No Cover Image

Conference Paper/Proceeding/Abstract 347 views 106 downloads

RetainEXT: Enhancing Rare Event Detection and Improving Interpretability of Health Records using Temporal Neural Networks

Suraj Ramchand, Gavin Tsang, Duncan Cole, Xianghua Xie Orcid Logo

2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI)

Swansea University Authors: Suraj Ramchand, Gavin Tsang, Xianghua Xie Orcid Logo

Check full text

DOI (Published version): 10.1109/bhi56158.2022.9926906

Abstract

A recurring theme during the pandemic was the shortage of hospital beds. Despite all efforts, the healthcare system still faces 25 % of resource strain felt during the first peak of coronavirus. Digitisation of Electronic Healthcare Records (EHRs) and the pandemic have brought about many successful...

Full description

Published in: 2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI)
ISBN: 978-1-6654-8792-4 978-1-6654-8791-7
ISSN: 2641-3590 2641-3604
Published: IEEE 2022
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa61212
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2022-09-14T09:04:04Z
last_indexed 2023-01-13T19:21:50Z
id cronfa61212
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2023-01-06T16:42:38.0447863</datestamp><bib-version>v2</bib-version><id>61212</id><entry>2022-09-14</entry><title>RetainEXT: Enhancing Rare Event Detection and Improving Interpretability of Health Records using Temporal Neural Networks</title><swanseaauthors><author><sid>c5b30d30add7b8e5dbd9ade90ea3e85d</sid><firstname>Suraj</firstname><surname>Ramchand</surname><name>Suraj Ramchand</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>ca887fecde0f72eaf96f0785f018113f</sid><firstname>Gavin</firstname><surname>Tsang</surname><name>Gavin Tsang</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>b334d40963c7a2f435f06d2c26c74e11</sid><ORCID>0000-0002-2701-8660</ORCID><firstname>Xianghua</firstname><surname>Xie</surname><name>Xianghua Xie</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2022-09-14</date><deptcode>REWI</deptcode><abstract>A recurring theme during the pandemic was the shortage of hospital beds. Despite all efforts, the healthcare system still faces 25 % of resource strain felt during the first peak of coronavirus. Digitisation of Electronic Healthcare Records (EHRs) and the pandemic have brought about many successful applications of Recurrent Neural Networks (RNNs) to predict patients' current and future states. Despite their strong per-formance, it remains a challenge for users to delve into the black box which has heavily influenced researchers to utilise more interpretable techniques such as ID-Convolutional neural networks. Others focus on using more interpretable machine learning techniques but only achieve high performance on a select subset of patients. By collaborating with medical experts and artificial intelligence scientists, our study improves on the REverse Time AttentIoN EX model, a feature and visit level attention network, for increased interpretability and usability of RNNs in predicting COVID-19-related hospitalisations. We achieved 82.40 % area under the receiver operating characteristic curve and showcased effective use of the REverse Time AttentIoN EXTension model and EHRs in understanding how individual medical codes contribute to hospitalisation risk prediction. This study provides a guideline for researchers aiming to design interpretable temporal neural networks using the power of RNNs and data mining techniques.</abstract><type>Conference Paper/Proceeding/Abstract</type><journal>2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI)</journal><volume/><journalNumber/><paginationStart/><paginationEnd/><publisher>IEEE</publisher><placeOfPublication/><isbnPrint>978-1-6654-8792-4</isbnPrint><isbnElectronic>978-1-6654-8791-7</isbnElectronic><issnPrint>2641-3590</issnPrint><issnElectronic>2641-3604</issnElectronic><keywords/><publishedDay>4</publishedDay><publishedMonth>11</publishedMonth><publishedYear>2022</publishedYear><publishedDate>2022-11-04</publishedDate><doi>10.1109/bhi56158.2022.9926906</doi><url/><notes/><college>COLLEGE NANME</college><department>Reaching Wider</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>REWI</DepartmentCode><institution>Swansea University</institution><apcterm/><funders>This work was supported by Amicus Therapeutics UK Operations and the Engineering and Physical Sciences Research Council (EPSRC) centre for doctoral training in enhancing human interactions and collaborations with data and intelligence-driven systems, grant number EP/S021892/1</funders><projectreference/><lastEdited>2023-01-06T16:42:38.0447863</lastEdited><Created>2022-09-14T09:52:41.8938380</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Suraj</firstname><surname>Ramchand</surname><order>1</order></author><author><firstname>Gavin</firstname><surname>Tsang</surname><order>2</order></author><author><firstname>Duncan</firstname><surname>Cole</surname><order>3</order></author><author><firstname>Xianghua</firstname><surname>Xie</surname><orcid>0000-0002-2701-8660</orcid><order>4</order></author></authors><documents><document><filename>61212__25132__0319b234744f4217bcb38ccd5f79822e.pdf</filename><originalFilename>RetainEXT by Suraj Ramchand.pdf</originalFilename><uploaded>2022-09-14T10:01:30.3040470</uploaded><type>Output</type><contentLength>1001378</contentLength><contentType>application/pdf</contentType><version>Accepted Manuscript</version><cronfaStatus>true</cronfaStatus><documentNotes>Released under the terms of a CC-BY license.