Predicting asthma-related crisis events using routine electronic healthcare data: a quantitative database analysis study

Noble, Michael; Burden, Annie; Stirling, Susan; Clark, Allan B; Musgrave, Stanley; Al, Mohammad A.; Price, David; Davies, Gwyneth; Pinnock, Hilary; Pond, Martin; Sheikh, Aziz; Sims, Erika J; Walker, Samantha; Wilson, Andrew M

doi:10.3399/bjgp.2020.1042

Journal article 168 views 25 downloads

Predicting asthma-related crisis events using routine electronic healthcare data: a quantitative database analysis study

Michael Noble, Annie Burden, Susan Stirling, Allan B Clark, Stanley Musgrave, Mohammad A. Al Sallakh

, David Price, Gwyneth Davies

, Hilary Pinnock, Martin Pond, Aziz Sheikh, Erika J Sims, Samantha Walker, Andrew M Wilson

British Journal of General Practice, Volume: 71, Issue: 713, Pages: e948 - e957

Swansea University Authors: Mohammad A. Al Sallakh , Gwyneth Davies

Check full text

DOI (Published version): 10.3399/bjgp.2020.1042

Abstract

Background There is no published algorithm predicting asthma crisis events (accident and emergency [A&E] attendance, hospitalisation, or death) using routinely available electronic health record (EHR) data.Aim To develop an algorithm to identify individuals at high risk of an asthma crisis event...

Full description

Published in:	British Journal of General Practice
ISSN:	0960-1643 1478-5242
Published:	Royal College of General Practitioners 2021
Online Access:	Check full text
URI:	https://cronfa.swan.ac.uk/Record/cronfa70386

