No Cover Image

Conference Paper/Proceeding/Abstract 135 views

Explainable Machine Learning: Predicting Clinical Outcomes in Welsh Emergency Departments

Meg Morgan, Alma Rahat Orcid Logo, Gareth Jenkins, Jiaxiang Zhang Orcid Logo

Lecture Notes in Computer Science, Volume: 14976, Pages: 290 - 301

Swansea University Authors: Meg Morgan, Alma Rahat Orcid Logo, Jiaxiang Zhang Orcid Logo

Full text not available from this repository: check for access using links below.

Check full text

DOI (Published version): 10.1007/978-3-031-67285-9_21

Abstract

The UK NHS emergency departments (EDs) are the front-line for patient care, with a wide range of patient presentations but limited resources. Using over 1.5 million ED data entries collected during 2015–2023 from a health board in Wales, we explored the application of machine learning models in pred...

Full description

Published in: Lecture Notes in Computer Science
ISBN: 9783031672842 9783031672859
ISSN: 0302-9743 1611-3349
Published: Cham Springer Nature Switzerland 2024
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa67432
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2024-08-19T09:21:51Z
last_indexed 2024-08-19T09:21:51Z
id cronfa67432
recordtype SURis
fullrecord <?xml version="1.0" encoding="utf-8"?><rfc1807 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema"><bib-version>v2</bib-version><id>67432</id><entry>2024-08-19</entry><title>Explainable Machine Learning: Predicting Clinical Outcomes in Welsh Emergency Departments</title><swanseaauthors><author><sid>219f952a4ddde6fd4c2e8a337935544f</sid><firstname>Meg</firstname><surname>Morgan</surname><name>Meg Morgan</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>6206f027aca1e3a5ff6b8cd224248bc2</sid><ORCID>0000-0002-5023-1371</ORCID><firstname>Alma</firstname><surname>Rahat</surname><name>Alma Rahat</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>555e06e0ed9a87608f2d035b3bde3a87</sid><ORCID>0000-0002-4758-0394</ORCID><firstname>Jiaxiang</firstname><surname>Zhang</surname><name>Jiaxiang Zhang</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2024-08-19</date><abstract>The UK NHS emergency departments (EDs) are the front-line for patient care, with a wide range of patient presentations but limited resources. Using over 1.5 million ED data entries collected during 2015–2023 from a health board in Wales, we explored the application of machine learning models in predicting clinical outcomes. The features in the models included age, sex, incident type, the reason for attendance, method of arrival, and the County of the ED. First, five supervised learning models were trained and evaluated on data collected before the 3rd quarter of 2019, and the Random Forest classifier outperformed other models with a weighted F1 score of 0.78. The same classifier yielded similar performance on subsequent data collected during 2019–2023. We then evaluated the stability of the classification performance by conducting cross-classification, using quarterly data before, during and after the COVID-19 pandemic (2019–2023). Predictive classification from models trained with historical data is stable during this period. Furthermore, we examined the feature importance (quantified by the mean decrease impurity score) of the fitted model. As expected, incident type (major vs minor) is the most important feature. Interestingly, the importance of age in predicting clinical outcomes varies substantially before and after the 4th quarter of 2019. Together, these results demonstrate the capacity of machine learning and its explainability in predicting ED clinical outcomes from simple features.</abstract><type>Conference Paper/Proceeding/Abstract</type><journal>Lecture Notes in Computer Science</journal><volume>14976</volume><journalNumber/><paginationStart>290</paginationStart><paginationEnd>301</paginationEnd><publisher>Springer Nature Switzerland</publisher><placeOfPublication>Cham</placeOfPublication><isbnPrint>9783031672842</isbnPrint><isbnElectronic>9783031672859</isbnElectronic><issnPrint>0302-9743</issnPrint><issnElectronic>1611-3349</issnElectronic><keywords>Machine learning; Explainable data mining; Emergency departments; Clinical outcomes</keywords><publishedDay>15</publishedDay><publishedMonth>8</publishedMonth><publishedYear>2024</publishedYear><publishedDate>2024-08-15</publishedDate><doi>10.1007/978-3-031-67285-9_21</doi><url/><notes/><college>COLLEGE NANME</college><CollegeCode>COLLEGE CODE</CollegeCode><institution>Swansea University</institution><apcterm/><funders/><projectreference/><lastEdited>2024-10-03T12:56:52.3146380</lastEdited><Created>2024-08-19T10:20:05.3699982</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>Meg</firstname><surname>Morgan</surname><order>1</order></author><author><firstname>Alma</firstname><surname>Rahat</surname><orcid>0000-0002-5023-1371</orcid><order>2</order></author><author><firstname>Gareth</firstname><surname>Jenkins</surname><order>3</order></author><author><firstname>Jiaxiang</firstname><surname>Zhang</surname><orcid>0000-0002-4758-0394</orcid><order>4</order></author></authors><documents/><OutputDurs/></rfc1807>
