Artificial intelligence sepsis prediction algorithm learns to say “I don’t know”

Sepsis is a leading cause of morbidity and mortality worldwide. Early identification of sepsis is important as it allows timely administration of potentially life-saving resuscitation and antimicrobial therapy. We present COMPOSER (COnformal Multidimensional Prediction Of SEpsis Risk), a deep learni...

Full description

Saved in:
Bibliographic Details
Published inNPJ digital medicine Vol. 4; no. 1; p. 134
Main Authors Shashikumar, Supreeth P., Wardi, Gabriel, Malhotra, Atul, Nemati, Shamim
Format Journal Article
LanguageEnglish
Published London Nature Publishing Group UK 09.09.2021
Nature Publishing Group
Nature Portfolio
Subjects
Online AccessGet full text

Cover

Loading…
Abstract Sepsis is a leading cause of morbidity and mortality worldwide. Early identification of sepsis is important as it allows timely administration of potentially life-saving resuscitation and antimicrobial therapy. We present COMPOSER (COnformal Multidimensional Prediction Of SEpsis Risk), a deep learning model for the early prediction of sepsis, specifically designed to reduce false alarms by detecting unfamiliar patients/situations arising from erroneous data, missingness, distributional shift and data drifts. COMPOSER flags these unfamiliar cases as indeterminate rather than making spurious predictions. Six patient cohorts (515,720 patients) curated from two healthcare systems in the United States across intensive care units (ICU) and emergency departments (ED) were used to train and externally and temporally validate this model. In a sequential prediction setting, COMPOSER achieved a consistently high area under the curve (AUC) (ICU: 0.925–0.953; ED: 0.938–0.945). Out of over 6 million prediction windows roughly 20% and 8% were identified as indeterminate amongst non-septic and septic patients, respectively. COMPOSER provided early warning within a clinically actionable timeframe (ICU: 12.2 [3.2 22.8] and ED: 2.1 [0.8 4.5] hours prior to first antibiotics order) across all six cohorts, thus allowing for identification and prioritization of patients at high risk for sepsis.
AbstractList Sepsis is a leading cause of morbidity and mortality worldwide. Early identification of sepsis is important as it allows timely administration of potentially life-saving resuscitation and antimicrobial therapy. We present COMPOSER (COnformal Multidimensional Prediction Of SEpsis Risk), a deep learning model for the early prediction of sepsis, specifically designed to reduce false alarms by detecting unfamiliar patients/situations arising from erroneous data, missingness, distributional shift and data drifts. COMPOSER flags these unfamiliar cases as indeterminate rather than making spurious predictions. Six patient cohorts (515,720 patients) curated from two healthcare systems in the United States across intensive care units (ICU) and emergency departments (ED) were used to train and externally and temporally validate this model. In a sequential prediction setting, COMPOSER achieved a consistently high area under the curve (AUC) (ICU: 0.925–0.953; ED: 0.938–0.945). Out of over 6 million prediction windows roughly 20% and 8% were identified as indeterminate amongst non-septic and septic patients, respectively. COMPOSER provided early warning within a clinically actionable timeframe (ICU: 12.2 [3.2 22.8] and ED: 2.1 [0.8 4.5] hours prior to first antibiotics order) across all six cohorts, thus allowing for identification and prioritization of patients at high risk for sepsis.
Sepsis is a leading cause of morbidity and mortality worldwide. Early identification of sepsis is important as it allows timely administration of potentially life-saving resuscitation and antimicrobial therapy. We present COMPOSER (COnformal Multidimensional Prediction Of SEpsis Risk), a deep learning model for the early prediction of sepsis, specifically designed to reduce false alarms by detecting unfamiliar patients/situations arising from erroneous data, missingness, distributional shift and data drifts. COMPOSER flags these unfamiliar cases as indeterminate rather than making spurious predictions. Six patient cohorts (515,720 patients) curated from two healthcare systems in the United States across intensive care units (ICU) and emergency departments (ED) were used to train and externally and temporally validate this model. In a sequential prediction setting, COMPOSER achieved a consistently high area under the curve (AUC) (ICU: 0.925–0.953; ED: 0.938–0.945). Out of over 6 million prediction windows roughly 20% and 8% were identified as indeterminate amongst non-septic and septic patients, respectively. COMPOSER provided early warning within a clinically actionable timeframe (ICU: 12.2 [3.2 22.8] and ED: 2.1 [0.8 4.5] hours prior to first antibiotics order) across all six cohorts, thus allowing for identification and prioritization of patients at high risk for sepsis.
Abstract Sepsis is a leading cause of morbidity and mortality worldwide. Early identification of sepsis is important as it allows timely administration of potentially life-saving resuscitation and antimicrobial therapy. We present COMPOSER (COnformal Multidimensional Prediction Of SEpsis Risk), a deep learning model for the early prediction of sepsis, specifically designed to reduce false alarms by detecting unfamiliar patients/situations arising from erroneous data, missingness, distributional shift and data drifts. COMPOSER flags these unfamiliar cases as indeterminate rather than making spurious predictions. Six patient cohorts (515,720 patients) curated from two healthcare systems in the United States across intensive care units (ICU) and emergency departments (ED) were used to train and externally and temporally validate this model. In a sequential prediction setting, COMPOSER achieved a consistently high area under the curve (AUC) (ICU: 0.925–0.953; ED: 0.938–0.945). Out of over 6 million prediction windows roughly 20% and 8% were identified as indeterminate amongst non-septic and septic patients, respectively. COMPOSER provided early warning within a clinically actionable timeframe (ICU: 12.2 [3.2 22.8] and ED: 2.1 [0.8 4.5] hours prior to first antibiotics order) across all six cohorts, thus allowing for identification and prioritization of patients at high risk for sepsis.
Abstract Sepsis is a leading cause of morbidity and mortality worldwide. Early identification of sepsis is important as it allows timely administration of potentially life-saving resuscitation and antimicrobial therapy. We present COMPOSER (COnformal Multidimensional Prediction Of SEpsis Risk), a deep learning model for the early prediction of sepsis, specifically designed to reduce false alarms by detecting unfamiliar patients/situations arising from erroneous data, missingness, distributional shift and data drifts. COMPOSER flags these unfamiliar cases as indeterminate rather than making spurious predictions. Six patient cohorts (515,720 patients) curated from two healthcare systems in the United States across intensive care units (ICU) and emergency departments (ED) were used to train and externally and temporally validate this model. In a sequential prediction setting, COMPOSER achieved a consistently high area under the curve (AUC) (ICU: 0.925–0.953; ED: 0.938–0.945). Out of over 6 million prediction windows roughly 20% and 8% were identified as indeterminate amongst non-septic and septic patients, respectively. COMPOSER provided early warning within a clinically actionable timeframe (ICU: 12.2 [3.2 22.8] and ED: 2.1 [0.8 4.5] hours prior to first antibiotics order) across all six cohorts, thus allowing for identification and prioritization of patients at high risk for sepsis.
