Predicting individual physiologically acceptable states at discharge from a pediatric intensive care unit

Predicting individual physiologically acceptable states at discharge from a pediatric intensive care unit

Quantify physiologically acceptable PICU-discharge vital signs and develop machine learning models to predict these values for individual patients throughout their PICU episode. EMR data from 7256 survivor PICU episodes (5632 patients) collected between 2009 and 2017 at Children's Hospital Los...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of the American Medical Informatics Association : JAMIA 2018-12, Vol.25 (12), p.1600-1607
Hauptverfasser: Carlin, Cameron S, Ho, Long V, Ledbetter, David R, Aczon, Melissa D, Wetzel, Randall C
Format: Artikel
Sprache:eng
Schlagworte:
Research and Applications
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 1607
container_issue 12
container_start_page 1600
container_title Journal of the American Medical Informatics Association : JAMIA
container_volume 25
creator Carlin, Cameron S
Ho, Long V
Ledbetter, David R
Aczon, Melissa D
Wetzel, Randall C
description Quantify physiologically acceptable PICU-discharge vital signs and develop machine learning models to predict these values for individual patients throughout their PICU episode. EMR data from 7256 survivor PICU episodes (5632 patients) collected between 2009 and 2017 at Children's Hospital Los Angeles was analyzed. Each episode contained 375 variables representing physiology, labs, interventions, and drugs. Between medical and physical discharge, when clinicians determined the patient was ready for ICU discharge, they were assumed to be in a physiologically acceptable state space (PASS) for discharge. Each patient's heart rate, systolic blood pressure, diastolic blood pressure in the PASS window were measured and compared to age-normal values, regression-quantified PASS predictions, and recurrent neural network (RNN) PASS predictions made 12 hours after PICU admission. Mean absolute errors (MAEs) between individual PASS values and age-normal values (HR: 21.0 bpm; SBP: 10.8 mm Hg; DBP: 10.6 mm Hg) were greater (p 
doi_str_mv 10.1093/jamia/ocy122
format Article
fullrecord <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_7647156</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2117153778</sourcerecordid><originalsourceid>FETCH-LOGICAL-c384t-fce42d80ba428cae5427cb883a9d099a693d04391699b1bc3236fa6f3c4dd4e3</originalsourceid><addsrcrecordid>eNpVkU1v1DAQhi0EoqVw44x85ECovxLHFyRUFVqpEhx64GZN7MmuKycOtrPS_nsCWyo4zUjz6JkZvYS85ewjZ0ZePsAU4DK5IxfiGTnnrdCN0erH861nnW5aJvQZeVXKA2O8E7J9Sc4kE6bVmp2T8D2jD66GeUfD7MMh-BUiXfbHElJMu-AgxiMF53CpMESkpULFQqFSH4rbQ94hHXOaKNBlU0HNwW2qinMJB6QOMtJ1DvU1eTFCLPjmsV6Q-y_X91c3zd23r7dXn-8aJ3tVm9GhEr5nAyjRO8BWCe2GvpdgPDMGOiM9U9LwzpiBD04K2Y3QjdIp7xXKC_LppF3WYULvcK4Zol1ymCAfbYJg_5_MYW936WB1pzRvu03w_lGQ088VS7XT9ifGCDOmtVjB-cZJrfsN_XBCXU6lZByf1nBmf4dj_4RjT-Fs-Lt_T3uC_6YhfwEgbJB-</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2117153778</pqid></control><display><type>article</type><title>Predicting individual physiologically acceptable states at discharge from a pediatric intensive care unit</title><source>Oxford University Press Journals All Titles (1996-Current)</source><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><source>PubMed Central</source><creator>Carlin, Cameron S ; Ho, Long V ; Ledbetter, David R ; Aczon, Melissa D ; Wetzel, Randall C</creator><creatorcontrib>Carlin, Cameron S ; Ho, Long V ; Ledbetter, David R ; Aczon, Melissa D ; Wetzel, Randall C</creatorcontrib><description>Quantify physiologically acceptable PICU-discharge vital signs and develop machine learning models to predict these values for individual patients throughout their PICU episode. EMR data from 7256 survivor PICU episodes (5632 patients) collected between 2009 and 2017 at Children's Hospital Los Angeles was analyzed. Each episode contained 375 variables representing physiology, labs, interventions, and drugs. Between medical and physical discharge, when clinicians determined the patient was ready for ICU discharge, they were assumed to be in a physiologically acceptable state space (PASS) for discharge. Each patient's heart rate, systolic blood pressure, diastolic blood pressure in the PASS window were measured and compared to age-normal values, regression-quantified PASS predictions, and recurrent neural network (RNN) PASS predictions made 12 hours after PICU admission. Mean absolute errors (MAEs) between individual PASS values and age-normal values (HR: 21.0 bpm; SBP: 10.8 mm Hg; DBP: 10.6 mm Hg) were greater (p &lt; .05) than regression prediction MAEs (HR: 15.4 bpm; SBP: 9.9 mm Hg; DBP: 8.6 mm Hg). The RNN models best approximated individual PASS values (HR: 12.3 bpm; SBP: 7.6 mm Hg; DBP: 7.0 mm Hg). The RNN model predictions better approximate patient-specific PASS values than regression and age-normal values.