Loading…
Modelling outcomes after paediatric brain injury with admission laboratory values: a machine-learning approach
Severe traumatic brain injury (TBI) is a leading cause of mortality in children, but the accurate prediction of outcomes at the point of admission remains very challenging. Admission laboratory results are a promising potential source of prognostic data, but have not been widely explored in paediatr...
Saved in:
| Published in: | Pediatric research 2019-11, Vol.86 (5), p.641-645 |
|---|---|
| Main Authors: | , , , , , , , |
| Format: | Article |
| Language: | English |
| Subjects: | |
| Citations: | Items that this one cites Items that cite this one |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| cited_by | cdi_FETCH-LOGICAL-c372t-2267beda39833ea10972363b1893eb6cb026754f150a18626022feffc89bec213 |
|---|---|
| cites | cdi_FETCH-LOGICAL-c372t-2267beda39833ea10972363b1893eb6cb026754f150a18626022feffc89bec213 |
| container_end_page | 645 |
| container_issue | 5 |
| container_start_page | 641 |
| container_title | Pediatric research |
| container_volume | 86 |
| creator | Kayhanian, Saeed Young, Adam M H Mangla, Chaitanya Jalloh, Ibrahim Fernandes, Helen M Garnett, Matthew R Hutchinson, Peter J Agrawal, Shruti |
| description | Severe traumatic brain injury (TBI) is a leading cause of mortality in children, but the accurate prediction of outcomes at the point of admission remains very challenging. Admission laboratory results are a promising potential source of prognostic data, but have not been widely explored in paediatric cohorts. Herein, we use machine-learning methods to analyse 14 different serum parameters together and develop a prognostic model to predict 6-month outcomes in children with severe TBI.
A retrospective review of patients admitted to Cambridge University Hospital's Paediatric Intensive Care Unit between 2009 and 2013 with a TBI. The data for 14 admission serum parameters were recorded. Logistic regression and a support vector machine (SVM) were trained with these data against dichotimised outcomes from the recorded 6-month Glasgow Outcome Scale.
Ninety-four patients were identified. Admission levels of lactate, H+, and glucose were identified as being the most informative of 6-month outcomes. Four different models were produced. The SVM using just the three most informative parameters was the best able to predict favourable outcomes at 6 months (sensitivity = 80%, specificity = 99%).
Our results demonstrate the potential for highly accurate outcome prediction after severe paediatric TBI using admission laboratory data. |
| doi_str_mv | 10.1038/s41390-019-0510-9 |
| format | article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2265739549</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2313760448</sourcerecordid><originalsourceid>FETCH-LOGICAL-c372t-2267beda39833ea10972363b1893eb6cb026754f150a18626022feffc89bec213</originalsourceid><addsrcrecordid>eNpdUbtOxDAQtBAIjoMPoEGWaGgCtjcv0yHESzpEA7W1cRzwKbEPOwHd3-PTAQXVSruzs7MzhJxwdsEZ1Jcx5yBZxrjMWMFZJnfIjBeQOnle7ZIZY8AzkLI-IIcxLhnjeVHn--QAOOQSSjYj7sm3pu-te6N-GrUfTKTYjSbQFZrW4hispk1A66h1yyms6Zcd3ym2g43Rekd7bHzA0afJJ_aTiVcU6YD63TqT9QaD23DjahV8ah6RvQ77aI5_6py83t2-3Dxki-f7x5vrRaahEmMmRFk1pkWQNYBBzmQloISG1xJMU-qGJUCRd7xgyOtSlEyIznSdrmVjtOAwJ-db3nT2I4kaVdKr06PojJ-iSgeKCmSRXJiTs3_QpZ-CS-qUSD5VZTKzTii-RengYwymU6tgBwxrxZnahKG2YagUhtqEoTbMpz_MUzOY9m_j1334BtckhVg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2313760448</pqid></control><display><type>article</type><title>Modelling outcomes after paediatric brain injury with admission laboratory values: a machine-learning approach</title><source>Springer Link</source><creator>Kayhanian, Saeed ; Young, Adam M H ; Mangla, Chaitanya ; Jalloh, Ibrahim ; Fernandes, Helen M ; Garnett, Matthew R ; Hutchinson, Peter J ; Agrawal, Shruti</creator><creatorcontrib>Kayhanian, Saeed ; Young, Adam M H ; Mangla, Chaitanya ; Jalloh, Ibrahim ; Fernandes, Helen M ; Garnett, Matthew R ; Hutchinson, Peter J ; Agrawal, Shruti</creatorcontrib><description>Severe traumatic brain injury (TBI) is a leading cause of mortality in children, but the accurate prediction of outcomes at the point of admission remains very challenging. Admission laboratory results are a promising potential source of prognostic data, but have not been widely explored in paediatric cohorts. Herein, we use machine-learning methods to analyse 14 different serum parameters together and develop a prognostic model to predict 6-month outcomes in children with severe TBI.