ArticleNumber 134
Author Malhotra, Atul
Nemati, Shamim
Wardi, Gabriel
Shashikumar, Supreeth P.
Author_xml – sequence: 1
  givenname: Supreeth P.
  orcidid: 0000-0002-0348-4261
  surname: Shashikumar
  fullname: Shashikumar, Supreeth P.
  email: spshashikumar@health.ucsd.edu
  organization: Division of Biomedical Informatics, University of California San Diego
– sequence: 2
  givenname: Gabriel
  surname: Wardi
  fullname: Wardi, Gabriel
  organization: Department of Emergency Medicine, University of California San Diego, Division of Pulmonary, Critical Care and Sleep Medicine, University of California San Diego
– sequence: 3
  givenname: Atul
  surname: Malhotra
  fullname: Malhotra, Atul
  organization: Division of Pulmonary, Critical Care and Sleep Medicine, University of California San Diego
– sequence: 4
  givenname: Shamim
  orcidid: 0000-0002-0520-4948
  surname: Nemati
  fullname: Nemati, Shamim
  email: snemati@health.ucsd.edu
  organization: Division of Biomedical Informatics, University of California San Diego
BackLink https://www.ncbi.nlm.nih.gov/pubmed/34504260$$D View this record in MEDLINE/PubMed
BookMark eNp9ks9u1DAQxi1UREvpC3BAlrhwCUz8L84FqaoorFSJC3C1bMdJvWTtxc6CetvXqAQvt0-Cuyml5cDJluc333hmvqfoIMTgEHpew-saqHyTWd0wUQGpKwAOrBKP0BGhrawE5eTg3v0QneS8BAACTLZMPEGHlJUMIuAIfTlNk--99XrEPkxuHP3ggnU4u3X2Ga-T67ydfAxYj0NMfrpc4dHpFDKeIs76Cu-2Pxe4i2G3vZ7w1xB_7La_nqHHvR6zO7k9j9Hn83efzj5UFx_fL85OLyrLGUwVtZb30La0AcqoEFJbynkvmp4ZYjvrnG3AWSd0aUTrmgoHojOEgWFNKxp6jBazbhf1Uq2TX-l0paL2av8Q06B0adCOTgnJiZZGMmIN64hsTcNB95ZxyWtuTNF6O2utN2blSvEwJT0-EH0YCf5SDfG7KpJtU7dF4NWtQIrfNi5PauWzLSPVwcVNVoQXqqxFyIK-_Addxk0KZVQ3FAgBsKfITNkUc06uv_tMDerGBWp2gSouUHsXKFGSXtxv4y7lz84LQGcgl1AYXPpb-z-yvwGMiMGg
CitedBy_id crossref_primary_10_1038_s41746_023_00986_6
crossref_primary_10_1038_s41746_022_00731_5
crossref_primary_10_1016_j_ccc_2023_02_003
crossref_primary_10_3349_ymj_2022_63_S108
crossref_primary_10_1016_j_jbi_2023_104550
crossref_primary_10_1016_j_eclinm_2023_102124
crossref_primary_10_3390_antibiotics11060784
crossref_primary_10_1016_j_xops_2023_100394
crossref_primary_10_2139_ssrn_4130480
crossref_primary_10_2196_50369
crossref_primary_10_3389_fimmu_2024_1434688
crossref_primary_10_1080_13102818_2024_2349587
crossref_primary_10_37882_2223_2966_2021_11_39
crossref_primary_10_1097_CCM_0000000000005894
crossref_primary_10_1515_mr_2023_0039
crossref_primary_10_1016_j_preteyeres_2023_101227
crossref_primary_10_1016_j_ebiom_2022_104394
crossref_primary_10_1016_j_jsse_2023_10_003
crossref_primary_10_3390_diagnostics13193091
crossref_primary_10_1056_AIoa2300032
crossref_primary_10_2196_45614
crossref_primary_10_1001_jamaophthalmol_2023_2554
crossref_primary_10_1016_j_artmed_2024_102785
crossref_primary_10_1038_s41746_024_01066_z
crossref_primary_10_1016_j_giq_2024_101953
crossref_primary_10_1016_S2589_7500_22_00149_2
crossref_primary_10_1186_s13054_024_04948_6
crossref_primary_10_1038_s41591_022_01961_6
crossref_primary_10_2196_43486
crossref_primary_10_1007_s00063_024_01141_z
crossref_primary_10_1161_JAHA_122_028882
Cites_doi 10.1186/s12873-016-0095-0
10.1002/jhm.2259
10.1038/s41746-020-0253-3
10.1001/jama.2016.0288
10.1016/j.dsp.2017.10.011
10.1001/jama.2017.13836
10.1001/jama.2013.6032
10.1371/journal.pone.0174708
10.1097/CCM.0000000000002936
10.1016/j.annemergmed.2014.02.023
10.1126/scitranslmed.aab3719
10.1038/s41591-020-0789-4
10.1038/s41467-020-17431-x
10.2196/15182
10.1016/j.jbi.2014.03.016
10.1136/bmjopen-2017-017833
10.2196/11605
10.1093/jamia/ocv189
10.1088/1361-6579/aa9772
10.1038/s41746-021-00426-3
10.2196/medinform.5909
10.1093/biostatistics/kxn018
10.1038/s41586-020-2649-2
10.1186/s12916-019-1426-2
10.1136/amiajnl-2011-000089
10.1093/jamia/ocw105
10.1001/jama.2016.0287
10.1101/2020.11.02.20224931
10.1136/bmj.k1479
10.2307/2531595
10.1109/EMBC44109.2020.9175947
10.1097/CCM.0000000000004145
10.21037/atm.2020.03.63
10.1093/jamia/ocaa319
10.1109/ICTAI.2007.47
10.1007/s00134-019-05872-y
ContentType Journal Article
Copyright The Author(s) 2021
2021. The Author(s).
The Author(s) 2021. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml – notice: The Author(s) 2021
– notice: 2021. The Author(s).
