Random forest machine learning method outperforms prehospital National Early Warning Score for predicting one-day mortality: A retrospective study

The National Early Warning Score (NEWS) is a validated method for predicting clinical deterioration in hospital wards, but its performance in prehospital settings remains controversial. Modern machine learning models may outperform traditional statistical analyses for predicting short-term mortality...

Full description

Saved in:
Bibliographic Details
Published in:Resuscitation plus Vol. 4; p. 100046
Main Authors: Pirneskoski, Jussi, Tamminen, Joonas, Kallonen, Antti, Nurmi, Jouni, Kuisma, Markku, Olkkola, Klaus T., Hoppu, Sanna
Format: Journal Article
Language:English
Published: Netherlands Elsevier B.V 01.12.2020
Elsevier
Subjects:
ISSN:2666-5204, 2666-5204
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract The National Early Warning Score (NEWS) is a validated method for predicting clinical deterioration in hospital wards, but its performance in prehospital settings remains controversial. Modern machine learning models may outperform traditional statistical analyses for predicting short-term mortality. Thus, we aimed to compare the mortality prediction accuracy of NEWS and random forest machine learning using prehospital vital signs. In this retrospective study, all electronic ambulance mission reports between 2008 and 2015 in a single EMS system were collected. Adult patients (≥ 18 years) were included in the analysis. Random forest models with and without blood glucose were compared to the traditional NEWS for predicting one-day mortality. A ten-fold cross-validation method was applied to train and validate the random forest models. A total of 26,458 patients were included in the study of whom 278 (1.0%) died within one day of ambulance mission. The area under the receiver operating characteristic curve for one-day mortality was 0.836 (95% CI, 0.810−0.860) for NEWS, 0.858 (95% CI, 0.832−0.883) for a random forest trained with NEWS variables only and 0.868 (0.843−0.892) for a random forest trained with NEWS variables and blood glucose. A random forest algorithm trained with NEWS variables was superior to traditional NEWS for predicting one-day mortality in adult prehospital patients, although the risk of selection bias must be acknowledged. The inclusion of blood glucose in the model further improved its predictive performance.
AbstractList The National Early Warning Score (NEWS) is a validated method for predicting clinical deterioration in hospital wards, but its performance in prehospital settings remains controversial. Modern machine learning models may outperform traditional statistical analyses for predicting short-term mortality. Thus, we aimed to compare the mortality prediction accuracy of NEWS and random forest machine learning using prehospital vital signs. In this retrospective study, all electronic ambulance mission reports between 2008 and 2015 in a single EMS system were collected. Adult patients (≥ 18 years) were included in the analysis. Random forest models with and without blood glucose were compared to the traditional NEWS for predicting one-day mortality. A ten-fold cross-validation method was applied to train and validate the random forest models. A total of 26,458 patients were included in the study of whom 278 (1.0%) died within one day of ambulance mission. The area under the receiver operating characteristic curve for one-day mortality was 0.836 (95% CI, 0.810−0.860) for NEWS, 0.858 (95% CI, 0.832−0.883) for a random forest trained with NEWS variables only and 0.868 (0.843−0.892) for a random forest trained with NEWS variables and blood glucose. A random forest algorithm trained with NEWS variables was superior to traditional NEWS for predicting one-day mortality in adult prehospital patients, although the risk of selection bias must be acknowledged. The inclusion of blood glucose in the model further improved its predictive performance.
AbstractAim of the studyThe National Early Warning Score (NEWS) is a validated method for predicting clinical deterioration in hospital wards, but its performance in prehospital settings remains controversial. Modern machine learning models may outperform traditional statistical analyses for predicting short-term mortality. Thus, we aimed to compare the mortality prediction accuracy of NEWS and random forest machine learning using prehospital vital signs. MethodsIn this retrospective study, all electronic ambulance mission reports between 2008 and 2015 in a single EMS system were collected. Adult patients (≥ 18 years) were included in the analysis. Random forest models with and without blood glucose were compared to the traditional NEWS for predicting one-day mortality. A ten-fold cross-validation method was applied to train and validate the random forest models. ResultsA total of 26,458 patients were included in the study of whom 278 (1.0%) died within one day of ambulance mission. The area under the receiver operating characteristic curve for one-day mortality was 0.836 (95% CI, 0.810−0.860) for NEWS, 0.858 (95% CI, 0.832−0.883) for a random forest trained with NEWS variables only and 0.868 (0.843−0.892) for a random forest trained with NEWS variables and blood glucose. ConclusionA random forest algorithm trained with NEWS variables was superior to traditional NEWS for predicting one-day mortality in adult prehospital patients, although the risk of selection bias must be acknowledged. The inclusion of blood glucose in the model further improved its predictive performance.