spelling v2 67432 2024-08-19 Explainable Machine Learning: Predicting Clinical Outcomes in Welsh Emergency Departments 219f952a4ddde6fd4c2e8a337935544f Meg Morgan Meg Morgan true false 6206f027aca1e3a5ff6b8cd224248bc2 0000-0002-5023-1371 Alma Rahat Alma Rahat true false 555e06e0ed9a87608f2d035b3bde3a87 0000-0002-4758-0394 Jiaxiang Zhang Jiaxiang Zhang true false 2024-08-19 The UK NHS emergency departments (EDs) are the front-line for patient care, with a wide range of patient presentations but limited resources. Using over 1.5 million ED data entries collected during 2015–2023 from a health board in Wales, we explored the application of machine learning models in predicting clinical outcomes. The features in the models included age, sex, incident type, the reason for attendance, method of arrival, and the County of the ED. First, five supervised learning models were trained and evaluated on data collected before the 3rd quarter of 2019, and the Random Forest classifier outperformed other models with a weighted F1 score of 0.78. The same classifier yielded similar performance on subsequent data collected during 2019–2023. We then evaluated the stability of the classification performance by conducting cross-classification, using quarterly data before, during and after the COVID-19 pandemic (2019–2023). Predictive classification from models trained with historical data is stable during this period. Furthermore, we examined the feature importance (quantified by the mean decrease impurity score) of the fitted model. As expected, incident type (major vs minor) is the most important feature. Interestingly, the importance of age in predicting clinical outcomes varies substantially before and after the 4th quarter of 2019. Together, these results demonstrate the capacity of machine learning and its explainability in predicting ED clinical outcomes from simple features. Conference Paper/Proceeding/Abstract Lecture Notes in Computer Science 14976 290 301 Springer Nature Switzerland Cham 9783031672842 9783031672859 0302-9743 1611-3349 Machine learning; Explainable data mining; Emergency departments; Clinical outcomes 15 8 2024 2024-08-15 10.1007/978-3-031-67285-9_21 COLLEGE NANME COLLEGE CODE Swansea University 2024-10-03T12:56:52.3146380 2024-08-19T10:20:05.3699982 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Meg Morgan 1 Alma Rahat 0000-0002-5023-1371 2 Gareth Jenkins 3 Jiaxiang Zhang 0000-0002-4758-0394 4
title Explainable Machine Learning: Predicting Clinical Outcomes in Welsh Emergency Departments
spellingShingle Explainable Machine Learning: Predicting Clinical Outcomes in Welsh Emergency Departments
Meg Morgan
Alma Rahat
Jiaxiang Zhang
title_short Explainable Machine Learning: Predicting Clinical Outcomes in Welsh Emergency Departments
title_full Explainable Machine Learning: Predicting Clinical Outcomes in Welsh Emergency Departments
title_fullStr Explainable Machine Learning: Predicting Clinical Outcomes in Welsh Emergency Departments
title_full_unstemmed Explainable Machine Learning: Predicting Clinical Outcomes in Welsh Emergency Departments
title_sort Explainable Machine Learning: Predicting Clinical Outcomes in Welsh Emergency Departments
author_id_str_mv 219f952a4ddde6fd4c2e8a337935544f
6206f027aca1e3a5ff6b8cd224248bc2
555e06e0ed9a87608f2d035b3bde3a87
author_id_fullname_str_mv 219f952a4ddde6fd4c2e8a337935544f_***_Meg Morgan
6206f027aca1e3a5ff6b8cd224248bc2_***_Alma Rahat
555e06e0ed9a87608f2d035b3bde3a87_***_Jiaxiang Zhang
author Meg Morgan
Alma Rahat
Jiaxiang Zhang
author2 Meg Morgan
Alma Rahat
Gareth Jenkins
Jiaxiang Zhang
format Conference Paper/Proceeding/Abstract
container_title Lecture Notes in Computer Science
container_volume 14976
container_start_page 290
publishDate 2024
institution Swansea University
isbn 9783031672842
9783031672859
issn 0302-9743
1611-3349
doi_str_mv 10.1007/978-3-031-67285-9_21
publisher Springer Nature Switzerland
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 0
active_str 0
description The UK NHS emergency departments (EDs) are the front-line for patient care, with a wide range of patient presentations but limited resources. Using over 1.5 million ED data entries collected during 2015–2023 from a health board in Wales, we explored the application of machine learning models in predicting clinical outcomes. The features in the models included age, sex, incident type, the reason for attendance, method of arrival, and the County of the ED. First, five supervised learning models were trained and evaluated on data collected before the 3rd quarter of 2019, and the Random Forest classifier outperformed other models with a weighted F1 score of 0.78. The same classifier yielded similar performance on subsequent data collected during 2019–2023. We then evaluated the stability of the classification performance by conducting cross-classification, using quarterly data before, during and after the COVID-19 pandemic (2019–2023). Predictive classification from models trained with historical data is stable during this period. Furthermore, we examined the feature importance (quantified by the mean decrease impurity score) of the fitted model. As expected, incident type (major vs minor) is the most important feature. Interestingly, the importance of age in predicting clinical outcomes varies substantially before and after the 4th quarter of 2019. Together, these results demonstrate the capacity of machine learning and its explainability in predicting ED clinical outcomes from simple features.
published_date 2024-08-15T12:56:51Z
_version_ 1811893831609614336
score 11.037581

Similar Items