– notice: The Author(s) 2021. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID C6C
NPM
AAYXX
CITATION
3V.
7RV
7X7
7XB
8FI
8FJ
8FK
ABUWG
AFKRA
AZQEC
BENPR
CCPQU
DWQXO
FYUFA
GHDGH
K9.
KB0
M0S
NAPCQ
PIMPY
PQEST
PQQKQ
PQUKI
PRINS
7X8
5PM
DOA
DOI 10.1038/s41746-021-00504-6
DatabaseName SpringerOpen
PubMed
CrossRef
ProQuest Central (Corporate)
ProQuest Nursing and Allied Health Journals
Health & Medical Collection
ProQuest Central (purchase pre-March 2016)
Hospital Premium Collection
Hospital Premium Collection (Alumni Edition)
ProQuest Central (Alumni) (purchase pre-March 2016)
ProQuest Central (Alumni)
ProQuest Central
ProQuest Central Essentials
AUTh Library subscriptions: ProQuest Central
ProQuest One Community College
ProQuest Central Korea
Health Research Premium Collection
Health Research Premium Collection (Alumni)
ProQuest Health & Medical Complete (Alumni)
Nursing & Allied Health Database (Alumni Edition)
Health & Medical Collection (Alumni Edition)
Nursing & Allied Health Premium
Publicly Available Content Database
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Academic
ProQuest One Academic UKI Edition
ProQuest Central China
MEDLINE - Academic
PubMed Central (Full Participant titles)
DOAJ Directory of Open Access Journals
DatabaseTitle PubMed
CrossRef
Publicly Available Content Database
ProQuest Central Essentials
ProQuest One Academic Eastern Edition
ProQuest Health & Medical Complete (Alumni)
ProQuest Central (Alumni Edition)
ProQuest One Community College
ProQuest Nursing & Allied Health Source
ProQuest Hospital Collection
Health Research Premium Collection (Alumni)
ProQuest Central China
ProQuest Hospital Collection (Alumni)
ProQuest Central
Nursing & Allied Health Premium
ProQuest Health & Medical Complete
Health Research Premium Collection
ProQuest One Academic UKI Edition
Health and Medicine Complete (Alumni Edition)
ProQuest Central Korea
ProQuest Nursing & Allied Health Source (Alumni)
ProQuest One Academic
ProQuest Central (Alumni)
MEDLINE - Academic
DatabaseTitleList Publicly Available Content Database


PubMed
CrossRef

MEDLINE - Academic
Database_xml – sequence: 1
  dbid: C6C
  name: SpringerOpen
  url: http://www.springeropen.com/
  sourceTypes: Publisher
– sequence: 2
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 3
  dbid: NPM
  name: PubMed
  url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 4
  dbid: 7X7
  name: Health & Medical Collection
  url: https://search.proquest.com/healthcomplete
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
EISSN 2398-6352
EndPage 134
ExternalDocumentID oai_doaj_org_article_6852a8b842cb4d289b750afc458515bb
10_1038_s41746_021_00504_6
34504260
Genre Journal Article
GrantInformation_xml – fundername: Gordon and Betty Moore Foundation (Gordon E. and Betty I. Moore Foundation)
  grantid: GBMF9052
  funderid: https://doi.org/10.13039/100000936
– fundername: U.S. Department of Health & Human Services | Biomedical Advanced Research and Development Authority (BARDA)
  grantid: HHSO100201900015C
  funderid: https://doi.org/10.13039/100012399
– fundername: Foundation for the National Institutes of Health (Foundation for the National Institutes of Health, Inc.)
  grantid: R56LM013517
  funderid: https://doi.org/10.13039/100000009
– fundername: Foundation for the National Institutes of Health (Foundation for the National Institutes of Health, Inc.)
  grantid: R56LM013517
– fundername: Gordon and Betty Moore Foundation (Gordon E. and Betty I. Moore Foundation)
  grantid: GBMF9052
– fundername: NIGMS NIH HHS
  grantid: R35 GM143121
– fundername: NLM NIH HHS
  grantid: R56 LM013517
– fundername: U.S. Department of Health & Human Services | Biomedical Advanced Research and Development Authority (BARDA)
  grantid: HHSO100201900015C
– fundername: NIEHS NIH HHS
  grantid: K01 ES025445
– fundername: ;
  grantid: HHSO100201900015C
– fundername: ;
  grantid: R56LM013517
– fundername: ;
  grantid: GBMF9052
GroupedDBID 0R~
53G
7RV
7X7
8FI
8FJ
AAJSJ
ABUWG
ACGFS
ACSMW
ADBBV
AFKRA
AJTQC
ALIPV
ALMA_UNASSIGNED_HOLDINGS
AOIJS
BCNDV
BENPR
C6C
CCPQU
EBLON
EBS
EIHBH
FYUFA
GROUPED_DOAJ
HMCUK
HYE
M~E
NAO
NAPCQ
NO~
OK1
PGMZT
PIMPY
RNT
RPM
SNYQT
UKHRP
NPM
AAYXX
CITATION
3V.
7XB
8FK
AZQEC
DWQXO
K9.
PQEST
PQQKQ
PQUKI
PRINS
7X8
5PM
ID FETCH-LOGICAL-c540t-3cc5f099370343668ac355f67f4b2cdceec70ece6a635aa136e06db240b479673
IEDL.DBID RPM
ISSN 2398-6352
IngestDate Tue Oct 22 15:12:02 EDT 2024
Tue Sep 17 21:14:29 EDT 2024
Tue Aug 27 04:32:41 EDT 2024
Thu Oct 10 16:04:51 EDT 2024
Fri Aug 23 03:46:44 EDT 2024
Thu Oct 24 09:42:31 EDT 2024
Fri Oct 11 20:44:51 EDT 2024
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 1
Language English
License 2021. The Author(s).
