Metraipolis › archive › dc_8a4596396c99

DynSHAP: Towards Explainable Dynamic Survival Analysis — arXiv:2609.13042

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.13042
License (as archived)
CC0-1.0
Archived
2026-10-16T03:03:46.160Z
SHA-256 of the archived text
939909dc78241168b0593f98af56ef4eea5ed61a8d448b820826ac24cc9bdefc
Stable URL of this page
https://metraipolis.com/documento/dc_8a4596396c99

How to cite

DynSHAP: Towards Explainable Dynamic Survival Analysis — arXiv:2609.13042 — arXiv (en), https://arxiv.org/abs/2609.13042 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8a4596396c99 (Metraipolis archive dc_8a4596396c99, sha256 939909dc78241168b0593f98af56ef4eea5ed61a8d448b820826ac24cc9bdefc)
BibTeX
@misc{dc8a4596396c99,
  title = {DynSHAP: Towards Explainable Dynamic Survival Analysis — arXiv:2609.13042},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.13042},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8a4596396c99; sha256 939909dc78241168b0593f98af56ef4eea5ed61a8d448b820826ac24cc9bdefc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13042. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.13042 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T02:51:27.972Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).