted to investigate the causal effects between dosimetric factors and the incidence of ORN. For each modality and each prespecified dose-volume histogram (DVH) index, candidate dose-volume thresholds were evaluated systematically, and the volume threshold yielding the largest CF-estimated average treatment effect was selected as the dose-volume constraint (DVC) volume threshold. Empirical RBE values were derived from equal-volume intersections on modality-specific volume-tolerance curves after converting PBSPT Gy[RBE] values to physical dose. RESULTS: A total of 335 VMAT patients were case-matched to 335 patients treated by PBSPT; however, standardized mean bias analysis revealed persistent covariate imbalances within each group, indicating residual confounding influence. Using CF modeling, we identified candidate DVC volume thresholds for mandibular ORN and found that PBSPT had lower selected DVC volume thresholds than VMAT. The threshold-stability analyses supported the robustness of the DVC thresholds emphasized in the empirical RBE analysis. The resulting empirical RBE exceeded 1.1 in the moderate dose range (1.61 at 40 Gy[RBE], 1.30 at 50 Gy[RBE], and 1.13 at 60 Gy[RBE]). CONCLUSIONS: This study presents a novel application of causal machine learning to evaluate mandibular ORN in radiation therapy, identifying candidate DVC volume thresholds linked to the strongest threshold-defined causal effects and deriving empirical RBEs from equal-volume equivalent constraint dose analysis based on volume-tolerance curves. The results indicate that proton RBE may exceed 1.1 in the moderate dose range (40-60 Gy[RBE]), underscoring the importance of considering endpoint-specific variable RBE in PBSPT treatment planning. These CF-identified DVC volume thresholds should be interpreted as hypothesis-generating risk regions rather than definitive clinical cutoffs, pending independent prospective validation.
引用
- Chen J, Liu Z, Yang Y, et al. Causal Machine Learning Analysis of Empirical Relative Biological Effectiveness for Mandible Osteoradionecrosis in Head and Neck Cancer Radiation Therapy. Int J Radiat Oncol Biol Phys. 2026. PMID: 42624220. doi:10.1016/j.ijrobp.2026.08.018
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。