The National Early Warning Score (NEWS) is a validated method for predicting clinical deterioration in hospital wards, but its performance in prehospital settings remains controversial. Modern machine learning models may outperform traditional statistical analyses for predicting short-term mortality. Thus, we aimed to compare the mortality prediction accuracy of NEWS and random forest machine learning using prehospital vital signs.AIM OF THE STUDYThe National Early Warning Score (NEWS) is a validated method for predicting clinical deterioration in hospital wards, but its performance in prehospital settings remains controversial. Modern machine learning models may outperform traditional statistical analyses for predicting short-term mortality. Thus, we aimed to compare the mortality prediction accuracy of NEWS and random forest machine learning using prehospital vital signs.In this retrospective study, all electronic ambulance mission reports between 2008 and 2015 in a single EMS system were collected. Adult patients (≥ 18 years) were included in the analysis. Random forest models with and without blood glucose were compared to the traditional NEWS for predicting one-day mortality. A ten-fold cross-validation method was applied to train and validate the random forest models.METHODSIn this retrospective study, all electronic ambulance mission reports between 2008 and 2015 in a single EMS system were collected. Adult patients (≥ 18 years) were included in the analysis. Random forest models with and without blood glucose were compared to the traditional NEWS for predicting one-day mortality. A ten-fold cross-validation method was applied to train and validate the random forest models.A total of 26,458 patients were included in the study of whom 278 (1.0%) died within one day of ambulance mission. The area under the receiver operating characteristic curve for one-day mortality was 0.836 (95% CI, 0.810-0.860) for NEWS, 0.858 (95% CI, 0.832-0.883) for a random forest trained with NEWS variables only and 0.868 (0.843-0.892) for a random forest trained with NEWS variables and blood glucose.RESULTSA total of 26,458 patients were included in the study of whom 278 (1.0%) died within one day of ambulance mission. The area under the receiver operating characteristic curve for one-day mortality was 0.836 (95% CI, 0.810-0.860) for NEWS, 0.858 (95% CI, 0.832-0.883) for a random forest trained with NEWS variables only and 0.868 (0.843-0.892) for a random forest trained with NEWS variables and blood glucose.A random forest algorithm trained with NEWS variables was superior to traditional NEWS for predicting one-day mortality in adult prehospital patients, although the risk of selection bias must be acknowledged. The inclusion of blood glucose in the model further improved its predictive performance.CONCLUSIONA random forest algorithm trained with NEWS variables was superior to traditional NEWS for predicting one-day mortality in adult prehospital patients, although the risk of selection bias must be acknowledged. The inclusion of blood glucose in the model further improved its predictive performance.
The National Early Warning Score (NEWS) is a validated method for predicting clinical deterioration in hospital wards, but its performance in prehospital settings remains controversial. Modern machine learning models may outperform traditional statistical analyses for predicting short-term mortality. Thus, we aimed to compare the mortality prediction accuracy of NEWS and random forest machine learning using prehospital vital signs. In this retrospective study, all electronic ambulance mission reports between 2008 and 2015 in a single EMS system were collected. Adult patients (≥ 18 years) were included in the analysis. Random forest models with and without blood glucose were compared to the traditional NEWS for predicting one-day mortality. A ten-fold cross-validation method was applied to train and validate the random forest models. A total of 26,458 patients were included in the study of whom 278 (1.0%) died within one day of ambulance mission. The area under the receiver operating characteristic curve for one-day mortality was 0.836 (95% CI, 0.810-0.860) for NEWS, 0.858 (95% CI, 0.832-0.883) for a random forest trained with NEWS variables only and 0.868 (0.843-0.892) for a random forest trained with NEWS variables and blood glucose. A random forest algorithm trained with NEWS variables was superior to traditional NEWS for predicting one-day mortality in adult prehospital patients, although the risk of selection bias must be acknowledged. The inclusion of blood glucose in the model further improved its predictive performance.
