The Cox Proportional Hazards (CPH) model has long been the preferred survival model for its explainability. However, to increase its predictive power beyond its linear log-risk, it was extended to utilize deep neural networks sacrificing its explainability. In this work, we explore the potential of self-explaining neural networks (SENN) for survival analysis. we propose a new locally explainable Cox proportional hazards model, named CoxSE, by estimating a locally-linear log-hazard function using the SENN. We also propose a modification to the Neural additive (NAM) models hybrid with SENN, named CoxSENAM, which enables the control of the stability and consistency of the generated explanations. Several experiments using synthetic and real datasets have been performed comparing with a NAM-based model, DeepSurv model explained with SHAP, and a linear CPH model. The results show that, unlike the NAM-based model, the SENN-based model can provide more stable and consistent explanations while maintaining the same expressiveness power of the black-box model. The results also show that, due to their structural design, NAM-based models demonstrated better robustness to non-informative features. Among these models, the hybrid model exhibited the best robustness.

翻译：Cox比例风险（CPH）模型因其可解释性长期以来一直是生存分析的首选模型。然而，为了提升其超越线性对数风险的预测能力，该模型被扩展为利用深度神经网络，却牺牲了可解释性。本研究探索了自解释神经网络（SENN）在生存分析中的应用潜力。我们提出了一种新的局部可解释Cox比例风险模型，命名为CoxSE，其通过使用SENN估计局部线性对数风险函数来实现。我们还提出了一种与SENN混合的神经可加模型（NAM）的改进版本，命名为CoxSENAM，该模型能够控制生成解释的稳定性与一致性。我们使用合成数据集和真实数据集进行了多项实验，并与基于NAM的模型、使用SHAP解释的DeepSurv模型以及线性CPH模型进行了比较。结果表明，与基于NAM的模型不同，基于SENN的模型能够在保持与黑盒模型相同表达能力的同时，提供更稳定且一致的解释。结果还显示，由于其结构设计，基于NAM的模型对非信息特征表现出更好的鲁棒性。在这些模型中，混合模型展现了最佳的鲁棒性。