文献类型：期刊文献

中文题名：基于改进DeepSurv模型的肺癌生存分析及其影响因素

英文题名：Improved DeepSurv model for survival analysis in lung cancer and exploration of influencing factors

作者：赵祺旸[1];赵旭[1];张颖[1];邝曼曼[1];郗群[1,2]

第一作者：赵祺旸

机构：[1]甘肃中医药大学医学信息工程学院,甘肃兰州730000;[2]兰州大学第二医院信息中心,甘肃兰州730000

第一机构：甘肃中医药大学信息工程学院（教育技术中心）

年份：2025

卷号：42

期号：6

起止页码：832

中文期刊名：中国医学物理学杂志

外文期刊名：Chinese Journal of Medical Physics

基金：甘肃省自然科学基金(20CX9JA145)。

语种：中文

中文关键词：肺癌;生存分析;深度学习;改进DeepSurv模型;影响因素

外文关键词：lung cancer;survival analysis;deep learning;improved DeepSurv model;influencing factor

摘要：目的:探究改进后的DeepSurv模型在预测肺癌患者生存期中的表现,并分析影响肺癌预后的关键因素。方法:基于SEER数据库中2018至2021年的肺癌患者数据,通过引入自注意力机制、残差网络、LIME方法以及熵正则化项对DeepSurv模型进行改进,以提升模型的预测性能和可解释性。利用C-index和Brier分数对模型性能进行评估,并应用改进后的模型分析各特征对肺癌预后的影响。结果:改进后的DeepSurv模型的C-index为0.852,Brier分数为0.139。特征重要性分析显示年龄是影响肺癌患者生存周期的最重要因素。结论:改进后的DeepSurv模型在性能上显著优于Cox比例风险模型和原始DeepSurv模型,具有更高的准确性、鲁棒性和可解释性,为个性化医疗和生存分析领域提供新的模型优化思路。
Objective To evaluate the performance of an improved DeepSurv model for survival analysis in lung cancer patients,and investigate key factors affecting the prognosis of lung cancer.Methods The lung cancer data from the SEER database(2018-2021)was used in the study,and the DeepSurv model was optimized by incorporating a self-attention mechanism,a residual network,a LIME module and an entropy regularization term to enhance prediction accuracy and interpretability.Model performance was assessed using C-index and Brier score,and the improved model was utilized to evaluate the effects of various features on the prognosis of lung cancer.Results The improved DeepSurv model achieved a C-index of 0.852 and a Brier score of 0.139.Feature importance analysis identified age as the primary determinant of the survival of lung cancer patients.Conclusion The improved DeepSurv model outperforms both the Cox proportional hazards model and the original DeepSurv model in terms of accuracy,robustness and interpretability,offering a novel methodology for personalized medicine and survival analysis.