为生存模型设计梯度解释方法，揭示特征随时间变化的影响。
Gradient-based Explanations for Deep Learning Survival Models
- 基于梯度构建适用于生存模型的解释框架，支持时变分析。
- 提出GradSHAP(t)方法，在速度与准确率上优于现有同类方法。
- 可应用于多模态医疗数据，可视化特征随时间的作用动态。
深度学习生存模型在时间-事件预测中表现优于传统方法，尤其在个性化医疗领域，但其“黑箱”特性限制了广泛应用。本文提出一种专为生存神经网络设计的梯度解释框架，突破了仅适用于回归与分类任务的局限。我们分析了理论假设对时变解释的影响，并提出融合时间维度的有效可视化方法。合成数据实验表明，梯度方法能准确捕捉局部与全局特征效应，包括时间依赖性。我们引入GradSHAP(t)，作为SurvSHAP(t)的梯度版本，在计算效率与准确性之间取得更优平衡。最后，我们在具有多模态输入的医学数据上应用该方法，揭示了相关表格特征、视觉模式及其随时间演变的动态规律。
原文摘要 · Abstract (English)
Deep learning survival models often outperform classical methods in time-to-event predictions, particularly in personalized medicine, but their "black box" nature hinders broader adoption. We propose a framework for gradient-based explanation methods tailored to survival neural networks, extending their use beyond regression and classification. We analyze the implications of their theoretical assumptions for time-dependent explanations in the survival setting and propose effective visualizations incorporating the temporal dimension. Experiments on synthetic data show that gradient-based methods capture the magnitude and direction of local and global feature effects, including time dependencies. We introduce GradSHAP(t), a gradient-based counterpart to SurvSHAP(t), which outperforms SurvSHAP(t) and SurvLIME in a computational speed vs. accuracy trade-off. Finally, we apply these methods to medical data with multi-modal inputs, revealing relevant tabular features and visual patterns, as well as their temporal dynamics.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。