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c540t-3cc5f099370343668ac355f67f4b2cdceec70ece6a635aa136e06db240b479673
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0000-0002-0520-4948
0000-0002-0348-4261
OpenAccessLink https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8429719/
PMID 34504260
PQID 2570660068
PQPubID 5061815
PageCount 1
ParticipantIDs doaj_primary_oai_doaj_org_article_6852a8b842cb4d289b750afc458515bb
pubmedcentral_primary_oai_pubmedcentral_nih_gov_8429719
proquest_miscellaneous_2571923968
proquest_journals_2570660068
crossref_primary_10_1038_s41746_021_00504_6
pubmed_primary_34504260
springer_journals_10_1038_s41746_021_00504_6
PublicationCentury 2000
PublicationDate 2021-09-09
PublicationDateYYYYMMDD 2021-09-09
PublicationDate_xml – month: 09
  year: 2021
  text: 2021-09-09
  day: 09
PublicationDecade 2020
PublicationPlace London
PublicationPlace_xml – name: London
– name: England
PublicationTitle NPJ digital medicine
PublicationTitleAbbrev npj Digit. Med
PublicationTitleAlternate NPJ Digit Med
PublicationYear 2021
Publisher Nature Publishing Group UK
Nature Publishing Group
Nature Portfolio
Publisher_xml – name: Nature Publishing Group UK
– name: Nature Publishing Group
– name: Nature Portfolio
References Goddard, Roudsari, Wyatt (CR21) 2012; 19
Montavon, Samek, Müller (CR48) 2018; 73
CR39
CR38
CR36
CR35
Umscheid (CR19) 2015; 10
CR31
Nemati (CR11) 2018; 46
CR30
Giuliano (CR9) 2007; 16
Sendak (CR18) 2020; 8
Sendak, Gao, Brajer, Balu (CR26) 2020; 3
Hyland (CR34) 2020; 26
Lyell, Coiera (CR40) 2017; 24
CR3
Desautels (CR5) 2016; 4
CR49
CR46
CR43
CR42
CR41
Horng (CR7) 2017; 12
Kelly, Karthikesalingam, Suleyman, Corrado, King (CR23) 2019; 17
Moskowitz, McSparron, Stone, Celi (CR44) 2015; 2
Lauritsen (CR15) 2020; 11
CR17
CR16
CR14
CR12
Beaulieu-Jones (CR24) 2021; 4
CR53
Abadi (CR55) 2016; 16
CR52
Shafer, Vovk (CR32) 2008; 9
CR51
Brown (CR8) 2016; 16
Villar (CR4) 2014; 64
Harris (CR54) 2020; 585
Mitka (CR37) 2013; 309
Mao (CR6) 2018; 8
Mandel, Kreda, Mandl, Kohane, Ramoni (CR45) 2016; 23
CR29
Steinberg, Fine, Chappell (CR50) 2009; 10
CR27
Seymour (CR33) 2016; 315
Singer (CR1) 2016; 315
CR25
Rhee (CR2) 2017; 318
Sharafoddini, Dubin, Maslove, Lee (CR28) 2019; 7
CR22
CR20
Henry, Hager, Pronovost, Saria (CR10) 2015; 7
Pivovarov, Albers, Sepulveda, Elhadad (CR47) 2014; 51
Shashikumar, Li, Clifford, Nemati (CR13) 2017; 38
504_CR17
504_CR16
504_CR14
504_CR12
504_CR53
KK Giuliano (504_CR9) 2007; 16
504_CR52
DM Steinberg (504_CR50) 2009; 10
504_CR51
SM Lauritsen (504_CR15) 2020; 11
S Nemati (504_CR11) 2018; 46
R Pivovarov (504_CR47) 2014; 51
M Abadi (504_CR55) 2016; 16
MP Sendak (504_CR26) 2020; 3
504_CR29
504_CR27
K Goddard (504_CR21) 2012; 19
Q Mao (504_CR6) 2018; 8
504_CR25
JC Mandel (504_CR45) 2016; 23
504_CR22
504_CR20
C Rhee (504_CR2) 2017; 318
CJ Kelly (504_CR23) 2019; 17
CW Seymour (504_CR33) 2016; 315
SL Hyland (504_CR34) 2020; 26
CR Harris (504_CR54) 2020; 585
504_CR39
504_CR3
SM Brown (504_CR8) 2016; 16
G Shafer (504_CR32) 2008; 9
504_CR38
504_CR36
D Lyell (504_CR40) 2017; 24
504_CR35
A Moskowitz (504_CR44) 2015; 2
504_CR31
504_CR30
MP Sendak (504_CR18) 2020; 8
T Desautels (504_CR5) 2016; 4
M Singer (504_CR1) 2016; 315
M Mitka (504_CR37) 2013; 309
KE Henry (504_CR10) 2015; 7
G Montavon (504_CR48) 2018; 73
S Horng (504_CR7) 2017; 12
BK Beaulieu-Jones (504_CR24) 2021; 4
CA Umscheid (504_CR19) 2015; 10
SP Shashikumar (504_CR13) 2017; 38
504_CR49
504_CR46
504_CR43
504_CR42
504_CR41
J Villar (504_CR4) 2014; 64
A Sharafoddini (504_CR28) 2019; 7
References_xml – volume: 16
  start-page: 122
  year: 2007
  end-page: 130
  ident: CR9
  article-title: Physiological monitoring for critically ill patients: testing a predictive model for the early detection of sepsis
  publication-title: AJCC
  contributor:
    fullname: Giuliano
– ident: CR22
– volume: 16
  year: 2016
  ident: CR8
  article-title: Prospective evaluation of an automated method to identify patients with severe sepsis or septic shock in the emergency department
  publication-title: BMC Emerg. Med.
  doi: 10.1186/s12873-016-0095-0
  contributor:
    fullname: Brown
– ident: CR49
– ident: CR39
– ident: CR16
– ident: CR51
– ident: CR12
– volume: 10
  start-page: 26
  year: 2015
  end-page: 31
  ident: CR19
  article-title: Development, implementation, and impact of an automated early warning and response system for sepsis
  publication-title: J. Hospital Med.
  doi: 10.1002/jhm.2259
  contributor:
    fullname: Umscheid
– ident: CR35
– ident: CR29
– volume: 3
  start-page: 1
  year: 2020
  end-page: 4
  ident: CR26
  article-title: Presenting machine learning model information to clinical end users with model facts labels
  publication-title: NPJ Digital Med.
  doi: 10.1038/s41746-020-0253-3
  contributor:
    fullname: Balu
– ident: CR25
– ident: CR42
– ident: CR46
– volume: 315
  start-page: 762
  year: 2016
  end-page: 774
  ident: CR33
  article-title: Assessment of clinical criteria for sepsis: for the third international consensus definitions for sepsis and septic shock (Sepsis-3)
  publication-title: JAMA
  doi: 10.1001/jama.2016.0288
  contributor:
    fullname: Seymour
– volume: 73
  start-page: 1
  year: 2018
  end-page: 15
  ident: CR48
  article-title: Methods for interpreting and understanding deep neural networks
  publication-title: Digital Signal Process.
