Survival Concept-Based Learning Models

TL;DR

This paper introduces two novel concept-based models, SurvCBM and SurvRCM, that integrate interpretability with survival analysis, effectively handling censored data and improving prediction accuracy.

Contribution

The paper presents the first concept-based survival analysis models that incorporate interpretability and handle censored data using Cox and Beran estimators.

Findings

SurvCBM outperforms SurvRCM and traditional models in experiments.

Models provide interpretable predictions based on human-understandable concepts.

End-to-end training enhances model performance and interpretability.

Abstract

Concept-based learning enhances prediction accuracy and interpretability by leveraging high-level, human-understandable concepts. However, existing CBL frameworks do not address survival analysis tasks, which involve predicting event times in the presence of censored data -- a common scenario in fields like medicine and reliability analysis. To bridge this gap, we propose two novel models: SurvCBM (Survival Concept-based Bottleneck Model) and SurvRCM (Survival Regularized Concept-based Model), which integrate concept-based learning with survival analysis to handle censored event time data. The models employ the Cox proportional hazards model and the Beran estimator. SurvCBM is based on the architecture of the well-known concept bottleneck model, offering interpretable predictions through concept-based explanations. SurvRCM uses concepts as regularization to enhance accuracy. Both models are trained end-to-end and provide interpretable predictions in terms of concepts. Two interpretability approaches are proposed: one leveraging the linear relationship in the Cox model and another using an instance-based explanation framework with the Beran estimator. Numerical experiments demonstrate that SurvCBM outperforms SurvRCM and traditional survival models, underscoring the importance and advantages of incorporating concept information. The code for the proposed algorithms is publicly available.