No Cover Image

Journal article 319 views 70 downloads

Artificial neural network risk prediction of COPD exacerbations using urine biomarkers

Ahmed J Yousuf, Gita Parekh, Malcolm Farrow, Graham Ball, Sara Graziadio, Kevin Wilson, Clare Lendrem Orcid Logo, Liesl Carr, Lynne Watson, Sarah Parker, Joanne Finch, Sarah Glover, Vijay Mistry, Kate Porter, Annelyse Duvoix, Linda O'Brien, Sarah Rees, Keir Lewis Orcid Logo, Paul Davis, Christopher E Brightling

ERJ Open Research, Volume: 11, Issue: 3, Start page: 00797-2024

Swansea University Author: Keir Lewis Orcid Logo

  • 69762.VOR.pdf

    PDF | Version of Record

    © The authors 2025. This version is distributed under the terms of the Creative Commons Attribution Licence 4.0.

    Download (496.88KB)

Check full text

DOI (Published version): 10.1183/23120541.00797-2024

Abstract

COPD exacerbations cause considerable morbidity and mortality. We sought to identify a panel of urine biomarkers that can distinguish between stable and exacerbation states and predict risk of future exacerbations. A retrospective discovery study was done measuring 35 biomarkers implicated in COPD p...

Full description

Published in: ERJ Open Research
ISSN: 2312-0541
Published: European Respiratory Society 2025
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa69762
first_indexed 2025-06-18T12:30:04Z
last_indexed 2025-06-19T10:47:22Z
id cronfa69762
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2025-06-18T13:31:17.6517656</datestamp><bib-version>v2</bib-version><id>69762</id><entry>2025-06-18</entry><title>Artificial neural network risk prediction of COPD exacerbations using urine biomarkers</title><swanseaauthors><author><sid>bc53c343c975d6e0ad88c1d8b9ddd70c</sid><ORCID>0000-0002-8248-6774</ORCID><firstname>Keir</firstname><surname>Lewis</surname><name>Keir Lewis</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2025-06-18</date><deptcode>MEDS</deptcode><abstract>COPD exacerbations cause considerable morbidity and mortality. We sought to identify a panel of urine biomarkers that can distinguish between stable and exacerbation states and predict risk of future exacerbations. A retrospective discovery study was done measuring 35 biomarkers implicated in COPD pathogenesis in paired urine samples from 55 COPD subjects during stable and exacerbation states. A logistic regression model combining the 10 most discriminatory biomarkers in distinguishing between stable and exacerbation states was developed as a near-patient dipstick test with an opto-electronic reader. This biomarker panel was tested in a prospective study of 105 COPD subjects who undertook daily home urine testing over 6&#x2005;months. The regression model was validated in paired samples from 26 individuals out of 105. An artificial neural network (ANN) using the urine biomarkers from 85 out of 105 subjects was developed and tested as a clinical decision tool to predict risk of an exacerbation. The 10-biomarker panel (NGAL, TIMP1, CRP, fibrinogen, CC16, fMLP, TIMP2, A1AT, B2M and MMP8) was able to distinguish exacerbation stable state in the discovery study (ROC with an AUC 0.84, 95% CI 0.76-0.92; p &lt;0.01) and validation study (AUC 0.81, 95% CI 0.70-0.92, p&lt;0.01). The ANN model predicted an exacerbation within a 13-day window frame with an AUC 0.89 (95% CI 0.89-0.90) and identified an exacerbation median (interquartile range) 7 (5-9) days prior to clinical diagnosis. We identified a panel of biomarkers that can distinguish between stable and exacerbation state, and using an ANN model, it can predict exacerbations before symptoms occur.</abstract><type>Journal Article</type><journal>ERJ Open Research</journal><volume>11</volume><journalNumber>3</journalNumber><paginationStart>00797-2024</paginationStart><paginationEnd/><publisher>European Respiratory Society</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic>2312-0541</issnElectronic><keywords/><publishedDay>4</publishedDay><publishedMonth>6</publishedMonth><publishedYear>2025</publishedYear><publishedDate>2025-06-04</publishedDate><doi>10.1183/23120541.00797-2024</doi><url/><notes/><college>COLLEGE NANME</college><department>Medical School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>MEDS</DepartmentCode><institution>Swansea University</institution><apcterm>Another institution paid the OA fee</apcterm><funders/><projectreference/><lastEdited>2025-06-18T13:31:17.6517656</lastEdited><Created>2025-06-18T13:20:11.1001495</Created><path><level id="1">Faculty of Medicine, Health and