Aim of the study: The National Early Warning Score (NEWS) is a validated method for predicting clinical deterioration in hospital wards, but its performance in prehospital settings remains controversial. Modern machine learning models may outperform traditional statistical analyses for predicting short-term mortality. Thus, we aimed to compare the mortality prediction accuracy of NEWS and random forest machine learning using prehospital vital signs. Methods: In this retrospective study, all electronic ambulance mission reports between 2008 and 2015 in a single EMS system were collected. Adult patients (≥ 18 years) were included in the analysis. Random forest models with and without blood glucose were compared to the traditional NEWS for predicting one-day mortality. A ten-fold cross-validation method was applied to train and validate the random forest models. Results: A total of 26,458 patients were included in the study of whom 278 (1.0%) died within one day of ambulance mission. The area under the receiver operating characteristic curve for one-day mortality was 0.836 (95% CI, 0.810−0.860) for NEWS, 0.858 (95% CI, 0.832−0.883) for a random forest trained with NEWS variables only and 0.868 (0.843−0.892) for a random forest trained with NEWS variables and blood glucose. Conclusion: A random forest algorithm trained with NEWS variables was superior to traditional NEWS for predicting one-day mortality in adult prehospital patients, although the risk of selection bias must be acknowledged. The inclusion of blood glucose in the model further improved its predictive performance.
ArticleNumber 100046
Author Kallonen, Antti
Kuisma, Markku
Tamminen, Joonas
Hoppu, Sanna
Nurmi, Jouni
Olkkola, Klaus T.
Pirneskoski, Jussi
Author_xml – sequence: 1
  givenname: Jussi
  orcidid: 0000-0001-9248-2235
  surname: Pirneskoski
  fullname: Pirneskoski, Jussi
  email: jussi.pirneskoski@helsinki.fi
  organization: Department of Emergency Medicine and Services, University of Helsinki and HUS Helsinki University Hospital, Helsinki, Finland
– sequence: 2
  givenname: Joonas
  surname: Tamminen
  fullname: Tamminen, Joonas
  organization: Faculty of Medicine and Health Technology, Tampere University, Tampere, Finland
– sequence: 3
  givenname: Antti
  surname: Kallonen
  fullname: Kallonen, Antti
  organization: Faculty of Medicine and Health Technology, Tampere University, Tampere, Finland
– sequence: 4
  givenname: Jouni
  surname: Nurmi
  fullname: Nurmi, Jouni
  organization: Department of Emergency Medicine and Services, University of Helsinki and HUS Helsinki University Hospital, Helsinki, Finland
– sequence: 5
  givenname: Markku
  surname: Kuisma
  fullname: Kuisma, Markku
  organization: Department of Emergency Medicine and Services, University of Helsinki and HUS Helsinki University Hospital, Helsinki, Finland
– sequence: 6
  givenname: Klaus T.
  orcidid: 0000-0001-7872-8665
  surname: Olkkola
  fullname: Olkkola, Klaus T.
  organization: Department of Anaesthesiology, Intensive Care and Pain Medicine, University of Helsinki and HUS Helsinki University Hospital, Helsinki, Finland
– sequence: 7
  givenname: Sanna
  surname: Hoppu
  fullname: Hoppu, Sanna
  organization: Emergency Medical Services, Tampere University Hospital, Tampere, Finland
BackLink https://www.ncbi.nlm.nih.gov/pubmed/34223321$$D View this record in MEDLINE/PubMed
BookMark eNqVkl9rFDEUxQep2Fr7DUTy6Muu-TeZmSJCKVULRcEqPoZM5s5u1kyyTTKF-Rp-YjPuVlpBik8TMuf8LrnnPC8OnHdQFC8JXhJMxJvNMkDc2nFJMZ2vMObiSXFEhRCLkmJ-cO98WJzEuMkSWhLKSfWsOGScUsYoOSp-flGu8wPqfQYmNCi9Ng6QBRWccSs0QFr7DvkxbSFk0RDRNsDax61JyqJPKhnv8uFCBTuh73vXtc64mTmLO6PTfJlfsOjUhAYfstWk6RSdoQApZBhkyS2gmMZuelE87ZWNcLL_Hhff3l98Pf-4uPr84fL87GqhK8zSQpctVBXrKqhESbnmqu4V5UBYI_qaVrQGXApKRNl3HalbmqWsaUvRAFONqthxcbnjdl5t5DaYQYVJemXk7wsfVlKFZLQFKWjDRN0SQUXNSYObsoSmb3hVt6Ch6jPr3Y61HdsBOg0uBWUfQB_-cWYtV_5W1pRzzngGvN4Dgr8ZcxRyMFGDtcqBH6OkJa8FqUlVZumr-7P-DLkLNQtOdwKdVxsD9FLnsOag8mhjJcFyLpHcyF2J5FwiuStRNvO_zHf8R2z7BUBO7NZAkFEbcDqnH3K4eaXmfwHaGme0sj9ggrjxY8g9i5LISCWW13O953ZTzGb__Oq3_wY8Pv8X9MQOsQ
