Explainable AI for survival analysis: a median-SHAP approach
Machine Learning
2024-02-02 v1 Methodology
Machine Learning
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.
Cite
@article{arxiv.2402.00072,
title = {Explainable AI for survival analysis: a median-SHAP approach},
author = {Lucile Ter-Minassian and Sahra Ghalebikesabi and Karla Diaz-Ordaz and Chris Holmes},
journal= {arXiv preprint arXiv:2402.00072},
year = {2024}
}
Comments
Accepted to the Interpretable Machine Learning for Healthcare (IMLH) workshop of the ICML 2022 Conference