Luo Tianchen, Yan Meng, Zhou Meng, Dekker Andre, Appelt Ane L, Ji Yongling, Zhu Ji, de Ruysscher Dirk, Wee Leonard, Zhao Lujun, Zhang Zhen
Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Hangzhou, Zhejiang, 310022, China.
Institute of System Science, National University of Singapore, Singapore, 119260, Singapore.
Radiol Med. 2025 Jan;130(1):96-109. doi: 10.1007/s11547-024-01919-3. Epub 2024 Nov 14.
Accurate prognostication of overall survival (OS) for non-small cell lung cancer (NSCLC) patients receiving definitive radiotherapy (RT) is crucial for developing personalized treatment strategies. This study aims to construct an interpretable prognostic model that combines radiomic features extracted from normal lung and from primary tumor with clinical parameters. Our model aimed to clarify the complex, nonlinear interactions between these variables and enhance prognostic accuracy.
We included 661 stage III NSCLC patients from three multi-national datasets: a training set (N = 349), test-set-1 (N = 229), and test-set-2 (N = 83), all undergoing definitive RT. A total of 104 distinct radiomic features were separately extracted from the regions of interest in the lung and the tumor. We developed four predictive models using eXtreme gradient boosting and selected the top 10 features based on the Shapley additive explanations (SHAP) values. These models were the tumor radiomic model (Model-T), lung radiomic model (Model-L), a combined radiomic model (Model-LT), and an integrated model incorporating clinical parameters (Model-LTC). Model performance was evaluated through Harrell's concordance index, Kaplan-Meier survival curves, time-dependent area under the receiver operating characteristic curve (AUC), calibration curves, and decision curve analysis. Interpretability was assessed using the SHAP framework.
Model-LTC exhibited superior performance, with notable predictive accuracy (C-index: training set, 0.87; test-set-2, 0.76) and time-dependent AUC above 0.75. Complex nonlinear relationships and interactions were evident among the model's variables.
The integration of radiomic and clinical factors within an interpretable framework significantly improved OS prediction. The SHAP analysis provided insightful interpretability, enhancing the model's clinical applicability and potential for aiding personalized treatment decisions.
准确预测接受根治性放疗（RT）的非小细胞肺癌（NSCLC）患者的总生存期（OS）对于制定个性化治疗策略至关重要。本研究旨在构建一个可解释的预后模型，该模型将从正常肺组织和原发性肿瘤中提取的放射组学特征与临床参数相结合。我们的模型旨在阐明这些变量之间复杂的非线性相互作用，并提高预后准确性。
我们纳入了来自三个跨国数据集的661例III期NSCLC患者：一个训练集（N = 349）、测试集1（N = 229）和测试集2（N = 83），所有患者均接受根治性放疗。总共从肺和肿瘤的感兴趣区域分别提取了104个不同的放射组学特征。我们使用极端梯度提升开发了四个预测模型，并根据Shapley加性解释（SHAP）值选择了前10个特征。这些模型分别是肿瘤放射组学模型（模型-T）、肺放射组学模型（模型-L）、联合放射组学模型（模型-LT）以及纳入临床参数的综合模型（模型-LTC）。通过Harrell一致性指数、Kaplan-Meier生存曲线、接受者操作特征曲线（AUC）随时间变化的面积、校准曲线和决策曲线分析来评估模型性能。使用SHAP框架评估可解释性。
模型-LTC表现出卓越的性能，具有显著的预测准确性（C指数：训练集为0.87；测试集2为0.76），且随时间变化的AUC高于0.75。模型变量之间存在明显的复杂非线性关系和相互作用。
在一个可解释的框架内整合放射组学和临床因素可显著改善OS预测。SHAP分析提供了有洞察力的可解释性，增强了模型的临床适用性以及辅助个性化治疗决策的潜力。