CitedBy_id crossref_primary_10_1016_j_saa_2025_126823
crossref_primary_10_31965_infokes_Vol21_Iss4_1105
crossref_primary_10_1016_j_ejim_2025_04_035
crossref_primary_10_1038_s41598_025_08247_0
crossref_primary_10_1016_j_measurement_2022_111403
crossref_primary_10_1177_20552076231152164
crossref_primary_10_1186_s40001_022_00843_4
crossref_primary_10_3390_knowledge2030021
crossref_primary_10_1016_j_ijmedinf_2023_105274
crossref_primary_10_1089_cyber_2022_0367
crossref_primary_10_1186_s40359_024_01566_3
crossref_primary_10_1038_s41598_022_26167_1
crossref_primary_10_3390_diagnostics15172258
crossref_primary_10_1186_s12873_024_01166_9
Cites_doi 10.1016/j.amsu.2018.01.006
10.1016/j.resuscitation.2012.12.016
10.1017/S1049023X19005041
10.1016/j.ijmedinf.2019.02.002
10.1016/j.annemergmed.2017.08.005
10.1186/s13054-019-2351-7
10.1371/journal.pone.0201016
10.1097/CCM.0000000000001571
10.1023/A:1010933404324
10.1016/j.resuscitation.2018.08.028
10.1136/emermed-2018-208309
10.1111/aas.13310
10.1016/j.resuscitation.2014.12.029
10.1136/emermed-2016-206115
10.1097/CCM.0000000000003891
10.1371/journal.pone.0226518
10.1056/NEJMra1814259
ContentType Journal Article
Copyright 2020 The Author(s)
The Author(s)
2020 The Author(s).
2020 The Author(s) 2020
Copyright_xml – notice: 2020 The Author(s)
– notice: The Author(s)
– notice: 2020 The Author(s).
– notice: 2020 The Author(s) 2020
DBID 6I.
AAFTH
AAYXX
CITATION
NPM
7X8
5PM
DOA
DOI 10.1016/j.resplu.2020.100046
DatabaseName ScienceDirect Open Access Titles
Elsevier:ScienceDirect:Open Access
CrossRef
PubMed
MEDLINE - Academic
PubMed Central (Full Participant titles)
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
PubMed
MEDLINE - Academic
DatabaseTitleList

MEDLINE - Academic
PubMed


Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 3
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
EISSN 2666-5204
EndPage 100046
ExternalDocumentID oai_doaj_org_article_629368b162684190955e9f9478bece7f
PMC8244434
34223321
10_1016_j_resplu_2020_100046
S2666520420300461
1_s2_0_S2666520420300461
Genre Journal Article
GroupedDBID .1-
.FO
0R~
1P~
53G
AAEDW
AALRI
AAXUO
AAYWO
ACVFH
ADCNI
ADVLN
AEUPX
AFJKZ
AFPUW
AFRHN
AIGII
AITUG
AJUYK
AKBMS
AKRWK
AKYEP
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
APXCP
EBS
FDB
GROUPED_DOAJ
M41
M~E
OK1
ROL
RPM
Z5R
AAHOK
AFCTW
6I.
AAFTH
AAYXX
CITATION
NPM
7X8
5PM
ID FETCH-LOGICAL-c703t-c5be773d7e76524c4a8fa24e1396f82728e0562165fdd18b23d739b569e3a9a73
IEDL.DBID DOA
ISICitedReferencesCount 14
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000675511000019&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2666-5204
IngestDate Fri Oct 03 12:51:23 EDT 2025
Thu Aug 21 13:38:18 EDT 2025
Thu Oct 02 06:25:05 EDT 2025
Wed Feb 19 02:25:28 EST 2025
Thu Nov 20 00:56:00 EST 2025
Tue Nov 18 21:01:11 EST 2025
Tue Jul 25 21:01:06 EDT 2023
Sun Feb 23 10:19:27 EST 2025
Tue Aug 26 18:20:55 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords Early warning score
Cardiac arrest prevention
NEWS
Machine learning
Random forest
National Early Warning Score
Emergency medical services
Prehospital
Language English
License This is an open access article under the CC BY license.
2020 The Author(s).
This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c703t-c5be773d7e76524c4a8fa24e1396f82728e0562165fdd18b23d739b569e3a9a73
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
Equal contribution.