A retrospective review of patients admitted to Cambridge University Hospital's Paediatric Intensive Care Unit between 2009 and 2013 with a TBI. The data for 14 admission serum parameters were recorded. Logistic regression and a support vector machine (SVM) were trained with these data against dichotimised outcomes from the recorded 6-month Glasgow Outcome Scale.
Ninety-four patients were identified. Admission levels of lactate, H+, and glucose were identified as being the most informative of 6-month outcomes. Four different models were produced. The SVM using just the three most informative parameters was the best able to predict favourable outcomes at 6 months (sensitivity = 80%, specificity = 99%).
Our results demonstrate the potential for highly accurate outcome prediction after severe paediatric TBI using admission laboratory data.</description><identifier>ISSN: 0031-3998</identifier><identifier>EISSN: 1530-0447</identifier><identifier>DOI: 10.1038/s41390-019-0510-9</identifier><identifier>PMID: 31349360</identifier><language>eng</language><publisher>United States: Nature Publishing Group</publisher><subject>Brain Injuries - therapy ; Child ; Female ; Humans ; Machine Learning ; Male ; Medical prognosis ; Medical tests ; Patient Admission ; Patient admissions ; Pediatrics ; Traumatic brain injury ; Treatment Outcome</subject><ispartof>Pediatric research, 2019-11, Vol.86 (5), p.641-645</ispartof><rights>Copyright Nature Publishing Group Nov 2019</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c372t-2267beda39833ea10972363b1893eb6cb026754f150a18626022feffc89bec213</citedby><cites>FETCH-LOGICAL-c372t-2267beda39833ea10972363b1893eb6cb026754f150a18626022feffc89bec213</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>315,786,790,27957,27958</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/31349360$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Kayhanian, Saeed</creatorcontrib><creatorcontrib>Young, Adam M H</creatorcontrib><creatorcontrib>Mangla, Chaitanya</creatorcontrib><creatorcontrib>Jalloh, Ibrahim</creatorcontrib><creatorcontrib>Fernandes, Helen M</creatorcontrib><creatorcontrib>Garnett, Matthew R</creatorcontrib><creatorcontrib>Hutchinson, Peter J</creatorcontrib><creatorcontrib>Agrawal, Shruti</creatorcontrib><title>Modelling outcomes after paediatric brain injury with admission laboratory values: a machine-learning approach</title><title>Pediatric research</title><addtitle>Pediatr Res</addtitle><description>Severe traumatic brain injury (TBI) is a leading cause of mortality in children, but the accurate prediction of outcomes at the point of admission remains very challenging. Admission laboratory results are a promising potential source of prognostic data, but have not been widely explored in paediatric cohorts. Herein, we use machine-learning methods to analyse 14 different serum parameters together and develop a prognostic model to predict 6-month outcomes in children with severe TBI.
A retrospective review of patients admitted to Cambridge University Hospital's Paediatric Intensive Care Unit between 2009 and 2013 with a TBI. The data for 14 admission serum parameters were recorded. Logistic regression and a support vector machine (SVM) were trained with these data against dichotimised outcomes from the recorded 6-month Glasgow Outcome Scale.
