发表机构
Cancer Research UK Scotland Centre; Institute of Genetics and Cancer; University of Edinburgh; University of Augsburg（英国癌症研究苏格兰中心; 遗传与癌症研究所; 爱丁堡大学; 奥格斯堡大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对竞争风险生存分析缺乏基准测试框架的问题，开发了开源可复现可扩展的竞争风险模型基准测试框架，还扩展了SHAP用于该场景的可解释性，相关代码已公开。
AI 中文摘要
针对存在竞争风险的生存分析，已有大量统计与机器学习方法被提出，其中某一事件（如癌症死亡）的发生会排除其他事件（如心血管疾病死亡）的发生。尽管方法有所进展，但缺乏全面、可复现且可扩展的基准测试框架，限制了这些方法的系统评估与应用。我们开发了一个开源的竞争风险模型基准测试框架，可在多个数据集上从校准、判别性、整体预测误差及临床效用等不同性能维度对模型进行系统比较；还引入了针对竞争风险的SHAP扩展，实现了协变量随时间贡献的模型不可知可解释性。所有代码已通过GitHub公开获取。
英文摘要
A wide range of statistical and machine learning methods have been proposed for survival analysis with competing risks, where the occurrence of one event (i.e., cancer death) precludes the occurrence of other events (i.e., cardiovascular disease death). Despite these methodological advances, their systematic evaluation and adoption are limited by the lack of comprehensive, reproducible and extensible benchmarking frameworks. We developed an open-source benchmarking framework for competing risks models that enables their systematic comparison across multiple datasets under different aspects of performance; calibration, discrimination, overall prediction error and clinical utility. We additionally introduce an extension of SHAP for competing risks, allowing model-agnostic interpretability of covariates contributions over time. All our code is publicly available via GitHub:https://github.com/BBolosSierra/CompRisksBenchmark
Comments23 pages main text (7 figures), 31 pages supplementary information
