No Cover Image

Conference Paper/Proceeding/Abstract 604 views 735 downloads

A Comparison of Explanations Given by Explainable Artificial Intelligence Methods on Analysing Electronic Health Records

Jamie Duell, Xiuyi Fan, Bruce Burnett, Gert Aarts Orcid Logo, Shang-Ming Zhou

2021 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI)

Swansea University Authors: Xiuyi Fan, Gert Aarts Orcid Logo

Abstract

eXplainable Artificial Intelligence (XAI) aims to provide intelligible explanations to users. XAI algorithms such as SHAP, LIME and Scoped Rules compute feature importance for machine learning predictions. Although XAI has attracted much research attention, applying XAI techniques in healthcare to i...

Full description

Published in: 2021 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI)
ISBN: 978-1-6654-4770-6 978-1-6654-0358-0
ISSN: 2641-3590 2641-3604
Published: IEEE 2021
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa57694
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract: eXplainable Artificial Intelligence (XAI) aims to provide intelligible explanations to users. XAI algorithms such as SHAP, LIME and Scoped Rules compute feature importance for machine learning predictions. Although XAI has attracted much research attention, applying XAI techniques in healthcare to inform clinical decision making is challenging. In this paper, we provide a comparison of explanations given by XAI methods as a tertiary extension in analysing complex Electronic Health Records (EHRs). With a large-scale EHR dataset, we compare features of EHRs in terms of their prediction importance estimated by XAI models. Our experimental results show that the studied XAI methods circumstantially generate different top features; their aberrations in shared feature importance merit further exploration from domain-experts to evaluate human trust towards XAI.
College: Faculty of Science and Engineering