Selecting Interpretability Techniques for Healthcare Machine Learning models

TL;DR

This paper reviews and compares eight interpretability techniques for healthcare machine learning models, emphasizing the importance of selecting appropriate methods to enhance decision-making transparency.

Contribution

It provides a framework and overview of eight interpretability algorithms, distinguishing between post-hoc and model-based approaches in healthcare ML.

Findings

Eight interpretability algorithms are summarized and compared.

Framework distinguishes post-hoc and model-based interpretability.

Guidance for selecting suitable interpretability techniques in healthcare.

Abstract

In healthcare there is a pursuit for employing interpretable algorithms to assist healthcare professionals in several decision scenarios. Following the Predictive, Descriptive and Relevant (PDR) framework, the definition of interpretable machine learning as a machine-learning model that explicitly and in a simple frame determines relationships either contained in data or learned by the model that are relevant for its functioning and the categorization of models by post-hoc, acquiring interpretability after training, or model-based, being intrinsically embedded in the algorithm design. We overview a selection of eight algorithms, both post-hoc and model-based, that can be used for such purposes.