Life Sciences</level><level id="2">Swansea University Medical School - Biomedical Science</level></path><authors><author><firstname>Ahmed J</firstname><surname>Yousuf</surname><order>1</order></author><author><firstname>Gita</firstname><surname>Parekh</surname><order>2</order></author><author><firstname>Malcolm</firstname><surname>Farrow</surname><order>3</order></author><author><firstname>Graham</firstname><surname>Ball</surname><order>4</order></author><author><firstname>Sara</firstname><surname>Graziadio</surname><order>5</order></author><author><firstname>Kevin</firstname><surname>Wilson</surname><order>6</order></author><author><firstname>Clare</firstname><surname>Lendrem</surname><orcid>0000-0002-9435-7398</orcid><order>7</order></author><author><firstname>Liesl</firstname><surname>Carr</surname><order>8</order></author><author><firstname>Lynne</firstname><surname>Watson</surname><order>9</order></author><author><firstname>Sarah</firstname><surname>Parker</surname><order>10</order></author><author><firstname>Joanne</firstname><surname>Finch</surname><order>11</order></author><author><firstname>Sarah</firstname><surname>Glover</surname><order>12</order></author><author><firstname>Vijay</firstname><surname>Mistry</surname><order>13</order></author><author><firstname>Kate</firstname><surname>Porter</surname><order>14</order></author><author><firstname>Annelyse</firstname><surname>Duvoix</surname><order>15</order></author><author><firstname>Linda</firstname><surname>O'Brien</surname><order>16</order></author><author><firstname>Sarah</firstname><surname>Rees</surname><order>17</order></author><author><firstname>Keir</firstname><surname>Lewis</surname><orcid>0000-0002-8248-6774</orcid><order>18</order></author><author><firstname>Paul</firstname><surname>Davis</surname><order>19</order></author><author><firstname>Christopher E</firstname><surname>Brightling</surname><order>20</order></author></authors><documents><document><filename>69762__34511__5c1dd2b657f04b5994df72d0630d0ea9.pdf</filename><originalFilename>69762.VOR.pdf</originalFilename><uploaded>2025-06-18T13:28:33.7168161</uploaded><type>Output</type><contentLength>508808</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>&#xA9; The authors 2025. This version is distributed under the terms of the Creative Commons Attribution Licence 4.0.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2025-06-18T13:31:17.6517656 v2 69762 2025-06-18 Artificial neural network risk prediction of COPD exacerbations using urine biomarkers bc53c343c975d6e0ad88c1d8b9ddd70c 0000-0002-8248-6774 Keir Lewis Keir Lewis true false 2025-06-18 MEDS COPD exacerbations cause considerable morbidity and mortality. We sought to identify a panel of urine biomarkers that can distinguish between stable and exacerbation states and predict risk of future exacerbations. A retrospective discovery study was done measuring 35 biomarkers implicated in COPD pathogenesis in paired urine samples from 55 COPD subjects during stable and exacerbation states. A logistic regression model combining the 10 most discriminatory biomarkers in distinguishing between stable and exacerbation states was developed as a near-patient dipstick test with an opto-electronic reader. This biomarker panel was tested in a prospective study of 105 COPD subjects who undertook daily home urine testing over 6 months. The regression model was validated in paired samples from 26 individuals out of 105. An artificial neural network (ANN) using the urine biomarkers from 85 out of 105 subjects was developed and tested as a clinical decision tool to predict risk of an exacerbation. The 10-biomarker panel (NGAL, TIMP1, CRP, fibrinogen, CC16, fMLP, TIMP2, A1AT, B2M and MMP8) was able to distinguish exacerbation stable state in the discovery study (ROC with an AUC 0.84, 95% CI 0.76-0.92; p <0.01) and validation study (AUC 0.81, 95% CI 0.70-0.92, p<0.01). The ANN model predicted an exacerbation within a 13-day window frame with an AUC 0.89 (95% CI 0.89-0.90) and identified an exacerbation median (interquartile range) 7 (5-9) days prior to clinical diagnosis. We identified a panel of biomarkers that can distinguish between stable and exacerbation state, and using an ANN model, it can predict exacerbations before symptoms occur. Journal Article ERJ Open Research 11 3 00797-2024 European Respiratory Society 2312-0541 4 6 2025 2025-06-04 10.1183/23120541.00797-2024 COLLEGE NANME Medical School COLLEGE CODE MEDS Swansea University Another institution paid the OA fee 