Explainable AI for survival analysis: a median-SHAP approach

TL;DR

This paper introduces median-SHAP, a novel explainable AI method tailored for survival analysis in medical contexts, addressing limitations of mean-based explanations and improving interpretability of survival models.

Contribution

The paper proposes median-SHAP, a new approach for explaining survival models that overcomes biases of mean-based explanations and enhances interpretability.

Findings

Median-SHAP provides more accurate explanations for survival models.

Mean anchor points can lead to misleading interpretations.

Median-SHAP improves model interpretability in clinical survival analysis.

Abstract

With the adoption of machine learning into routine clinical practice comes the need for Explainable AI methods tailored to medical applications. Shapley values have sparked wide interest for locally explaining models. Here, we demonstrate their interpretation strongly depends on both the summary statistic and the estimator for it, which in turn define what we identify as an 'anchor point'. We show that the convention of using a mean anchor point may generate misleading interpretations for survival analysis and introduce median-SHAP, a method for explaining black-box models predicting individual survival times.