贝叶斯个性化剂量约束筛选NSCLC心脏风险Adaptive治疗
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.
引用
- 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。