文献速递胸部肿瘤放疗放疗物理与技术

贝叶斯个性化剂量约束筛选NSCLC心脏风险Adaptive治疗

Bayesian personalized dose constraints in selecting patients with non-small cell lung cancer for cardiac risk-adaptive treatment.
PubMed 文献 · Radiother Oncol · 2026-09-12

本研究基于160例训练队列和91例验证队列,建立贝叶斯分层NTCP模型预测NSCLC放疗期间hs-cTnT升高风险,按肿瘤位置和年龄分为3个风险亚组。纳入模型不确定性的个性化MHD约束在特异性(0.57-0.68 vs 0.28-0.51)和准确率(0.60-0.69 vs 0.43-0.59)上优于传统点估计约束。

要点

  • 按肿瘤位置和年龄将NSCLC患者分为3个心脏风险亚组。
  • >64岁左肺/纵隔肿瘤患者MHD与hs-cTnT升高风险相关(OR=2.16)。
  • 不确定性整合的个性化MHD约束筛选准确率优于点估计约束。

核心结论

  • 基于贝叶斯分层NTCP模型,建议使用整合不确定性的个性化MHD约束筛选适合心脏风险Adaptive治疗的NSCLC患者。

研究设计与样本

  • 分析已完成前瞻性试验的160例训练队列和进行中试验的91例验证队列。
  • 终点为放疗期间高敏心肌肌钙蛋白T升高>5 ng/L。
  • 采用决策树风险分层建立贝叶斯分层NTCP模型,以MHD为组特异性效应。
  • 通过优化概率截断参数最大化敏感性和特异性以纳入模型不确定性。
  • 在内部验证、同机构外部验证和前瞻性实施测试中比较筛选准确率。

主要发现

  • 按肿瘤位置和年龄将患者分为3个风险亚组。
  • MHD对>64岁左肺/纵隔肿瘤患者影响显著(OR=2.16,95%可信区间=1.07-4.14)。
  • 不确定性整合约束在特异性(0.57-0.68 vs 0.28-0.51)和准确率(0.60-0.69 vs 0.43-0.59)上优于点估计约束。

关键数值与推荐

  • 高风险亚组为>64岁且肿瘤位于左肺/纵隔者,MHD与hs-cTnT升高相关(OR=2.16,95%可信区间=1.07-4.14)。
  • 不确定性整合的个性化MHD约束特异性为0.57-0.68,准确率为0.60-0.69。
  • 点估计约束特异性为0.28-0.51,准确率为0.43-0.59。

临床怎么用

  • 可利用贝叶斯分层NTCP模型对NSCLC患者按肿瘤位置和年龄进行心脏风险分层。
  • 对>64岁左肺/纵隔肿瘤患者,可参考个性化MHD约束筛选心脏风险Adaptive治疗候选者。
  • 优先采用整合模型不确定性的约束以提高筛选特异性和准确率。

局限性

  • 训练队列来自已完成试验,验证队列来自进行中试验,样本来源有限。
  • 终点为放疗期间hs-cTnT升高>5 ng/L,非长期心脏临床事件。
  • 需进一步前瞻性实施验证以确认临床获益。

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: To develop a personalized approach for selecting patients with non-small cell lung cancer (NSCLC) for cardiac risk-adaptive treatment by creating a normal-tissue complication probability (NTCP) model that accounts for heterogeneous radiation dose effects and deriving personalized dose constraints that incorporate model uncertainty. METHODS AND MATERIALS: We analyzed a training cohort of 160 patients from a completed prospective trial and a validation cohort of 91 patients from an ongoing trial. The endpoint was high-sensitivity cardiac troponin T (hs-cTnT) elevation > 5 ng/L during radiotherapy. A Bayesian hierarchical NTCP model based on risk stratification by decision tree was developed to predict the risk of hs-cTnT elevation, treating mean heart dose (MHD) as a group-specific effect. To address model uncertainty in deriving personalized dose constraints, the probability cut-off parameter was optimized to maximize sensitivity and specificity based on posterior distributions. The patient selection accuracy of the uncertainty-incorporated dose constraints was compared against the conventional point-estimate-based ones in internal validation, same-institution external validation, and prospective implementation testing. RESULTS: Patients were stratified into 3 risk subgroups based on tumor location and age. The MHD strongly affected patients aged > 64 years with left/mediastinal tumors (odds ratio = 2.16 [95 % credible interval = 1.07-4.14]). The uncertainty-incorporated dose constraints outperformed point-estimate-based dose constraints in specificity (0.57-0.68 vs 0.28-0.51) and accuracy (0.60-0.69 vs 0.43-0.59) across validations. CONCLUSION: Based on our Bayesian hierarchical NTCP model, we proposed using uncertainty-incorporated personalized MHD constraints to select patients with NSCLC for cardiac risk-adaptive treatment. This framework represents an important step toward personalized radiotherapy to reduce cardiac toxicity.

来源:Radiother Oncol,查看原文。版权归原作者所有。

引用

  1. Chen M, Xu T, Xu T, et al. Bayesian personalized dose constraints in selecting patients with non-small cell lung cancer for cardiac risk-adaptive treatment. Radiother Oncol. 2026. PMID: 42731758. doi:10.1016/j.radonc.2026.111775

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。