DynSHAP：面向可解释动态生存分析的 SHAP 框架
DynSHAP: Towards Explainable Dynamic Survival Analysis
AI 导读
研究者提出 DynSHAP，一个专为动态生存分析（DSA）设计的 SHAP 可解释性框架，将时间—特征对作为 Shapley 博弈中的玩家，扩展了现有的边际 SHAP 估计方法。
正文 · 原文
Abstract:Deep learning models for dynamic survival analysis (DSA) achieve strong predictive performance by incorporating longitudinal patient data, but their black box nature limits clinical trust and adoption. Existing explainability methods cannot handle longitudinal, irregular inputs and functional survival outputs simultaneously, which limits their usability in DSA. We propose DynSHAP, a SHAP framework suited specifically for dynamic survival analysis. It extends common marginal SHAP estimators to this setting by treating time--feature pairs as players in the Shapley game. We further introduce Temporal DynSHAP, which learns linear dependencies in features over time and uses conditional sampling to address them in explanations. When applied to synthetic data with known ground-truth attributions, Temporal DynSHAP recovers temporally dependent features more accurately than marginal estimators for a given state-of-the-art model. Applied to two real-world clinical datasets and two DSA architectures, DynSHAP produces attributions faithful to model learning, allowing medical experts to see which patient information drove the prediction and when.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2609.13042 [cs.LG] |
| (or arXiv:2609.13042v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2609.13042 arXiv-issued DOI via DataCite |
Submission history
From: Nastasya Anokhina [view email]
[v1]
Fri, 11 Sep 2026 16:39:55 UTC (2,943 KB)
[v2]
Thu, 5 Nov 2026 12:11:57 UTC (2,944 KB)
来源：arXiv cs.AI · arxiv.org