ORCID 0000-0001-9248-2235
0000-0001-7872-8665
OpenAccessLink https://doaj.org/article/629368b162684190955e9f9478bece7f
PMID 34223321
PQID 2548618175
PQPubID 23479
PageCount 1
ParticipantIDs doaj_primary_oai_doaj_org_article_629368b162684190955e9f9478bece7f
pubmedcentral_primary_oai_pubmedcentral_nih_gov_8244434
proquest_miscellaneous_2548618175
pubmed_primary_34223321
crossref_citationtrail_10_1016_j_resplu_2020_100046
crossref_primary_10_1016_j_resplu_2020_100046
elsevier_sciencedirect_doi_10_1016_j_resplu_2020_100046
elsevier_clinicalkeyesjournals_1_s2_0_S2666520420300461
elsevier_clinicalkey_doi_10_1016_j_resplu_2020_100046
PublicationCentury 2000
PublicationDate 2020-12-01
PublicationDateYYYYMMDD 2020-12-01
PublicationDate_xml – month: 12
  year: 2020
  text: 2020-12-01
  day: 01
PublicationDecade 2020
PublicationPlace Netherlands
PublicationPlace_xml – name: Netherlands
PublicationTitle Resuscitation plus
PublicationTitleAlternate Resusc Plus
PublicationYear 2020
Publisher Elsevier B.V
Elsevier
Publisher_xml – name: Elsevier B.V
– name: Elsevier
References Giannini, Ginestra, Chivers (bib0060) 2019; 47
Spangler, Hermansson, Smekal, Blomberg (bib0065) 2019; 14
Lin, Hu, Kong (bib0080) 2019; 125
Silcock, Corfield, Gowens, Rooney (bib0015) 2015; 89
Martín-Rodríguez, López-Izquierdo, del Vegas (bib0035) 2019; 34
Hong, Haimovich, Taylor (bib0050) 2018; 13
Patel, Nugawela, Edwards (bib0040) 2018; 132
Levin, Toerper, Hamrock (bib0055) 2017; 71
Pirneskoski, Kuisma, Olkkola, Nurmi (bib0030) 2019; 63
Churpek, Yuen, Winslow, Meltzer, Kattan, Edelson (bib0075) 2016; 44
Breiman (bib0085) 2001; 45
Smith, Prytherch, Meredith, Schmidt, Featherstone (bib0010) 2013; 84
Rajkomar, Dean, Kohane (bib0090) 2019; 380
Raita, Goto, Faridi, Brown, Camargo, Hasegawa (bib0045) 2019; 23
Vihonen, Lääperi, Kuisma, Pirneskoski, Nurmi (bib0070) 2020; 37
Abbott, Cron, Vaid, Ip, Torrance, Emmanuel (bib0025) 2018; 27
Shaw, Fothergill, Clark, Moore (bib0020) 2017; 34
Royal College of Physicians (bib0005) 2012
Silcock (10.1016/j.resplu.2020.100046_bib0015) 2015; 89
Lin (10.1016/j.resplu.2020.100046_bib0080) 2019; 125
Breiman (10.1016/j.resplu.2020.100046_bib0085) 2001; 45
Smith (10.1016/j.resplu.2020.100046_bib0010) 2013; 84
Abbott (10.1016/j.resplu.2020.100046_bib0025) 2018; 27
Shaw (10.1016/j.resplu.2020.100046_bib0020) 2017; 34
Levin (10.1016/j.resplu.2020.100046_bib0055) 2017; 71
Rajkomar (10.1016/j.resplu.2020.100046_bib0090) 2019; 380
Royal College of Physicians (10.1016/j.resplu.2020.100046_bib0005) 2012
Martín-Rodríguez (10.1016/j.resplu.2020.100046_bib0035) 2019; 34
Hong (10.1016/j.resplu.2020.100046_bib0050) 2018; 13
Churpek (10.1016/j.resplu.2020.100046_bib0075) 2016; 44
Giannini (10.1016/j.resplu.2020.100046_bib0060) 2019; 47
Patel (10.1016/j.resplu.2020.100046_bib0040) 2018; 132
Raita (10.1016/j.resplu.2020.100046_bib0045) 2019; 23
Vihonen (10.1016/j.resplu.2020.100046_bib0070) 2020; 37
Spangler (10.1016/j.resplu.2020.100046_bib0065) 2019; 14
Pirneskoski (10.1016/j.resplu.2020.100046_bib0030) 2019; 63
References_xml – year: 2012
  ident: bib0005
  article-title: National Early Warning Score (NEWS): Standardising the assessment of acute-illness severity in the NHS. Report of a working party
– volume: 34
  start-page: 1
  year: 2019
  end-page: 9
  ident: bib0035
  article-title: Accuracy of National Early Warning Score 2 (NEWS2) in prehospital triage on in-hospital early mortality: a multi-center observational prospective cohort study
  publication-title: Prehosp Disaster Med
– volume: 47
  start-page: 1485
  year: 2019
  end-page: 1492
  ident: bib0060
  article-title: A machine learning algorithm to predict severe sepsis and septic shock: development, implementation, and impact on clinical practice
  publication-title: Crit Care Med
– volume: 125
  start-page: 55
  year: 2019
  end-page: 61
  ident: bib0080
  article-title: Predicting in-hospital mortality of patients with acute kidney injury in the ICU using random forest model
  publication-title: Int J Med Inform
– volume: 89
  start-page: 31
  year: 2015
  end-page: 35
