Explainable AI for survival analysis: a median-SHAP approach
This work addresses the need for tailored Explainable AI methods in clinical practice, though it is incremental as it modifies an existing technique for a specific domain.
The authors tackled the problem of misleading interpretations from Shapley values in survival analysis by introducing median-SHAP, a method that uses a median anchor point to explain black-box models predicting individual survival times, showing it improves interpretability over the conventional mean-based approach.
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.