文献速递头颈部肿瘤放疗

基于贝叶斯网络与马尔可夫毯的头颈癌生存风险分层

Clinically Interpretable Survival Risk Stratification in Head and Neck Cancer Using Bayesian Networks and Markov Blankets.
PubMed 文献 · Int J Radiat Oncol Biol Phys · 2025-10-11

本研究利用RADCURE数据集3346例接受根治性放化疗的头颈癌患者,构建贝叶斯网络并提取2年生存的马尔可夫毯,训练逻辑回归模型。模型在测试集上AUC为0.65、C-index为0.78,可显著区分高低风险组,并在HPV阴性、T4及大肿瘤体积亚组中表现良好。

要点

  • 马尔可夫毯包含6个临床特征:ECOG评分、T分期、HPV状态、疾病部位、原发肿瘤体积和治疗方式。
  • 模型测试集AUC 0.65、C-index 0.78,log-rank P < .01,可显著分层生存。
  • HPV阴性、T4及大肿瘤体积亚组中模型区分度良好,支持个体化决策。

核心结论

  • 紧凑的马尔可夫毯衍生贝叶斯网络模型可稳健地对头颈癌生存风险进行分层。
  • 模型结构支持可解释的预后评估,并有助于关键临床亚组的个体化决策。

研究设计与样本

  • 使用RADCURE数据集,共3346例接受根治性放化疗的头颈癌患者。
  • 构建概率贝叶斯网络,提取2年生存的马尔可夫毯,训练逻辑回归模型。
  • 排除不完整病例后,以2007年为截断年进行时间分割,训练集2174例、测试集820例。

主要发现

  • 马尔可夫毯包含6个临床特征:ECOG评分、T分期、HPV状态、疾病部位、原发肿瘤体积和治疗方式。
  • 测试集AUC为0.65,C-index为0.78,显著分层高低风险组(log-rank P < .01)。
  • 模型拟合对数似然比为70.32(P < .01)。
  • HPV阴性亚组AUC=0.69、C-index=0.76;T4亚组AUC=0.69、C-index=0.80;大肿瘤体积亚组AUC=0.67、C-index=0.75,均显示显著Kaplan-Meier分离。
  • 因果分析支持ECOG 0、HPV阳性状态和放化疗对生存的正向影响。

关键数值与推荐

  • 模型性能评估指标包括AUC、C-index和Kaplan-Meier生存分层。
  • 模型拟合使用对数似然比检验评估。
  • 因果推断采用do-calculus对马尔可夫毯变量进行干预分析。

临床怎么用

  • 可利用ECOG评分、T分期、HPV状态、疾病部位、原发肿瘤体积和治疗方式6个特征进行生存风险分层。
  • 模型在HPV阴性、T4及大肿瘤体积亚组中区分度良好,可辅助这些亚组的个体化决策。
  • 模型结构可解释,支持临床预后沟通和风险分层管理。

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 identify a clinically interpretable subset of survival-relevant features in head and neck cancer using Bayesian network (BN) and evaluate its prognostic and causal utility. METHODS AND MATERIALS: We used the RADCURE data set, consisting of 3346 patients with head and neck cancer treated with definitive (chemo)radiation therapy. A probabilistic BN was constructed to model dependencies among clinical, anatomic, and treatment variables. The Markov blanket (MB) of 2-year survival (SVy2) was extracted and used to train a logistic regression model. After excluding incomplete cases, a temporal split yielded a train/test (2174/820) data set using 2007 as the cutoff year. Model performance was assessed using the area under the receiver operating characteristic (ROC) curve (AUC), concordance index (C-index), and Kaplan-Meier survival stratification. Model fit was further evaluated using a log-likelihood ratio test. Causal inference was performed using do-calculus interventions on MB variables. RESULTS: The MB of SVy2 included 6 clinically relevant features: Eastern Cooperative Oncology Group performance status, T stage, human papillomavirus (HPV) status, disease site, the primary gross tumor volume, and treatment modality. The model achieved an AUC of 0.65 and C-index of 0.78 on the test data set, significantly stratifying patients into high- and low-risk groups (log-rank P < .01). Model fit was further supported by a log-likelihood ratio of 70.32 (P < .01). Subgroup analyses revealed strong performance in HPV-negative (AUC = 0.69; C-index = 0.76), T4 (AUC = 0.69; C-index = 0.80), and large-gross tumor volume (AUC = 0.67; C-index = 0.75) cohorts, each showing significant Kaplan-Meier separation. Causal analysis further supported the positive survival impact of Eastern Cooperative Oncology Group 0, HPV-positive status, and chemoradiation. CONCLUSIONS: A compact, MB-derived BN model can robustly stratify survival risk in head and neck cancer. The model's structure enables explainable prognostication and supports individualized decision-making across key clinical subgroups.

来源:Int J Radiat Oncol Biol Phys,查看原文。版权归原作者所有。

引用

  1. Shah KD, Chamseddine I, Yuan X, et al. Clinically Interpretable Survival Risk Stratification in Head and Neck Cancer Using Bayesian Networks and Markov Blankets. Int J Radiat Oncol Biol Phys. 2025. PMID: 41083026. doi:10.1016/j.ijrobp.2025.09.063

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。