  ident: bib0015
  article-title: Validation of the National Early Warning Score in the prehospital setting
  publication-title: Resuscitation
– volume: 44
  start-page: 368
  year: 2016
  end-page: 374
  ident: bib0075
  article-title: Multicenter comparison of machine learning methods and conventional regression for predicting clinical deterioration on the wards
  publication-title: Crit Care Med
– volume: 63
  start-page: 676
  year: 2019
  end-page: 683
  ident: bib0030
  article-title: Prehospital National Early Warning Score predicts early mortality
  publication-title: Acta Anaesth Scand
– volume: 27
  start-page: 17
  year: 2018
  end-page: 21
  ident: bib0025
  article-title: Pre-hospital National Early Warning Score (NEWS) is associated with in-hospital mortality and critical care unit admission: a cohort study
  publication-title: Ann Med Surg
– volume: 23
  start-page: 64
  year: 2019
  ident: bib0045
  article-title: Emergency department triage prediction of clinical outcomes using machine learning models
  publication-title: Crit Care
– volume: 71
  start-page: 565
  year: 2017
  end-page: 574
  ident: bib0055
  article-title: Machine-learning-based electronic triage more accurately differentiates patients with respect to clinical outcomes compared with the Emergency Severity Index
  publication-title: Ann Emerg Med
– volume: 45
  start-page: 5
  year: 2001
  end-page: 32
  ident: bib0085
  article-title: Random forests
  publication-title: Mach Learn
– volume: 37
  start-page: 286
  year: 2020
  end-page: 292
  ident: bib0070
  article-title: Glucose as an additional parameter to National Early Warning Score (NEWS) in prehospital setting enhances identification of patients at risk of death: an observational cohort study
  publication-title: Emerg Med J
– volume: 34
  start-page: 533
  year: 2017
  end-page: 537
  ident: bib0020
  article-title: Can the prehospital National Early Warning Score identify patients most at risk from subsequent deterioration?
  publication-title: Emerg Med J
– volume: 13
  start-page: e0201016
  year: 2018
  ident: bib0050
  article-title: Predicting hospital admission at emergency department triage using machine learning
  publication-title: PLoS One
– volume: 14
  year: 2019
  ident: bib0065
  article-title: A validation of machine learning-based risk scores in the prehospital setting
  publication-title: PLoS One
– volume: 380
  start-page: 1347
  year: 2019
  end-page: 1358
  ident: bib0090
  article-title: Machine learning in medicine
  publication-title: NEJM
– volume: 132
  start-page: 101
  year: 2018
  end-page: 111
  ident: bib0040
  article-title: Can early warning scores identify deteriorating patients in pre-hospital settings? A systematic review
  publication-title: Resuscitation
– volume: 84
  start-page: 465
  year: 2013
  end-page: 470
  ident: bib0010
  article-title: The ability of the National Early Warning Score (NEWS) to discriminate patients at risk of early cardiac arrest, unanticipated intensive care unit admission, and death
  publication-title: Resuscitation
– volume: 27
  start-page: 17
  year: 2018
  ident: 10.1016/j.resplu.2020.100046_bib0025
  article-title: Pre-hospital National Early Warning Score (NEWS) is associated with in-hospital mortality and critical care unit admission: a cohort study
  publication-title: Ann Med Surg
  doi: 10.1016/j.amsu.2018.01.006
– volume: 84
  start-page: 465
  year: 2013
  ident: 10.1016/j.resplu.2020.100046_bib0010
  article-title: The ability of the National Early Warning Score (NEWS) to discriminate patients at risk of early cardiac arrest, unanticipated intensive care unit admission, and death
  publication-title: Resuscitation
  doi: 10.1016/j.resuscitation.2012.12.016
– volume: 34
  start-page: 1
  year: 2019
  ident: 10.1016/j.resplu.2020.100046_bib0035
  article-title: Accuracy of National Early Warning Score 2 (NEWS2) in prehospital triage on in-hospital early mortality: a multi-center observational prospective cohort study
  publication-title: Prehosp Disaster Med
  doi: 10.1017/S1049023X19005041