2025-06-18T13:31:17.6517656 2025-06-18T13:20:11.1001495 Faculty of Medicine, Health and Life Sciences Swansea University Medical School - Biomedical Science Ahmed J Yousuf 1 Gita Parekh 2 Malcolm Farrow 3 Graham Ball 4 Sara Graziadio 5 Kevin Wilson 6 Clare Lendrem 0000-0002-9435-7398 7 Liesl Carr 8 Lynne Watson 9 Sarah Parker 10 Joanne Finch 11 Sarah Glover 12 Vijay Mistry 13 Kate Porter 14 Annelyse Duvoix 15 Linda O'Brien 16 Sarah Rees 17 Keir Lewis 0000-0002-8248-6774 18 Paul Davis 19 Christopher E Brightling 20 69762__34511__5c1dd2b657f04b5994df72d0630d0ea9.pdf 69762.VOR.pdf 2025-06-18T13:28:33.7168161 Output 508808 application/pdf Version of Record true © The authors 2025. This version is distributed under the terms of the Creative Commons Attribution Licence 4.0. true eng https://creativecommons.org/licenses/by/4.0/
title Artificial neural network risk prediction of COPD exacerbations using urine biomarkers
spellingShingle Artificial neural network risk prediction of COPD exacerbations using urine biomarkers
Keir Lewis
title_short Artificial neural network risk prediction of COPD exacerbations using urine biomarkers
title_full Artificial neural network risk prediction of COPD exacerbations using urine biomarkers
title_fullStr Artificial neural network risk prediction of COPD exacerbations using urine biomarkers
title_full_unstemmed Artificial neural network risk prediction of COPD exacerbations using urine biomarkers
title_sort Artificial neural network risk prediction of COPD exacerbations using urine biomarkers
author_id_str_mv bc53c343c975d6e0ad88c1d8b9ddd70c
author_id_fullname_str_mv bc53c343c975d6e0ad88c1d8b9ddd70c_***_Keir Lewis
author Keir Lewis
author2 Ahmed J Yousuf
Gita Parekh
Malcolm Farrow
Graham Ball
Sara Graziadio
Kevin Wilson
Clare Lendrem
Liesl Carr
Lynne Watson
Sarah Parker
Joanne Finch
Sarah Glover
Vijay Mistry
Kate Porter
Annelyse Duvoix
Linda O'Brien
Sarah Rees
Keir Lewis
Paul Davis
Christopher E Brightling
format Journal article
container_title ERJ Open Research
container_volume 11
container_issue 3
container_start_page 00797-2024
publishDate 2025
institution Swansea University
issn 2312-0541
doi_str_mv 10.1183/23120541.00797-2024
publisher European Respiratory Society
college_str Faculty of Medicine, Health and Life Sciences
hierarchytype
hierarchy_top_id facultyofmedicinehealthandlifesciences
hierarchy_top_title Faculty of Medicine, Health and Life Sciences
hierarchy_parent_id facultyofmedicinehealthandlifesciences
hierarchy_parent_title Faculty of Medicine, Health and Life Sciences
department_str Swansea University Medical School - Biomedical Science{{{_:::_}}}Faculty of Medicine, Health and Life Sciences{{{_:::_}}}Swansea University Medical School - Biomedical Science
document_store_str 1
active_str 0
description COPD exacerbations cause considerable morbidity and mortality. We sought to identify a panel of urine biomarkers that can distinguish between stable and exacerbation states and predict risk of future exacerbations. A retrospective discovery study was done measuring 35 biomarkers implicated in COPD pathogenesis in paired urine samples from 55 COPD subjects during stable and exacerbation states. A logistic regression model combining the 10 most discriminatory biomarkers in distinguishing between stable and exacerbation states was developed as a near-patient dipstick test with an opto-electronic reader. This biomarker panel was tested in a prospective study of 105 COPD subjects who undertook daily home urine testing over 6 months. The regression model was validated in paired samples from 26 individuals out of 105. An artificial neural network (ANN) using the urine biomarkers from 85 out of 105 subjects was developed and tested as a clinical decision tool to predict risk of an exacerbation. The 10-biomarker panel (NGAL, TIMP1, CRP, fibrinogen, CC16, fMLP, TIMP2, A1AT, B2M and MMP8) was able to distinguish exacerbation stable state in the discovery study (ROC with an AUC 0.84, 95% CI 0.76-0.92; p <0.01) and validation study (AUC 0.81, 95% CI 0.70-0.92, p<0.01). The ANN model predicted an exacerbation within a 13-day window frame with an AUC 0.89 (95% CI 0.89-0.90) and identified an exacerbation median (interquartile range) 7 (5-9) days prior to clinical diagnosis. We identified a panel of biomarkers that can distinguish between stable and exacerbation state, and using an ANN model, it can predict exacerbations before symptoms occur.
published_date 2025-06-04T14:16:43Z
_version_ 1851040521398517760
score 11.089469

Similar Items