No Cover Image

Conference Paper/Proceeding/Abstract 111 views 2 downloads

Towards Polynomial Adaptive Local Explanations for Healthcare Classifiers

Jamie Duell Orcid Logo, Xiuyi Fan, Monika Seisenberger Orcid Logo

Lecture Notes in Computer Science, Volume: 13515, Pages: 411 - 420

Swansea University Authors: Xiuyi Fan, Monika Seisenberger Orcid Logo

Abstract

Local explanations aim to provide transparency for individual instances and their associated predictions. The need for local explanations is prominent for high-risk domains such as finance, law and health care. We propose a new model-agnostic framework for local explanations ``Polynomial Adaptive Lo...

Full description

Published in: Lecture Notes in Computer Science
ISBN: 9783031165634 9783031165641
ISSN: 0302-9743 1611-3349
Published: Cham Springer International Publishing 2022
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa60605
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract: Local explanations aim to provide transparency for individual instances and their associated predictions. The need for local explanations is prominent for high-risk domains such as finance, law and health care. We propose a new model-agnostic framework for local explanations ``Polynomial Adaptive Local Explanations (PALE)", to combat the lack of transparency of predictions through adaptive local models. We aim to explore explanations of predictions by assessing the impact of instantaneous rate of change in each feature and the association with the resulting prediction of the local model. PALE optimises a complex black-box model and the local explanation models for each instance, providing two forms of explanations, one provided by a localised derivative of an adapting polynomial, thus emphasising instance specificity, and the latter a core interpretable logistic regression model.
Keywords: Explainable AI, Feature Importance, Electronic health records.
College: Faculty of Science and Engineering
Start Page: 411
End Page: 420