– volume: 125
  start-page: 55
  year: 2019
  ident: 10.1016/j.resplu.2020.100046_bib0080
  article-title: Predicting in-hospital mortality of patients with acute kidney injury in the ICU using random forest model
  publication-title: Int J Med Inform
  doi: 10.1016/j.ijmedinf.2019.02.002
– volume: 71
  start-page: 565
  year: 2017
  ident: 10.1016/j.resplu.2020.100046_bib0055
  article-title: Machine-learning-based electronic triage more accurately differentiates patients with respect to clinical outcomes compared with the Emergency Severity Index
  publication-title: Ann Emerg Med
  doi: 10.1016/j.annemergmed.2017.08.005
– volume: 23
  start-page: 64
  year: 2019
  ident: 10.1016/j.resplu.2020.100046_bib0045
  article-title: Emergency department triage prediction of clinical outcomes using machine learning models
  publication-title: Crit Care
  doi: 10.1186/s13054-019-2351-7
– volume: 13
  start-page: e0201016
  year: 2018
  ident: 10.1016/j.resplu.2020.100046_bib0050
  article-title: Predicting hospital admission at emergency department triage using machine learning
  publication-title: PLoS One
  doi: 10.1371/journal.pone.0201016
– volume: 44
  start-page: 368
  year: 2016
  ident: 10.1016/j.resplu.2020.100046_bib0075
  article-title: Multicenter comparison of machine learning methods and conventional regression for predicting clinical deterioration on the wards
  publication-title: Crit Care Med
  doi: 10.1097/CCM.0000000000001571
– year: 2012
  ident: 10.1016/j.resplu.2020.100046_bib0005
– volume: 45
  start-page: 5
  year: 2001
  ident: 10.1016/j.resplu.2020.100046_bib0085
  article-title: Random forests
  publication-title: Mach Learn
  doi: 10.1023/A:1010933404324
– volume: 132
  start-page: 101
  year: 2018
  ident: 10.1016/j.resplu.2020.100046_bib0040
  article-title: Can early warning scores identify deteriorating patients in pre-hospital settings? A systematic review
  publication-title: Resuscitation
  doi: 10.1016/j.resuscitation.2018.08.028
– volume: 37
  start-page: 286
  year: 2020
  ident: 10.1016/j.resplu.2020.100046_bib0070
  article-title: Glucose as an additional parameter to National Early Warning Score (NEWS) in prehospital setting enhances identification of patients at risk of death: an observational cohort study
  publication-title: Emerg Med J
  doi: 10.1136/emermed-2018-208309
– volume: 63
  start-page: 676
  year: 2019
  ident: 10.1016/j.resplu.2020.100046_bib0030
  article-title: Prehospital National Early Warning Score predicts early mortality
  publication-title: Acta Anaesth Scand
  doi: 10.1111/aas.13310
– volume: 89
  start-page: 31
  year: 2015
  ident: 10.1016/j.resplu.2020.100046_bib0015
  article-title: Validation of the National Early Warning Score in the prehospital setting
  publication-title: Resuscitation
  doi: 10.1016/j.resuscitation.2014.12.029
– volume: 34
  start-page: 533
  year: 2017
  ident: 10.1016/j.resplu.2020.100046_bib0020
  article-title: Can the prehospital National Early Warning Score identify patients most at risk from subsequent deterioration?
  publication-title: Emerg Med J
  doi: 10.1136/emermed-2016-206115
– volume: 47
  start-page: 1485
  year: 2019
  ident: 10.1016/j.resplu.2020.100046_bib0060
  article-title: A machine learning algorithm to predict severe sepsis and septic shock: development, implementation, and impact on clinical practice
  publication-title: Crit Care Med
  doi: 10.1097/CCM.0000000000003891
– volume: 14
  year: 2019
  ident: 10.1016/j.resplu.2020.100046_bib0065
  article-title: A validation of machine learning-based risk scores in the prehospital setting
  publication-title: PLoS One
  doi: 10.1371/journal.pone.0226518
– volume: 380
  start-page: 1347
  year: 2019
  ident: 10.1016/j.resplu.2020.100046_bib0090
  article-title: Machine learning in medicine
  publication-title: NEJM
  doi: 10.1056/NEJMra1814259
SSID ssj0002512417
Score 2.2306955
Snippet The National Early Warning Score (NEWS) is a validated method for predicting clinical deterioration in hospital wards, but its performance in prehospital...