Ninety-four patients were identified. Admission levels of lactate, H+, and glucose were identified as being the most informative of 6-month outcomes. Four different models were produced. The SVM using just the three most informative parameters was the best able to predict favourable outcomes at 6 months (sensitivity = 80%, specificity = 99%).
Our results demonstrate the potential for highly accurate outcome prediction after severe paediatric TBI using admission laboratory data.</description><subject>Brain Injuries - therapy</subject><subject>Child</subject><subject>Female</subject><subject>Humans</subject><subject>Machine Learning</subject><subject>Male</subject><subject>Medical prognosis</subject><subject>Medical tests</subject><subject>Patient Admission</subject><subject>Patient admissions</subject><subject>Pediatrics</subject><subject>Traumatic brain injury</subject><subject>Treatment Outcome</subject><issn>0031-3998</issn><issn>1530-0447</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><recordid>eNpdUbtOxDAQtBAIjoMPoEGWaGgCtjcv0yHESzpEA7W1cRzwKbEPOwHd3-PTAQXVSruzs7MzhJxwdsEZ1Jcx5yBZxrjMWMFZJnfIjBeQOnle7ZIZY8AzkLI-IIcxLhnjeVHn--QAOOQSSjYj7sm3pu-te6N-GrUfTKTYjSbQFZrW4hispk1A66h1yyms6Zcd3ym2g43Rekd7bHzA0afJJ_aTiVcU6YD63TqT9QaD23DjahV8ah6RvQ77aI5_6py83t2-3Dxki-f7x5vrRaahEmMmRFk1pkWQNYBBzmQloISG1xJMU-qGJUCRd7xgyOtSlEyIznSdrmVjtOAwJ-db3nT2I4kaVdKr06PojJ-iSgeKCmSRXJiTs3_QpZ-CS-qUSD5VZTKzTii-RengYwymU6tgBwxrxZnahKG2YagUhtqEoTbMpz_MUzOY9m_j1334BtckhVg</recordid><startdate>20191101</startdate><enddate>20191101</enddate><creator>Kayhanian, Saeed</creator><creator>Young, Adam M H</creator><creator>Mangla, Chaitanya</creator><creator>Jalloh, Ibrahim</creator><creator>Fernandes, Helen M</creator><creator>Garnett, Matthew R</creator><creator>Hutchinson, Peter J</creator><creator>Agrawal, Shruti</creator><general>Nature Publishing Group</general><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>7X7</scope><scope>7XB</scope><scope>88E</scope><scope>8C1</scope><scope>8FI</scope><scope>8FJ</scope><scope>8FK</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>BENPR</scope><scope>CCPQU</scope><scope>FYUFA</scope><scope>GHDGH</scope><scope>K9.</scope><scope>M0S</scope><scope>M1P</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>7X8</scope></search><sort><creationdate>20191101</creationdate><title>Modelling outcomes after paediatric brain injury with admission laboratory values: a machine-learning approach</title><author>Kayhanian, Saeed ; Young, Adam M H ; Mangla, Chaitanya ; Jalloh, Ibrahim ; Fernandes, Helen M ; Garnett, Matthew R ; Hutchinson, Peter J ; Agrawal, Shruti</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c372t-2267beda39833ea10972363b1893eb6cb026754f150a18626022feffc89bec213</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Brain Injuries - therapy</topic><topic>Child</topic><topic>Female</topic><topic>Humans</topic><topic>Machine Learning</topic><topic>Male</topic><topic>Medical prognosis</topic><topic>Medical tests</topic><topic>Patient Admission</topic><topic>Patient admissions</topic><topic>Pediatrics</topic><topic>Traumatic brain injury</topic><topic>Treatment Outcome</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Kayhanian, Saeed</creatorcontrib><creatorcontrib>Young, Adam M H</creatorcontrib><creatorcontrib>Mangla, Chaitanya</creatorcontrib><creatorcontrib>Jalloh, Ibrahim</creatorcontrib><creatorcontrib>Fernandes, Helen M</creatorcontrib><creatorcontrib>Garnett, Matthew R</creatorcontrib><creatorcontrib>Hutchinson, Peter J</creatorcontrib><creatorcontrib>Agrawal, Shruti</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>ProQuest Health & Medical Collection</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>Medical Database (Alumni Edition)</collection><collection>ProQuest Public Health Database</collection><collection>Hospital Premium Collection</collection><collection>Hospital Premium Collection (Alumni Edition)</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central</collection><collection>ProQuest One Community