DynSHAP: Towards Explainable Dynamic Survival Analysis

• URL: http://arxiv.org/abs/2609.13042v1
• Date: Fri, 11 Sep 2026 16:39:55 GMT
• Title: DynSHAP: Towards Explainable Dynamic Survival Analysis
• Abstract summary: Deep learning models for dynamic survival analysis (DSA) achieve strong predictive performance by incorporating longitudinal patient data.<n>Existing explainability methods cannot handle longitudinal, irregular inputs and functional survival outputs simultaneously.<n>We propose DynSHAP, a SHAP framework suited specifically for dynamic survival analysis.
• Score: 12.866975501183967
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• SurvCF(t): Counterfactual Explanations for Survival Analysis in Predictive Maintenance Multivariate Time Series Data [5.77414732529171]
  We introduce textitSurvCF(t), the first framework for generating counterfactual explanations for survival models operating on time-series data.<n>textitSurvCF(t) identifies minimal, plausible, and temporally consistent changes to an asset's operational history that increase its predicted life time.<n>Our results show that textitSurvCF(t) bridges the gap between survival prediction and prescriptive maintenance, enabling explainable and decision-oriented AI for maintenance strategies.
  arXiv  Detail & Related papers  (2026-07-18T21:06:46Z)
• A Temporal Machine Learning-Based Time-to-Event Model for Predicting ALS Progression and Healthcare Utilization [4.920779064186337]
  Amyotrophic lateral sclerosis (ALS) is a progressive and heterogeneous neurodegenerative disease.<n>We developed a framework that integrates ALS Functional Rating Scale-Revised (ALSFRS-R) trajectories with survival modeling.<n>This framework provides a scalable, interpretable, and clinically actionable approach for linking ALS progression with personalized decision support.
  arXiv  Detail & Related papers  (2026-07-15T16:11:23Z)
• Methodology for Comparing Machine Learning Algorithms for Survival Analysis [55.65997641180011]
  Six machine learning models for survival analysis were evaluated.<n>XGB-AFT achieved the best performance (C-Index = 0.7618; IPCW = 0.7532, followed by GBSA and RSF)
  arXiv  Detail & Related papers  (2025-10-28T14:42:28Z)
• PISA: An AI Pipeline for Interpretable-by-design Survival Analysis Providing Multiple Complexity-Accuracy Trade-off Models [0.9851812512860351]
  Survival analysis is central to clinical research, informing patient prognoses, guiding treatment decisions, and optimising resource allocation.<n>For these models to be relevant in healthcare, predictions must be traceable to patient-specific characteristics.<n>Traditional survival models often fail to capture non-linear interactions, while modern deep learning approaches are limited by poor interpretability.<n>We propose a Pipeline for Interpretable Survival Analysis (PISA) - a pipeline that provides multiple survival analysis models that trade off complexity and performance.
  arXiv  Detail & Related papers  (2025-09-13T18:09:14Z)
• Deep Survival Analysis in Multimodal Medical Data: A Parametric and Probabilistic Approach with Competing Risks [47.19194118883552]
  We introduce a multimodal deep learning framework for survival analysis capable of modeling both single and competing risks scenarios.<n>We propose SAMVAE (Survival Analysis Multimodal Variational Autoencoder), a novel deep learning architecture designed for survival prediction.
  arXiv  Detail & Related papers  (2025-07-10T14:29:48Z)
• Self-Explaining Hypergraph Neural Networks for Diagnosis Prediction [45.89562183034469]
  Existing deep learning diagnosis prediction models with intrinsic interpretability often assign attention weights to every past diagnosis or hospital visit.<n>We introduce SHy, a self-explaining hypergraph neural network model, designed to offer personalized, concise and faithful explanations.<n> SHy captures higher-order disease interactions and extracts distinct temporal phenotypes as personalized explanations.
  arXiv  Detail & Related papers  (2025-02-15T06:33:02Z)
• Gradient-based Explanations for Deep Learning Survival Models [0.716879432974126]
  We propose a framework for gradient-based explanation methods tailored to survival neural networks.<n>We analyze the implications of their theoretical assumptions for time-dependent explanations in the survival setting.<n>We propose effective visualizations incorporating the temporal dimension.
  arXiv  Detail & Related papers  (2025-02-07T14:36:55Z)
• Deep End-to-End Survival Analysis with Temporal Consistency [49.77103348208835]
  We present a novel Survival Analysis algorithm designed to efficiently handle large-scale longitudinal data. A central idea in our method is temporal consistency, a hypothesis that past and future outcomes in the data evolve smoothly over time. Our framework uniquely incorporates temporal consistency into large datasets by providing a stable training signal.
  arXiv  Detail & Related papers  (2024-10-09T11:37:09Z)
• Generative Modeling of Regular and Irregular Time Series Data via Koopman VAEs [50.25683648762602]
  We introduce Koopman VAE, a new generative framework that is based on a novel design for the model prior. Inspired by Koopman theory, we represent the latent conditional prior dynamics using a linear map. KoVAE outperforms state-of-the-art GAN and VAE methods across several challenging synthetic and real-world time series generation benchmarks.
  arXiv  Detail & Related papers  (2023-10-04T07:14:43Z)
• SurvSHAP(t): Time-dependent explanations of machine learning survival models [6.950862982117125]
  We introduce SurvSHAP(t), the first time-dependent explanation that allows for interpreting survival black-box models. Experiments on synthetic and medical data confirm that SurvSHAP(t) can detect variables with a time-dependent effect. We provide an accessible implementation of time-dependent explanations in Python.
  arXiv  Detail & Related papers  (2022-08-23T17:01:14Z)
• Learning Dynamic and Personalized Comorbidity Networks from Event Data using Deep Diffusion Processes [102.02672176520382]
  Comorbid diseases co-occur and progress via complex temporal patterns that vary among individuals. In electronic health records we can observe the different diseases a patient has, but can only infer the temporal relationship between each co-morbid condition. We develop deep diffusion processes to model "dynamic comorbidity networks"
  arXiv  Detail & Related papers  (2020-01-08T15:47:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.