  doi: 10.1016/j.dsp.2017.10.011
  contributor:
    fullname: Müller
– volume: 318
  start-page: 1241
  year: 2017
  end-page: 1249
  ident: CR2
  article-title: Incidence and trends of sepsis in US hospitals using clinical vs claims data, 2009–2014
  publication-title: JAMA
  doi: 10.1001/jama.2017.13836
  contributor:
    fullname: Rhee
– volume: 309
  start-page: 2315
  year: 2013
  end-page: 2316
  ident: CR37
  article-title: Joint commission warns of alarm fatigue: multitude of alarms from monitoring devices problematic
  publication-title: Jama
  doi: 10.1001/jama.2013.6032
  contributor:
    fullname: Mitka
– volume: 12
  year: 2017
  ident: CR7
  article-title: Creating an automated trigger for sepsis clinical decision support at emergency department triage using machine learning
  publication-title: PLoS ONE
  doi: 10.1371/journal.pone.0174708
  contributor:
    fullname: Horng
– volume: 46
  start-page: 547
  year: 2018
  end-page: 553
  ident: CR11
  article-title: An interpretable machine learning model for accurate prediction of sepsis in the ICU
  publication-title: Crit. Care Med.
  doi: 10.1097/CCM.0000000000002936
  contributor:
    fullname: Nemati
– volume: 64
  start-page: 48
  year: 2014
  end-page: 54
  ident: CR4
  article-title: Many emergency department patients with severe sepsis and septic shock do not meet diagnostic criteria within 3h of arrival
  publication-title: Ann. Emerg. Med.
  doi: 10.1016/j.annemergmed.2014.02.023
  contributor:
    fullname: Villar
– volume: 7
  start-page: 299ra122
  year: 2015
  end-page: 299ra122
  ident: CR10
  article-title: A targeted real-time early warning score (TREWScore) for septic shock
  publication-title: Sci. Transl. Med.
  doi: 10.1126/scitranslmed.aab3719
  contributor:
    fullname: Saria
– ident: CR36
– volume: 16
  start-page: 265
  year: 2016
  end-page: 283
  ident: CR55
  article-title: Tensorflow: a system for large-scale machine learning
  publication-title: OSDI
  contributor:
    fullname: Abadi
– volume: 26
  start-page: 364
  year: 2020
  end-page: 373
  ident: CR34
  article-title: Early prediction of circulatory failure in the intensive care unit using machine learning
  publication-title: Nat. Med.
  doi: 10.1038/s41591-020-0789-4
  contributor:
    fullname: Hyland
– volume: 2
  start-page: 24
  year: 2015
  ident: CR44
  article-title: Preparing a new generation of clinicians for the era of big data
  publication-title: Harv. Med. Stud. Rev.
  contributor:
    fullname: Celi
– ident: CR43
– ident: CR14
– ident: CR53
– volume: 11
  start-page: 1
  year: 2020
  end-page: 11
  ident: CR15
  article-title: Explainable artificial intelligence model to predict acute critical illness from electronic health records
  publication-title: Nat. Commun.
  doi: 10.1038/s41467-020-17431-x
  contributor:
    fullname: Lauritsen
– ident: CR30
– volume: 8
  year: 2020
  ident: CR18
  article-title: Real-world integration of a sepsis deep learning technology into routine clinical care: implementation study
  publication-title: JMIR Med. Inform.
  doi: 10.2196/15182
  contributor:
    fullname: Sendak
– volume: 51
  start-page: 24
  year: 2014
  end-page: 34
  ident: CR47
  article-title: Identifying and mitigating biases in EHR laboratory tests
  publication-title: J. Biomed. Inform.
  doi: 10.1016/j.jbi.2014.03.016
  contributor:
    fullname: Elhadad
– volume: 8
  year: 2018
  ident: CR6
  article-title: Multicentre validation of a sepsis prediction algorithm using only vital sign data in the emergency department, general ward and ICU
  publication-title: BMJ Open
  doi: 10.1136/bmjopen-2017-017833
  contributor:
    fullname: Mao
– ident: CR27
– volume: 7
  year: 2019
  ident: CR28
  article-title: A new insight into missing data in intensive care unit patient profiles: observational study
  publication-title: JMIR Med. Inform.
  doi: 10.2196/11605
  contributor:
    fullname: Lee
– volume: 23
  start-page: 899
  year: 2016
  end-page: 908
  ident: CR45
  article-title: SMART on FHIR: a standards-based, interoperable apps platform for electronic health records
  publication-title: J. Am. Med Inf. Assoc.
  doi: 10.1093/jamia/ocv189
  contributor:
    fullname: Ramoni
– volume: 38
  start-page: 2235
  year: 2017
  end-page: 2248
  ident: CR13
  article-title: Multiscale network representation of physiological time series for early prediction of sepsis
  publication-title: Physiol. Meas.
  doi: 10.1088/1361-6579/aa9772
  contributor:
    fullname: Nemati
– volume: 4
  start-page: 1
  year: 2021
  end-page: 6
  ident: CR24
  article-title: Machine learning for patient risk stratification: standing on, or looking over, the shoulders of clinicians?
  publication-title: NPJ Digital Med.
  doi: 10.1038/s41746-021-00426-3
  contributor:
    fullname: Beaulieu-Jones
– ident: CR3
– ident: CR38
– volume: 4
  year: 2016
  ident: CR5
  article-title: Prediction of sepsis in the intensive care unit with minimal electronic health record data: a machine learning approach
  publication-title: JMIR Med. Inform.
  doi: 10.2196/medinform.5909
  contributor:
    fullname: Desautels
– ident: CR52
– ident: CR17
– ident: CR31
– volume: 10
  start-page: 94
  year: 2009
  end-page: 105
  ident: CR50
  article-title: Sample size for positive and negative predictive value in diagnostic research using case–control designs
  publication-title: Biostatistics
  doi: 10.1093/biostatistics/kxn018
  contributor:
    fullname: Chappell
– volume: 9
  start-page: 371
  year: 2008
  end-page: 421
  ident: CR32
  article-title: A tutorial on conformal prediction
  publication-title: J. Mach. Learn. Res.
  contributor:
    fullname: Vovk
– volume: 585
  start-page: 357
  year: 2020
  end-page: 362
  ident: CR54
  article-title: Array programming with NumPy
  publication-title: Nature
  doi: 10.1038/s41586-020-2649-2
  contributor:
    fullname: Harris
– volume: 17
  year: 2019
  ident: CR23
  article-title: Key challenges for delivering clinical impact with artificial intelligence
  publication-title: BMC Med.