first_indexed	2025-09-18T16:02:06Z
last_indexed	2025-11-04T15:01:56Z
id	cronfa70386
recordtype	SURis
fullrecord	<?xml version="1.0"?><rfc1807><datestamp>2025-11-03T09:29:07.9830278</datestamp><bib-version>v2</bib-version><id>70386</id><entry>2025-09-18</entry><title>Predicting asthma-related crisis events using routine electronic healthcare data: a quantitative database analysis study</title><swanseaauthors><author><sid>caefb3bbcb492f1e7e938c2a3189f474</sid><ORCID>NULL</ORCID><firstname>Mohammad A.</firstname><surname>Al Sallakh</surname><name>Mohammad A. Al Sallakh</name><active>true</active><ethesisStudent>true</ethesisStudent></author><author><sid>92d69cf8519a334ced3f55142c811d95</sid><ORCID>0000-0003-1218-1008</ORCID><firstname>Gwyneth</firstname><surname>Davies</surname><name>Gwyneth Davies</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2025-09-18</date><abstract>Background There is no published algorithm predicting asthma crisis events (accident and emergency [A&E] attendance, hospitalisation, or death) using routinely available electronic health record (EHR) data.Aim To develop an algorithm to identify individuals at high risk of an asthma crisis event.Design and setting Database analysis from primary care EHRs of people with asthma across England and Scotland.Method Multivariable logistic regression was applied to a dataset of 61 861 people with asthma from England and Scotland using the Clinical Practice Research Datalink. External validation was performed using the Secure Anonymised Information Linkage Databank of 174 240 patients from Wales. Outcomes were ≥1 hospitalisation (development dataset) and asthma-related hospitalisation, A&E attendance, or death (validation dataset) within a 12-month period.Results Risk factors for asthma-related crisis events included previous hospitalisation, older age, underweight, smoking, and blood eosinophilia. The prediction algorithm had acceptable predictive ability with a receiver operating characteristic of 0.71 (95% confidence interval [CI] = 0.70 to 0.72) in the validation dataset. Using a cut-point based on the 7% of the population at greatest risk results in a positive predictive value of 5.7% (95% CI = 5.3% to 6.1%) and a negative predictive value of 98.9% (95% CI = 98.9% to 99.0%), with sensitivity of 28.5% (95% CI = 26.7% to 30.3%) and specificity of 93.3% (95% CI = 93.2% to 93.4%); those individuals had an event risk of 6.0% compared with 1.1% for the remaining population. In total, 18 people would need to be followed to identify one admission.Conclusion This externally validated algorithm has acceptable predictive ability for identifying patients at high risk of asthma-related crisis events and excluding those not at high risk.</abstract><type>Journal Article</type><journal>British Journal of General Practice</journal><volume>71</volume><journalNumber>713</journalNumber><paginationStart>e948</paginationStart><paginationEnd>e957</paginationEnd><publisher>Royal College of General Practitioners</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>0960-1643</issnPrint><issnElectronic>1478-5242</issnElectronic><keywords>algorithms; asthma; asthma attack; general practice; prediction; risk</keywords><publishedDay>25</publishedDay><publishedMonth>11</publishedMonth><publishedYear>2021</publishedYear><publishedDate>2021-11-25</publishedDate><doi>10.3399/bjgp.2020.1042</doi><url/><notes/><college>COLLEGE NANME</college><department>Medicine</department><CollegeCode>COLLEGE CODE</CollegeCode><institution>Swansea University</institution><apcterm>Another institution paid the OA fee</apcterm><funders>Asthma UK Centre for Applied Research</funders><projectreference/><lastEdited>2025-11-03T09:29:07.9830278</lastEdited><Created>2025-09-18T11:16:08.2326591</Created><path><level id="1">Faculty of Medicine, Health and Life Sciences</level><level id="2">Swansea University Medical School - Health Data Science</level></path><authors><author><firstname>Michael</firstname><surname>Noble</surname><order>1</order></author><author><firstname>Annie</firstname><surname>Burden</surname><order>2</order></author><author><firstname>Susan</firstname><surname>Stirling</surname><order>3</order></author><author><firstname>Allan B</firstname><surname>Clark</surname><order>4</order></author><author><firstname>Stanley</firstname><surname>Musgrave</surname><order>5</order></author><author><firstname>Mohammad A.</firstname><surname>Al Sallakh</surname><orcid>NULL</orcid><order>6</order></author><author><firstname>David</firstname><surname>Price</surname><order>7</order></author><author><firstname>Gwyneth</firstname><surname>Davies</surname><orcid>0000-0003-1218-1008</orcid><order>8</order></author><author><firstname>Hilary</firstname><surname>Pinnock</surname><order>9</order></author><author><firstname>Martin</firstname><surname>Pond</surname><order>10</order></author><author><firstname>Aziz</firstname><surname>Sheikh</surname><order>11</order></author><author><firstname>Erika J</firstname><surname>Sims</surname><order>12</order></author><author><firstname>Samantha</firstname><surname>Walker</surname><order>13</order></author><author><firstname>Andrew M</firstname><surname>Wilson</surname><order>14</order></author></authors><documents><document><filename>70386__35533__4232b2642da44cb3a0f8daa7ecc8814e.pdf</filename><originalFilename>70386.VoR.pdf</originalFilename><uploaded>2025-11-03T09:26:15.4339879</uploaded><type>Output</type><contentLength>184640</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>©The Authors. This article is Open Access: CC BY 4.0 licence.