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2023-01-06T16:42:38.0447863 v2 61212 2022-09-14 RetainEXT: Enhancing Rare Event Detection and Improving Interpretability of Health Records using Temporal Neural Networks c5b30d30add7b8e5dbd9ade90ea3e85d Suraj Ramchand Suraj Ramchand true false ca887fecde0f72eaf96f0785f018113f Gavin Tsang Gavin Tsang true false b334d40963c7a2f435f06d2c26c74e11 0000-0002-2701-8660 Xianghua Xie Xianghua Xie true false 2022-09-14 REWI A recurring theme during the pandemic was the shortage of hospital beds. Despite all efforts, the healthcare system still faces 25 % of resource strain felt during the first peak of coronavirus. Digitisation of Electronic Healthcare Records (EHRs) and the pandemic have brought about many successful applications of Recurrent Neural Networks (RNNs) to predict patients' current and future states. Despite their strong per-formance, it remains a challenge for users to delve into the black box which has heavily influenced researchers to utilise more interpretable techniques such as ID-Convolutional neural networks. Others focus on using more interpretable machine learning techniques but only achieve high performance on a select subset of patients. By collaborating with medical experts and artificial intelligence scientists, our study improves on the REverse Time AttentIoN EX model, a feature and visit level attention network, for increased interpretability and usability of RNNs in predicting COVID-19-related hospitalisations. We achieved 82.40 % area under the receiver operating characteristic curve and showcased effective use of the REverse Time AttentIoN EXTension model and EHRs in understanding how individual medical codes contribute to hospitalisation risk prediction. This study provides a guideline for researchers aiming to design interpretable temporal neural networks using the power of RNNs and data mining techniques. Conference Paper/Proceeding/Abstract 2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI) IEEE 978-1-6654-8792-4 978-1-6654-8791-7 2641-3590 2641-3604 4 11 2022 2022-11-04 10.1109/bhi56158.2022.9926906 COLLEGE NANME Reaching Wider COLLEGE CODE REWI Swansea University This work was supported by Amicus Therapeutics UK Operations and the Engineering and Physical Sciences Research Council (EPSRC) centre for doctoral training in enhancing human interactions and collaborations with data and intelligence-driven systems, grant number EP/S021892/1 2023-01-06T16:42:38.0447863 2022-09-14T09:52:41.8938380 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Suraj Ramchand 1 Gavin Tsang 2 Duncan Cole 3 Xianghua Xie 0000-0002-2701-8660 4 61212__25132__0319b234744f4217bcb38ccd5f79822e.pdf RetainEXT by Suraj Ramchand.pdf 2022-09-14T10:01:30.3040470 Output 1001378 application/pdf Accepted Manuscript true Released under the terms of a CC-BY license. true eng https://creativecommons.org/licenses/by/4.0/
title RetainEXT: Enhancing Rare Event Detection and Improving Interpretability of Health Records using Temporal Neural Networks
spellingShingle RetainEXT: Enhancing Rare Event Detection and Improving Interpretability of Health Records using Temporal Neural Networks
Suraj Ramchand
Gavin Tsang
Xianghua Xie
title_short RetainEXT: Enhancing Rare Event Detection and Improving Interpretability of Health Records using Temporal Neural Networks
title_full RetainEXT: Enhancing Rare Event Detection and Improving Interpretability of Health Records using Temporal Neural Networks
title_fullStr RetainEXT: Enhancing Rare Event Detection and Improving Interpretability of Health Records using Temporal Neural Networks
title_full_unstemmed RetainEXT: Enhancing Rare Event Detection and Improving Interpretability of Health Records using Temporal Neural Networks
title_sort RetainEXT: Enhancing Rare Event Detection and Improving Interpretability of Health Records using Temporal Neural Networks
author_id_str_mv c5b30d30add7b8e5dbd9ade90ea3e85d
ca887fecde0f72eaf96f0785f018113f
b334d40963c7a2f435f06d2c26c74e11
author_id_fullname_str_mv c5b30d30add7b8e5dbd9ade90ea3e85d_***_Suraj Ramchand
ca887fecde0f72eaf96f0785f018113f_***_Gavin Tsang
b334d40963c7a2f435f06d2c26c74e11_***_Xianghua Xie
author Suraj Ramchand
Gavin Tsang
Xianghua Xie
author2 Suraj Ramchand
Gavin Tsang
Duncan Cole
Xianghua Xie
format Conference Paper/Proceeding/Abstract
container_title 2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI)
publishDate 2022
institution Swansea University
isbn 978-1-6654-8792-4
978-1-6654-8791-7
issn 2641-3590
2641-3604
doi_str_mv 10.1109/bhi56158.2022.9926906
publisher IEEE
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
document_store_str 1
active_str 0
description A recurring theme during the pandemic was the shortage of hospital beds. Despite all efforts, the healthcare system still faces 25 % of resource strain felt during the first peak of coronavirus. Digitisation of Electronic Healthcare Records (EHRs) and the pandemic have brought about many successful applications of Recurrent Neural Networks (RNNs) to predict patients' current and future states. Despite their strong per-formance, it remains a challenge for users to delve into the black box which has heavily influenced researchers to utilise more interpretable techniques such as ID-Convolutional neural networks. Others focus on using more interpretable machine learning techniques but only achieve high performance on a select subset of patients. By collaborating with medical experts and artificial intelligence scientists, our study improves on the REverse Time AttentIoN EX model, a feature and visit level attention network, for increased interpretability and usability of RNNs in predicting COVID-19-related hospitalisations. We achieved 82.40 % area under the receiver operating characteristic curve and showcased effective use of the REverse Time AttentIoN EXTension model and EHRs in understanding how individual medical codes contribute to hospitalisation risk prediction. This study provides a guideline for researchers aiming to design interpretable temporal neural networks using the power of RNNs and data mining techniques.
published_date 2022-11-04T04:19:53Z
_version_ 1763754317949435904
score 11.013731

Similar Items