  doi: 10.1186/s12916-019-1426-2
  contributor:
    fullname: King
– volume: 19
  start-page: 121
  year: 2012
  end-page: 127
  ident: CR21
  article-title: Automation bias: a systematic review of frequency, effect mediators, and mitigators
  publication-title: J. Am. Med. Inform. Assoc.
  doi: 10.1136/amiajnl-2011-000089
  contributor:
    fullname: Wyatt
– volume: 24
  start-page: 423
  year: 2017
  end-page: 431
  ident: CR40
  article-title: Automation bias and verification complexity: a systematic review
  publication-title: J. Am. Med Inf. Assoc.
  doi: 10.1093/jamia/ocw105
  contributor:
    fullname: Coiera
– ident: CR41
– volume: 315
  start-page: 801
  year: 2016
  end-page: 810
  ident: CR1
  article-title: The third international consensus definitions for sepsis and septic shock (Sepsis-3)
  publication-title: JAMA
  doi: 10.1001/jama.2016.0287
  contributor:
    fullname: Singer
– ident: CR20
– ident: 504_CR43
  doi: 10.1101/2020.11.02.20224931
– volume: 585
  start-page: 357
  year: 2020
  ident: 504_CR54
  publication-title: Nature
  doi: 10.1038/s41586-020-2649-2
  contributor:
    fullname: CR Harris
– volume: 4
  start-page: 1
  year: 2021
  ident: 504_CR24
  publication-title: NPJ Digital Med.
  doi: 10.1038/s41746-021-00426-3
  contributor:
    fullname: BK Beaulieu-Jones
– volume: 2
  start-page: 24
  year: 2015
  ident: 504_CR44
  publication-title: Harv. Med. Stud. Rev.
  contributor:
    fullname: A Moskowitz
– volume: 26
  start-page: 364
  year: 2020
  ident: 504_CR34
  publication-title: Nat. Med.
  doi: 10.1038/s41591-020-0789-4
  contributor:
    fullname: SL Hyland
– volume: 315
  start-page: 801
  year: 2016
  ident: 504_CR1
  publication-title: JAMA
  doi: 10.1001/jama.2016.0287
  contributor:
    fullname: M Singer
– ident: 504_CR27
  doi: 10.1136/bmj.k1479
– ident: 504_CR49
  doi: 10.2307/2531595
– volume: 17
  year: 2019
  ident: 504_CR23
  publication-title: BMC Med.
  doi: 10.1186/s12916-019-1426-2
  contributor:
    fullname: CJ Kelly
– ident: 504_CR14
– volume: 7
  start-page: 299ra122
  year: 2015
  ident: 504_CR10
  publication-title: Sci. Transl. Med.
  doi: 10.1126/scitranslmed.aab3719
  contributor:
    fullname: KE Henry
– ident: 504_CR52
– volume: 16
  start-page: 122
  year: 2007
  ident: 504_CR9
  publication-title: AJCC
  contributor:
    fullname: KK Giuliano
– volume: 318
  start-page: 1241
  year: 2017
  ident: 504_CR2
  publication-title: JAMA
  doi: 10.1001/jama.2017.13836
  contributor:
    fullname: C Rhee
– volume: 3
  start-page: 1
  year: 2020
  ident: 504_CR26
  publication-title: NPJ Digital Med.
  doi: 10.1038/s41746-020-0253-3
  contributor:
    fullname: MP Sendak
– volume: 309
  start-page: 2315
  year: 2013
  ident: 504_CR37
  publication-title: Jama
  doi: 10.1001/jama.2013.6032
  contributor:
    fullname: M Mitka
– volume: 64
  start-page: 48
  year: 2014
  ident: 504_CR4
  publication-title: Ann. Emerg. Med.
  doi: 10.1016/j.annemergmed.2014.02.023
  contributor:
    fullname: J Villar
– volume: 11
  start-page: 1
  year: 2020
  ident: 504_CR15
  publication-title: Nat. Commun.
  doi: 10.1038/s41467-020-17431-x
  contributor:
    fullname: SM Lauritsen
– volume: 8
  year: 2020
  ident: 504_CR18
  publication-title: JMIR Med. Inform.
  doi: 10.2196/15182
  contributor:
    fullname: MP Sendak
– ident: 504_CR46
  doi: 10.1109/EMBC44109.2020.9175947
– ident: 504_CR12
  doi: 10.1097/CCM.0000000000004145
– ident: 504_CR30
– ident: 504_CR38
  doi: 10.21037/atm.2020.03.63
– volume: 46
  start-page: 547
  year: 2018
  ident: 504_CR11
  publication-title: Crit. Care Med.
  doi: 10.1097/CCM.0000000000002936
  contributor:
    fullname: S Nemati
– ident: 504_CR17
– volume: 24
  start-page: 423
  year: 2017
  ident: 504_CR40
  publication-title: J. Am. Med Inf. Assoc.
  doi: 10.1093/jamia/ocw105
  contributor:
    fullname: D Lyell
– ident: 504_CR51
– volume: 12
  year: 2017
  ident: 504_CR7
  publication-title: PLoS ONE
  doi: 10.1371/journal.pone.0174708
  contributor:
    fullname: S Horng
– volume: 16
  year: 2016
  ident: 504_CR8
  publication-title: BMC Emerg. Med.
  doi: 10.1186/s12873-016-0095-0
  contributor:
    fullname: SM Brown
– ident: 504_CR41
– ident: 504_CR20
– volume: 315
  start-page: 762
  year: 2016
  ident: 504_CR33
  publication-title: JAMA
  doi: 10.1001/jama.2016.0288
  contributor:
    fullname: CW Seymour
– ident: 504_CR35
– ident: 504_CR39
– volume: 10
  start-page: 94
  year: 2009
  ident: 504_CR50
  publication-title: Biostatistics
  doi: 10.1093/biostatistics/kxn018
  contributor:
    fullname: DM Steinberg
– volume: 23
  start-page: 899
  year: 2016
  ident: 504_CR45
  publication-title: J. Am. Med Inf. Assoc.
  doi: 10.1093/jamia/ocv189
  contributor:
    fullname: JC Mandel
– volume: 16
  start-page: 265
  year: 2016
  ident: 504_CR55
  publication-title: OSDI
  contributor:
    fullname: M Abadi
– volume: 51
  start-page: 24
  year: 2014
  ident: 504_CR47
  publication-title: J. Biomed. Inform.