College</collection><collection>Health Research Premium Collection</collection><collection>Health Research Premium Collection (Alumni)</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>Health & Medical Collection (Alumni Edition)</collection><collection>PML(ProQuest Medical Library)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>MEDLINE - Academic</collection><jtitle>Pediatric research</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Kayhanian, Saeed</au><au>Young, Adam M H</au><au>Mangla, Chaitanya</au><au>Jalloh, Ibrahim</au><au>Fernandes, Helen M</au><au>Garnett, Matthew R</au><au>Hutchinson, Peter J</au><au>Agrawal, Shruti</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Modelling outcomes after paediatric brain injury with admission laboratory values: a machine-learning approach</atitle><jtitle>Pediatric research</jtitle><addtitle>Pediatr Res</addtitle><date>2019-11-01</date><risdate>2019</risdate><volume>86</volume><issue>5</issue><spage>641</spage><epage>645</epage><pages>641-645</pages><issn>0031-3998</issn><eissn>1530-0447</eissn><notes>ObjectType-Article-1</notes><notes>SourceType-Scholarly Journals-1</notes><notes>ObjectType-Feature-2</notes><notes>content type line 23</notes><abstract>Severe traumatic brain injury (TBI) is a leading cause of mortality in children, but the accurate prediction of outcomes at the point of admission remains very challenging. Admission laboratory results are a promising potential source of prognostic data, but have not been widely explored in paediatric cohorts. Herein, we use machine-learning methods to analyse 14 different serum parameters together and develop a prognostic model to predict 6-month outcomes in children with severe TBI.
A retrospective review of patients admitted to Cambridge University Hospital's Paediatric Intensive Care Unit between 2009 and 2013 with a TBI. The data for 14 admission serum parameters were recorded. Logistic regression and a support vector machine (SVM) were trained with these data against dichotimised outcomes from the recorded 6-month Glasgow Outcome Scale.
Ninety-four patients were identified. Admission levels of lactate, H+, and glucose were identified as being the most informative of 6-month outcomes. Four different models were produced. The SVM using just the three most informative parameters was the best able to predict favourable outcomes at 6 months (sensitivity = 80%, specificity = 99%).
Our results demonstrate the potential for highly accurate outcome prediction after severe paediatric TBI using admission laboratory data.</abstract><cop>United States</cop><pub>Nature Publishing Group</pub><pmid>31349360</pmid><doi>10.1038/s41390-019-0510-9</doi><tpages>5</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0031-3998 |
| ispartof | Pediatric research, 2019-11, Vol.86 (5), p.641-645 |
| issn | 0031-3998 1530-0447 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_2265739549 |
| source | Springer Link |
| subjects | Brain Injuries - therapy Child Female Humans Machine Learning Male Medical prognosis Medical tests Patient Admission Patient admissions Pediatrics Traumatic brain injury Treatment Outcome |
| title | Modelling outcomes after paediatric brain injury with admission laboratory values: a machine-learning approach |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-09-22T18%3A17%3A57IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Modelling%20outcomes%20after%20paediatric%20brain%20injury%20with%20admission%20laboratory%20values:%20a%20machine-learning%20approach&rft.jtitle=Pediatric%20research&rft.au=Kayhanian,%20Saeed&rft.date=2019-11-01&rft.volume=86&rft.issue=5&rft.spage=641&rft.epage=645&rft.pages=641-645&rft.issn=0031-3998&rft.eissn=1530-0447&rft_id=info:doi/10.1038/s41390-019-0510-9&rft_dat=%3Cproquest_cross%3E2313760448%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c372t-2267beda39833ea10972363b1893eb6cb026754f150a18626022feffc89bec213%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2313760448&rft_id=info:pmid/31349360&rfr_iscdi=true |