</description><identifier>ISSN: 1067-5027</identifier><identifier>EISSN: 1527-974X</identifier><identifier>DOI: 10.1093/jamia/ocy122</identifier><identifier>PMID: 30295770</identifier><language>eng</language><publisher>England: Oxford University Press</publisher><subject>Research and Applications</subject><ispartof>Journal of the American Medical Informatics Association : JAMIA, 2018-12, Vol.25 (12), p.1600-1607</ispartof><rights>The Author(s) 2018. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For permissions, please email: journals.permissions@oup.com 2018</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c384t-fce42d80ba428cae5427cb883a9d099a693d04391699b1bc3236fa6f3c4dd4e3</citedby><cites>FETCH-LOGICAL-c384t-fce42d80ba428cae5427cb883a9d099a693d04391699b1bc3236fa6f3c4dd4e3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC7647156/pdf/$$EPDF$$P50$$Gpubmedcentral$$H</linktopdf><linktohtml>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC7647156/$$EHTML$$P50$$Gpubmedcentral$$H</linktohtml><link.rule.ids>230,314,723,776,780,881,27901,27902,53766,53768</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/30295770$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Carlin, Cameron S</creatorcontrib><creatorcontrib>Ho, Long V</creatorcontrib><creatorcontrib>Ledbetter, David R</creatorcontrib><creatorcontrib>Aczon, Melissa D</creatorcontrib><creatorcontrib>Wetzel, Randall C</creatorcontrib><title>Predicting individual physiologically acceptable states at discharge from a pediatric intensive care unit</title><title>Journal of the American Medical Informatics Association : JAMIA</title><addtitle>J Am Med Inform Assoc</addtitle><description>Quantify physiologically acceptable PICU-discharge vital signs and develop machine learning models to predict these values for individual patients throughout their PICU episode. EMR data from 7256 survivor PICU episodes (5632 patients) collected between 2009 and 2017 at Children's Hospital Los Angeles was analyzed. Each episode contained 375 variables representing physiology, labs, interventions, and drugs. Between medical and physical discharge, when clinicians determined the patient was ready for ICU discharge, they were assumed to be in a physiologically acceptable state space (PASS) for discharge. Each patient's heart rate, systolic blood pressure, diastolic blood pressure in the PASS window were measured and compared to age-normal values, regression-quantified PASS predictions, and recurrent neural network (RNN) PASS predictions made 12 hours after PICU admission. Mean absolute errors (MAEs) between individual PASS values and age-normal values (HR: 21.0 bpm; SBP: 10.8 mm Hg; DBP: 10.6 mm Hg) were greater (p &lt; .05) than regression prediction MAEs (HR: 15.4 bpm; SBP: 9.9 mm Hg; DBP: 8.6 mm Hg). The RNN models best approximated individual PASS values (HR: 12.3 bpm; SBP: 7.6 mm Hg; DBP: 7.0 mm Hg). The RNN model predictions better approximate patient-specific PASS values than regression and age-normal values.</description><subject>Research and Applications</subject><issn>1067-5027</issn><issn>1527-974X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><recordid>eNpVkU1v1DAQhi0EoqVw44x85ECovxLHFyRUFVqpEhx64GZN7MmuKycOtrPS_nsCWyo4zUjz6JkZvYS85ewjZ0ZePsAU4DK5IxfiGTnnrdCN0erH861nnW5aJvQZeVXKA2O8E7J9Sc4kE6bVmp2T8D2jD66GeUfD7MMh-BUiXfbHElJMu-AgxiMF53CpMESkpULFQqFSH4rbQ94hHXOaKNBlU0HNwW2qinMJB6QOMtJ1DvU1eTFCLPjmsV6Q-y_X91c3zd23r7dXn-8aJ3tVm9GhEr5nAyjRO8BWCe2GvpdgPDMGOiM9U9LwzpiBD04K2Y3QjdIp7xXKC_LppF3WYULvcK4Zol1ymCAfbYJg_5_MYW936WB1pzRvu03w_lGQ088VS7XT9ifGCDOmtVjB-cZJrfsN_XBCXU6lZByf1nBmf4dj_4RjT-Fs-Lt_T3uC_6YhfwEgbJB-</recordid><startdate>20181201</startdate><enddate>20181201</enddate><creator>Carlin, Cameron S</creator><creator>Ho, Long V</creator><creator>Ledbetter, David R</creator><creator>Aczon, Melissa D</creator><creator>Wetzel, Randall