  doi: 10.1016/j.jbi.2014.03.016
  contributor:
    fullname: R Pivovarov
– volume: 38
  start-page: 2235
  year: 2017
  ident: 504_CR13
  publication-title: Physiol. Meas.
  doi: 10.1088/1361-6579/aa9772
  contributor:
    fullname: SP Shashikumar
– volume: 73
  start-page: 1
  year: 2018
  ident: 504_CR48
  publication-title: Digital Signal Process.
  doi: 10.1016/j.dsp.2017.10.011
  contributor:
    fullname: G Montavon
– ident: 504_CR25
– ident: 504_CR42
  doi: 10.1093/jamia/ocaa319
– ident: 504_CR29
– ident: 504_CR3
– ident: 504_CR36
– volume: 7
  year: 2019
  ident: 504_CR28
  publication-title: JMIR Med. Inform.
  doi: 10.2196/11605
  contributor:
    fullname: A Sharafoddini
– volume: 9
  start-page: 371
  year: 2008
  ident: 504_CR32
  publication-title: J. Mach. Learn. Res.
  contributor:
    fullname: G Shafer
– volume: 4
  year: 2016
  ident: 504_CR5
  publication-title: JMIR Med. Inform.
  doi: 10.2196/medinform.5909
  contributor:
    fullname: T Desautels
– ident: 504_CR53
– volume: 10
  start-page: 26
  year: 2015
  ident: 504_CR19
  publication-title: J. Hospital Med.
  doi: 10.1002/jhm.2259
  contributor:
    fullname: CA Umscheid
– volume: 19
  start-page: 121
  year: 2012
  ident: 504_CR21
  publication-title: J. Am. Med. Inform. Assoc.
  doi: 10.1136/amiajnl-2011-000089
  contributor:
    fullname: K Goddard
– volume: 8
  year: 2018
  ident: 504_CR6
  publication-title: BMJ Open
  doi: 10.1136/bmjopen-2017-017833
  contributor:
    fullname: Q Mao
– ident: 504_CR31
  doi: 10.1109/ICTAI.2007.47
– ident: 504_CR22
– ident: 504_CR16
  doi: 10.1007/s00134-019-05872-y
SSID ssj0002048946
Score 2.4206588
Snippet Sepsis is a leading cause of morbidity and mortality worldwide. Early identification of sepsis is important as it allows timely administration of potentially...
Abstract Sepsis is a leading cause of morbidity and mortality worldwide. Early identification of sepsis is important as it allows timely administration of...
Abstract Sepsis is a leading cause of morbidity and mortality worldwide. Early identification of sepsis is important as it allows timely administration of...
SourceID doaj
pubmedcentral
proquest
crossref
pubmed
springer
SourceType Open Website
Open Access Repository
Aggregation Database
Index Database
Publisher
StartPage 134
SubjectTerms 631/114/1305
631/114/2397
631/114/2413
692/308/575
692/699/255/1318
Antibiotics
Artificial intelligence
Biomedicine
Biotechnology
Deep learning
Digital technology
Health risks
Medical diagnosis
Medicine
Medicine & Public Health
Sepsis
SummonAdditionalLinks – databaseName: DOAJ Directory of Open Access Journals
  dbid: DOA
  link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3NbtQwEB5VPVS9IH5KCRRkpN4gqjf-SXIsFVVBak8t6s2yHZsuoslqkx647WtUal9unwSPk112C4gL1_UomnxjZ77ZGc8A7Jcjh9c3bYhNvE85q2RqKulTITV3mTe5jiX_p2fy5IJ_vhSXK6O-sCasbw_cA3cgC5HpwhQ8s4ZXITwwwcdpbznms4Qx8etLy5Vg6ltMr_Gi5HK4JUNZcdDywL2x3jZEz1RQnso1TxQb9v-JZf5eLPkgYxod0fFjeDQwSHLYa_4ENlz9FLZOhxz5M_iCK31fCDJeabhJWjdpxy2ZTFEU7UH096_NdNxdXZM4PKIlXUNa_YPMZ3efSNXU89ltR_Bft_nsfgcujj-eH52kw_SE1AYW1qXMWuEp0g_KOJOy0DZwCy9zz01mw-s4m1NnndSBc2g9YtJRHC7FqeF5KXP2HDbrpnYvgOSj0kl0a8ZrXpWVDkGK1iIrRNgA1o4SeLdAUk36JhkqJrdZoXrcVcBdRdyVTOADgr2UxAbX8YdgdjWYXf3L7AnsLUylhlPXKpzIJyXeekng7XI5nBdMgujaNTdRBkltiTK7vWWXmjAuYsf-BPI1m6-pur5Sj69iT-6gaBkenMD7xe74pdbfoXj5P6B4BdtZ3NZY-7YHm930xr0OTKkzb-Kh-AlIsRHK
  priority: 102
  providerName: Directory of Open Access Journals
– databaseName: AUTh Library subscriptions: ProQuest Central
  dbid: BENPR
