No Cover Image

Conference Paper/Proceeding/Abstract 138 views 87 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!
first_indexed 2021-08-26T11:50:06Z
last_indexed 2021-12-15T04:26:41Z
id cronfa57694
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2021-12-14T16:22:39.4013347</datestamp><bib-version>v2</bib-version><id>57694</id><entry>2021-08-26</entry><title>A Comparison of Explanations Given by Explainable Artificial Intelligence Methods on Analysing Electronic Health Records</title><swanseaauthors><author><sid>a88a07c43b3e80f27cb96897d1bc2534</sid><firstname>Xiuyi</firstname><surname>Fan</surname><name>Xiuyi Fan</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>1ba0dad382dfe18348ec32fc65f3f3de</sid><ORCID>0000-0002-6038-3782</ORCID><firstname>Gert</firstname><surname>Aarts</surname><name>Gert Aarts</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2021-08-26</date><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.</abstract><type>Conference Paper/Proceeding/Abstract</type><journal>2021 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI)</journal><volume/><journalNumber/><paginationStart/><paginationEnd/><publisher>IEEE</publisher><placeOfPublication/><isbnPrint>978-1-6654-4770-6</isbnPrint><isbnElectronic>978-1-6654-0358-0</isbnElectronic><issnPrint>2641-3590</issnPrint><issnElectronic>2641-3604</issnElectronic><keywords/><publishedDay>10</publishedDay><publishedMonth>8</publishedMonth><publishedYear>2021</publishedYear><publishedDate>2021-08-10</publishedDate><doi>10.1109/bhi50953.2021.9508618</doi><url/><notes/><college>COLLEGE NANME</college><CollegeCode>COLLEGE CODE</CollegeCode><institution>Swansea University</institution><apcterm/><lastEdited>2021-12-14T16:22:39.4013347</lastEdited><Created>2021-08-26T12:44:54.2934143</Created><path><level id="1">College of Science</level><level id="2">Computer Science</level></path><authors><author><firstname>Jamie</firstname><surname>Duell</surname><order>1</order></author><author><firstname>Xiuyi</firstname><surname>Fan</surname><order>2</order></author><author><firstname>Bruce</firstname><surname>Burnett</surname><order>3</order></author><author><firstname>Gert</firstname><surname>Aarts</surname><orcid>0000-0002-6038-3782</orcid><order>4</order></author><author><firstname>Shang-Ming</firstname><surname>Zhou</surname><order>5</order></author></authors><documents><document><filename>57694__20704__d835cb39a4224b93a7e483053b31ce9e.pdf</filename><originalFilename>FINEDT_BHI___A_Comparison_of_Explanations_Given_by_XAI___Analysing_EHR_Conference_Paper (2).pdf</originalFilename><uploaded>2021-08-26T13:27:17.9855432</uploaded><type>Output</type><contentLength>330928</contentLength><contentType>application/pdf</contentType><version>Accepted Manuscript</version><cronfaStatus>true</cronfaStatus><copyrightCorrect>true</copyrightCorrect><language>eng</language></document></documents><OutputDurs/></rfc1807>
spelling 2021-12-14T16:22:39.4013347 v2 57694 2021-08-26 A Comparison of Explanations Given by Explainable Artificial Intelligence Methods on Analysing Electronic Health Records a88a07c43b3e80f27cb96897d1bc2534 Xiuyi Fan Xiuyi Fan true false 1ba0dad382dfe18348ec32fc65f3f3de 0000-0002-6038-3782 Gert Aarts Gert Aarts true false 2021-08-26 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. Conference Paper/Proceeding/Abstract 2021 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI) IEEE 978-1-6654-4770-6 978-1-6654-0358-0 2641-3590 2641-3604 10 8 2021 2021-08-10 10.1109/bhi50953.2021.9508618 COLLEGE NANME COLLEGE CODE Swansea University 2021-12-14T16:22:39.4013347 2021-08-26T12:44:54.2934143 College of Science Computer Science Jamie Duell 1 Xiuyi Fan 2 Bruce Burnett 3 Gert Aarts 0000-0002-6038-3782 4 Shang-Ming Zhou 5 57694__20704__d835cb39a4224b93a7e483053b31ce9e.pdf FINEDT_BHI___A_Comparison_of_Explanations_Given_by_XAI___Analysing_EHR_Conference_Paper (2).pdf 2021-08-26T13:27:17.9855432 Output 330928 application/pdf Accepted Manuscript true true eng
title A Comparison of Explanations Given by Explainable Artificial Intelligence Methods on Analysing Electronic Health Records
spellingShingle A Comparison of Explanations Given by Explainable Artificial Intelligence Methods on Analysing Electronic Health Records
Xiuyi Fan
Gert Aarts
title_short A Comparison of Explanations Given by Explainable Artificial Intelligence Methods on Analysing Electronic Health Records
title_full A Comparison of Explanations Given by Explainable Artificial Intelligence Methods on Analysing Electronic Health Records
title_fullStr A Comparison of Explanations Given by Explainable Artificial Intelligence Methods on Analysing Electronic Health Records
title_full_unstemmed A Comparison of Explanations Given by Explainable Artificial Intelligence Methods on Analysing Electronic Health Records
title_sort A Comparison of Explanations Given by Explainable Artificial Intelligence Methods on Analysing Electronic Health Records
author_id_str_mv a88a07c43b3e80f27cb96897d1bc2534
1ba0dad382dfe18348ec32fc65f3f3de
author_id_fullname_str_mv a88a07c43b3e80f27cb96897d1bc2534_***_Xiuyi Fan
1ba0dad382dfe18348ec32fc65f3f3de_***_Gert Aarts
author Xiuyi Fan
Gert Aarts
author2 Jamie Duell
Xiuyi Fan
Bruce Burnett
Gert Aarts
Shang-Ming Zhou
format Conference Paper/Proceeding/Abstract
container_title 2021 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI)
publishDate 2021
institution Swansea University
isbn 978-1-6654-4770-6
978-1-6654-0358-0
issn 2641-3590
2641-3604
doi_str_mv 10.1109/bhi50953.2021.9508618
publisher IEEE
college_str College of Science
hierarchytype
hierarchy_top_id collegeofscience
hierarchy_top_title College of Science
hierarchy_parent_id collegeofscience
hierarchy_parent_title College of Science
department_str Computer Science{{{_:::_}}}College of Science{{{_:::_}}}Computer Science
document_store_str 1
active_str 0
description 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.
published_date 2021-08-10T04:31:20Z
_version_ 1733133263351840768
score 10.871248