C</creator><general>Oxford University Press</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><scope>5PM</scope></search><sort><creationdate>20181201</creationdate><title>Predicting individual physiologically acceptable states at discharge from a pediatric intensive care unit</title><author>Carlin, Cameron S ; Ho, Long V ; Ledbetter, David R ; Aczon, Melissa D ; Wetzel, Randall C</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c384t-fce42d80ba428cae5427cb883a9d099a693d04391699b1bc3236fa6f3c4dd4e3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2018</creationdate><topic>Research and Applications</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Carlin, Cameron S</creatorcontrib><creatorcontrib>Ho, Long V</creatorcontrib><creatorcontrib>Ledbetter, David R</creatorcontrib><creatorcontrib>Aczon, Melissa D</creatorcontrib><creatorcontrib>Wetzel, Randall C</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>Journal of the American Medical Informatics Association : JAMIA</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Carlin, Cameron S</au><au>Ho, Long V</au><au>Ledbetter, David R</au><au>Aczon, Melissa D</au><au>Wetzel, Randall C</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Predicting individual physiologically acceptable states at discharge from a pediatric intensive care unit</atitle><jtitle>Journal of the American Medical Informatics Association : JAMIA</jtitle><addtitle>J Am Med Inform Assoc</addtitle><date>2018-12-01</date><risdate>2018</risdate><volume>25</volume><issue>12</issue><spage>1600</spage><epage>1607</epage><pages>1600-1607</pages><issn>1067-5027</issn><eissn>1527-974X</eissn><abstract>Quantify physiologically acceptable PICU-discharge vital signs and develop machine learning models to predict these values for individual patients throughout their PICU episode. EMR data from 7256 survivor PICU episodes (5632 patients) collected between 2009 and 2017 at Children's Hospital Los Angeles was analyzed. Each episode contained 375 variables representing physiology, labs, interventions, and drugs. Between medical and physical discharge, when clinicians determined the patient was ready for ICU discharge, they were assumed to be in a physiologically acceptable state space (PASS) for discharge. Each patient's heart rate, systolic blood pressure, diastolic blood pressure in the PASS window were measured and compared to age-normal values, regression-quantified PASS predictions, and recurrent neural network (RNN) PASS predictions made 12 hours after PICU admission. Mean absolute errors (MAEs) between individual PASS values and age-normal values (HR: 21.0 bpm; SBP: 10.8 mm Hg; DBP: 10.6 mm Hg) were greater (p &lt; .05) than regression prediction MAEs (HR: 15.4 bpm; SBP: 9.9 mm Hg; DBP: 8.6 mm Hg). The RNN models best approximated individual PASS values (HR: 12.3 bpm; SBP: 7.6 mm Hg; DBP: 7.0 mm Hg). The RNN model predictions better approximate patient-specific PASS values than regression and age-normal values.</abstract><cop>England</cop><pub>Oxford University Press</pub><pmid>30295770</pmid><doi>10.1093/jamia/ocy122</doi><tpages>8</tpages><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 1067-5027
ispartof Journal of the American Medical Informatics Association : JAMIA, 2018-12, Vol.25 (12), p.1600-1607
issn 1067-5027
1527-974X
language eng
recordid cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_7647156
source Oxford University Press Journals All Titles (1996-Current); Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals; PubMed Central
subjects Research and Applications
title Predicting individual physiologically acceptable states at discharge from a pediatric intensive care unit
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-31T15%3A03%3A58IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Predicting%20individual%20physiologically%20acceptable%20states%20at%20discharge%20from%20a%20pediatric%20intensive%20care%20unit&rft.jtitle=Journal%20of%20the%20American%20Medical%20Informatics%20Association%20:%20JAMIA&rft.au=Carlin,%20Cameron%20S&rft.date=2018-12-01&rft.volume=25&rft.issue=12&rft.spage=1600&rft.epage=1607&rft.pages=1600-1607&rft.issn=1067-5027&rft.eissn=1527-974X&rft_id=info:doi/10.1093/jamia/ocy122&rft_dat=%3Cproquest_pubme%3E2117153778%3C/proquest_pubme%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2117153778&rft_id=info:pmid/30295770&rfr_iscdi=true