AbstractAim of the studyThe National Early Warning Score (NEWS) is a validated method for predicting clinical deterioration in hospital wards, but its...
Aim of the study: The National Early Warning Score (NEWS) is a validated method for predicting clinical deterioration in hospital wards, but its performance in...
SourceID doaj
pubmedcentral
proquest
pubmed
crossref
elsevier
SourceType Open Website
Open Access Repository
Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 100046
SubjectTerms Cardiac arrest prevention
Clinical Paper
Early warning score
Emergency
Emergency medical services
Machine learning
National Early Warning Score
NEWS
Prehospital
Random forest
Title Random forest machine learning method outperforms prehospital National Early Warning Score for predicting one-day mortality: A retrospective study
URI https://www.clinicalkey.com/#!/content/1-s2.0-S2666520420300461
https://www.clinicalkey.es/playcontent/1-s2.0-S2666520420300461
https://dx.doi.org/10.1016/j.resplu.2020.100046
https://www.ncbi.nlm.nih.gov/pubmed/34223321
https://www.proquest.com/docview/2548618175
https://pubmed.ncbi.nlm.nih.gov/PMC8244434
https://doaj.org/article/629368b162684190955e9f9478bece7f
Volume 4
WOSCitedRecordID wos000675511000019&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2666-5204
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002512417
  issn: 2666-5204
  databaseCode: DOA
  dateStart: 20200101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2666-5204
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002512417
  issn: 2666-5204
  databaseCode: M~E
  dateStart: 20200101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lj9MwELZghRAXxJvyWBmJa0Ti-BVuC9oVl10hFkRvVhI7bFGbVkmKxIUfwS9mxnaqFJDKgUsPqR-JZzLzjTLzDSEv60bUtQUJlAWvEt7oLKmElQkgJOUagAip077ZhLq40PN58X7S6gtzwgI9cDi4VxL8kdRVJpGWBLxXIYQrmoIrDbs71aD1BdQzCabQBqPX5r7dLjggCdFWyse6OZ_cBaHsZrmF8JD5PIEU8e_EL3n6_j339Cf8_D2LcuKWzu6Q2xFP0pPwHHfJNdfeIzfP4xfz--Tnh7K16xUFbArL0pXPnXQ0Nov4QkMHabreDptQQtDTTeeuYjcRGmmzl9QTIdPPcdYlkl_imjjYYlUJXFy3LrHld7ryiB7Q_Wt6Qjs3dOuxnJN6MtsH5NPZ6ce375LYhyGpwR4MSS0qp1RulVNSMF7zUjcl4w7Ao2w0U0w7hFGZFI21ma4YDM2LSsjC5WVRqvwhOWrhHh4TyrkVYNayotI1zzUIEeBJYV2jKyEAnMxIPkrB1JGkHHtlLM2YjfbVBNkZlJ0JspuRZDdrE0g6Dox_gwLejUWKbX8BFM9ExTOHFG9GxKgeZqxiBbsLCy0ObK7-Ns_10Xj0JjM9M6m5RNVFzWUp0qLJbDoz4qOAe_5hzxej_howH_hNqGzdetsbBhGrBJSnxIw8Cvq8O5acg3Byhvvuafreue3_0y6uPEW5BtTIc_7kfxz0U3ILHyXkED0jR0O3dc_JjfrbsOi7Y3JdzfWxf_vh9_zH6S89y17y
linkProvider Directory of Open Access Journals
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Random+forest+machine+learning+method+outperforms+prehospital+National+Early+Warning+Score+for+predicting+one-day+mortality%3A+A+retrospective+study&rft.jtitle=Resuscitation+plus&rft.au=Pirneskoski%2C+Jussi&rft.au=Tamminen%2C+Joonas&rft.au=Kallonen%2C+Antti&rft.au=Nurmi%2C+Jouni&rft.date=2020-12-01&rft.issn=2666-5204&rft.eissn=2666-5204&rft.volume=4&rft.spage=100046&rft.epage=100046&rft_id=info:doi/10.1016%2Fj.resplu.2020.100046&rft.externalDBID=ECK1-s2.0-S2666520420300461&rft.externalDocID=1_s2_0_S2666520420300461
thumbnail_m http://cvtisr.summon.serialssolutions.com/2.0.0/image/custom?url=https%3A%2F%2Fcdn.clinicalkey.com%2Fck-thumbnails%2F26665204%2FS2666520420X0004X%2Fcov150h.gif