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licences/ by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling	2025-11-03T09:29:07.9830278 v2 70386 2025-09-18 Predicting asthma-related crisis events using routine electronic healthcare data: a quantitative database analysis study caefb3bbcb492f1e7e938c2a3189f474 NULL Mohammad A. Al Sallakh Mohammad A. Al Sallakh true true 92d69cf8519a334ced3f55142c811d95 0000-0003-1218-1008 Gwyneth Davies Gwyneth Davies true false 2025-09-18 Background There is no published algorithm predicting asthma crisis events (accident and emergency [A&E] attendance, hospitalisation, or death) using routinely available electronic health record (EHR) data.Aim To develop an algorithm to identify individuals at high risk of an asthma crisis event.Design and setting Database analysis from primary care EHRs of people with asthma across England and Scotland.Method Multivariable logistic regression was applied to a dataset of 61 861 people with asthma from England and Scotland using the Clinical Practice Research Datalink. External validation was performed using the Secure Anonymised Information Linkage Databank of 174 240 patients from Wales. Outcomes were ≥1 hospitalisation (development dataset) and asthma-related hospitalisation, A&E attendance, or death (validation dataset) within a 12-month period.Results Risk factors for asthma-related crisis events included previous hospitalisation, older age, underweight, smoking, and blood eosinophilia. The prediction algorithm had acceptable predictive ability with a receiver operating characteristic of 0.71 (95% confidence interval [CI] = 0.70 to 0.72) in the validation dataset. Using a cut-point based on the 7% of the population at greatest risk results in a positive predictive value of 5.7% (95% CI = 5.3% to 6.1%) and a negative predictive value of 98.9% (95% CI = 98.9% to 99.0%), with sensitivity of 28.5% (95% CI = 26.7% to 30.3%) and specificity of 93.3% (95% CI = 93.2% to 93.4%); those individuals had an event risk of 6.0% compared with 1.1% for the remaining population. In total, 18 people would need to be followed to identify one admission.Conclusion This externally validated algorithm has acceptable predictive ability for identifying patients at high risk of asthma-related crisis events and excluding those not at high risk. Journal Article British Journal of General Practice 71 713 e948 e957 Royal College of General Practitioners 0960-1643 1478-5242 algorithms; asthma; asthma attack; general practice; prediction; risk 25 11 2021 2021-11-25 10.3399/bjgp.2020.1042 COLLEGE NANME Medicine COLLEGE CODE Swansea University Another institution paid the OA fee Asthma UK Centre for Applied Research 2025-11-03T09:29:07.9830278 2025-09-18T11:16:08.2326591 Faculty of Medicine, Health and Life Sciences Swansea University Medical School - Health Data Science Michael Noble 1 Annie Burden 2 Susan Stirling 3 Allan B Clark 4 Stanley Musgrave 5 Mohammad A. Al Sallakh NULL 6 David Price 7 Gwyneth Davies 0000-0003-1218-1008 8 Hilary Pinnock 9 Martin Pond 10 Aziz Sheikh 11 Erika J Sims 12 Samantha Walker 13 Andrew M Wilson 14 70386__35533__4232b2642da44cb3a0f8daa7ecc8814e.pdf 70386.VoR.pdf 2025-11-03T09:26:15.4339879 Output 184640 application/pdf Version of Record true ©The Authors. This article is Open Access: CC BY 4.0 licence. true eng http://creativecommons.org/licences/ by/4.0/
title	Predicting asthma-related crisis events using routine electronic healthcare data: a quantitative database analysis study
spellingShingle	Predicting asthma-related crisis events using routine electronic healthcare data: a quantitative database analysis study Mohammad A. Al Sallakh Gwyneth Davies
title_short	Predicting asthma-related crisis events using routine electronic healthcare data: a quantitative database analysis study
title_full	Predicting asthma-related crisis events using routine electronic healthcare data: a quantitative database analysis study
title_fullStr	Predicting asthma-related crisis events using routine electronic healthcare data: a quantitative database analysis study
title_full_unstemmed	Predicting asthma-related crisis events using routine electronic healthcare data: a quantitative database analysis study
title_sort	Predicting asthma-related crisis events using routine electronic healthcare data: a quantitative database analysis study
author_id_str_mv	caefb3bbcb492f1e7e938c2a3189f474 92d69cf8519a334ced3f55142c811d95
author_id_fullname_str_mv	caefb3bbcb492f1e7e938c2a3189f474_*_Mohammad A. Al Sallakh 92d69cf8519a334ced3f55142c811d95_*_Gwyneth Davies
author	Mohammad A. Al Sallakh Gwyneth Davies
author2	Michael Noble Annie Burden Susan Stirling Allan B Clark Stanley Musgrave Mohammad A. Al Sallakh David Price Gwyneth Davies Hilary Pinnock Martin Pond Aziz Sheikh Erika J Sims Samantha Walker Andrew M Wilson
format	Journal article
container_title	British Journal of General Practice
container_volume	71
container_issue	713
container_start_page	e948
publishDate	2021
institution	Swansea University
issn	0960-1643 1478-5242
doi_str_mv	10.3399/bjgp.2020.1042
publisher	Royal College of General Practitioners
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 - Health Data Science{{{_:::_}}}Faculty of Medicine, Health and Life Sciences{{{_:::_}}}Swansea University Medical School - Health Data Science
document_store_str	1
active_str	0
description	Background There is no published algorithm predicting asthma crisis events (accident and emergency [A&E] attendance, hospitalisation, or death) using routinely available electronic health record (EHR) data.Aim To develop an algorithm to identify individuals at high risk of an asthma crisis event.Design and setting Database analysis from primary care EHRs of people with asthma across England and Scotland.Method Multivariable logistic regression was applied to a dataset of 61 861 people with asthma from England and Scotland using the Clinical Practice Research Datalink. External validation was performed using the Secure Anonymised Information Linkage Databank of 174 240 patients from Wales. Outcomes were ≥1 hospitalisation (development dataset) and asthma-related hospitalisation, A&E attendance, or death (validation dataset) within a 12-month period.Results Risk factors for asthma-related crisis events included previous hospitalisation, older age, underweight, smoking, and blood eosinophilia. The prediction algorithm had acceptable predictive ability with a receiver operating characteristic of 0.71 (95% confidence interval [CI] = 0.70 to 0.72) in the validation dataset. Using a cut-point based on the 7% of the population at greatest risk results in a positive predictive value of 5.7% (95% CI = 5.3% to 6.1%) and a negative predictive value of 98.9% (95% CI = 98.9% to 99.0%), with sensitivity of 28.5% (95% CI = 26.7% to 30.3%) and specificity of 93.3% (95% CI = 93.2% to 93.4%); those individuals had an event risk of 6.0% compared with 1.1% for the remaining population. In total, 18 people would need to be followed to identify one admission.Conclusion This externally validated algorithm has acceptable predictive ability for identifying patients at high risk of asthma-related crisis events and excluding those not at high risk.
published_date	2021-11-25T18:06:43Z
_version_	1850692604912467968
score	11.08899

Predicting asthma-related crisis events using routine electronic healthcare data: a quantitative database analysis study

Similar Items