  link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1Lb9QwEB7BVkJcKt6kFGQkbhA1Gz-SnBBFrQpSK4Qo6s2yHbtdiSbbTXrgtn8Dqf1z-0vwON4ty-saj6LxzNj-xjOeAXhVjS0-3zTeN3EuZbQWqa6FS7lQzOZOFyqk_B8eiYNj9vGEn8QLty6mVS73xLBR163BO_Id7LYmBL5oeDu9SLFrFEZXYwuN27CRe08hH8HG7t7Rp8-rWxYsS1sxEV_LZLTc6ZjH4Jh3673ojGcsFWsnUijc_ze0-WfS5G-R03Ag7d-DzYgkybtB9ffhlm0ewJ3DGCt_CF9xZKgPQSa_FN4knZ12k45MZ0iKeiHq26mfan92TkITiY70LenUd7KYX30gddss5j96grdvi_n1Izje3_vy_iCNXRRS49FYn1JjuMsQhmSUUSFKZTzGcKJwTOfGT8eaIrPGCuWxh1JjKmyGTaZYpllRiYI-hlHTNvYpkGJcWYHHm3aK1VWtvLOiFM9L7g3BmHECr5eSlNOhWIYMQW5aykHu0stdBrlLkcAuCntFiYWuw4d2dirjupGi5Lkqdclyo1ntvUPtIY5yhmE4k2udwPZSVTKuvk7e2EoCL1fDft1gMEQ1tr0MNAhuK6R5Mmh2xQllPFTuT6BY0_kaq-sjzeQs1Ob2jFb-xwm8WVrHDVv_FsXW_2fxDO7mwWAxu20bRv3s0j73WKjXL6LB_wTxyQrg
  priority: 102
  providerName: ProQuest
– databaseName: SpringerOpen
  dbid: C6C
  link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NbtQwEB5BkRAXxD8pBRmJG0RkY3uSHGFFVZDKiaLeLNux6UolWW3SA7d9jUrwcvskeJzsQqAcuMaTaDJjy994xt8AvKhmjq5v2hCbeJ8KXmNqavSpRC1c7k2hY8n_8Uc8OhEfTuXpSJNDd2Em-Xtevu5EgMxUJhuC3kxmIsXrcIP2YGrTMMf57jyFCGgrgeO9mKtfnew9kaL_Klz5d3nkHznSuPUc3oHbI2ZkbwYn34VrrrkHN4_HrPh9-EwjAxMEW_xGsck6t-wWHVuuSJQ8wPT5l3a16M--stguomN9yzr9jW3W39-zum0268ue0TnbZv3jAZwcvvs0P0rHfgmpDbirT7m10mcEODIuOGKpbUATHgsvTG7D7zhbZM461AFlaD3j6DJqJyUyI4oKC_4Q9pq2cY-BFbPKIW1kxmtRV7UOYYnWMi9lcLm1swRebi2plgMthorpbF6qwe4q2F1FuytM4C0ZeydJlNbxQfC0GleIwlLmujSlyK0RdYgDTQAz2ltBiUtpTAIHW1epcZ11inrwIdI9lwSe74bDCqG0h25cexFlCMZWJPNo8OxOEy5k5OhPoJj4fKLqdKRZnEUW7qBoFT6cwKvt7Pil1r9Nsf9_4k_gVh4nMNW1HcBev7pwTwMK6s2zOP1_AizrAlM
  priority: 102
  providerName: Springer Nature
Title Artificial intelligence sepsis prediction algorithm learns to say “I don’t know”
URI https://link.springer.com/article/10.1038/s41746-021-00504-6
https://www.ncbi.nlm.nih.gov/pubmed/34504260
https://www.proquest.com/docview/2570660068
https://search.proquest.com/docview/2571923968
https://pubmed.ncbi.nlm.nih.gov/PMC8429719
https://doaj.org/article/6852a8b842cb4d289b750afc458515bb
Volume 4
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1fb9MwED9tQ0K8IP4TNioj8QZZ08R2kseu2jQqdZqAob5ZtuNsQWtSNdnD3vo1kODL9ZNwdpOy8ueFp0j2SXH8O8e_853vAN6mA2Ovb2q0TfLcp1HGfZXx3GdcUhPmKpYu5H9yxk8v6HjKpjvAurswLmhfq-KwvJ4dlsWVi62cz3S_ixPrn09GCf5E40Ha34VdVNA7JvpX51mjSUp5e0EmiJJ-TZF221BbNJwDFlDf1i2KKHPZ2bf2I5e2_29c88-Qyd_8pm47OnkED1seSYbr8T6GHVM-gfuT1lP-FL7YnnV2CFLcSbtJajOvi5rMF1bUokLk9WW1KJqrGXElJGrSVKSWt2S1_P6BZFW5Wn5riD17Wy1_PIOLk-PPo1O_raHga-RijR9pzfLAkpAgohHnidTIMHIe51SFGj_H6Dgw2nCJzEPKQcRNYEtM0UDROOVx9Bz2yqo0L4HgjBtuNzeVS5qlmURTRUoWJgzVQOuBB--6mRTzdaoM4VzcUSLWEAiEQDgIBPfgyE72RtKmuXYN1eJStGALnrBQJgrx1opmaBsqJDgy19Q6M5lSHhx0UIl27dXC1uXj3N598eDNphtXjXWFyNJUN07GUtvUyrxYI7sZSacZHsRbmG8NdbsHFdVl5m4V04P3nXb8Gta_p-LVf79oHx6ETq1t2NsB7DWLG_MaSVKjerg0pnEP7g2H409jfB4dn51_xNYRH_XcwUPPLZufWVoYYg
link.rule.ids 230,315,730,783,787,867,888,2109,12070,21402,27938,27939,31733,31734,33758,33759,41134,42203,43324,43819,51590,53806,53808
linkProvider National Library of Medicine
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1Lb9QwEB5BkYAL4k2ggJG4QdRs4kdyQoCottDtqUV7s2zHbleCZNmkB277N5Dgz-0vweN4tyyva2xF45mx_dkz_gbgeTWy-HzT-LOJcyktap7qmruUcUVt7rRQIeV_csTHJ_T9lE3jhVsX0yrXa2JYqOvW4B35HlZb4xxfNLyaf0mxahRGV2MJjctwBXm4kDtfTMXmjgVJaSvK41uZrCj3OuoROGbd-jN0xjKa8q39KND2_w1r_pky-VvcNGxH-zfhRsSR5PVg-FtwyTa34eokRsrvwEdsGdghyOwX2k3S2Xk368h8gV3RKkR9OvUD7c8-k1BCoiN9Szr1layW3w9I3Tar5bee4N3bavnjLpzsvzt-O05jDYXUeCzWp4UxzGUIQrKCFpyXyniE4bhwVOfGD8cakVljufLIQ6lRwW2GJaZopqmouCjuwU7TNvYBEDGqLMfNTTtF66pW_qiiFMtL5t3AmFECL9aalPOBKkOGEHdRykHv0utdBr1LnsAbVPamJ9Jchw_t4lTGWSN5yXJV6pLmRtPanw21BzjKGYrBTKZ1ArtrU8k49zp54SkJPNs0-1mDoRDV2PY89EFoW2Gf-4NlN5IUlAXe_gTEls23RN1uaWZngZnbC1r5Hyfwcu0dF2L9WxUP_z-Kp3BtfDw5lIcHRx8ewfU8OC_mue3CTr84t489Kur1k-D6PwEsbQxr
linkToPdf http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3NbtQwEB5BkSouUP5KoICRuEE22cRxkiMtrFpgqx4oqrhYtmO3gW4SbbIHOO1rINGX2yep7STLboFLr_FIsT0z8TeZ8TcAr9KhNNc3hY5NlHJxmBGXZ0S5EWFYBorHzJb8jw_J_jH-cBKdrLT6skX7gueD4nwyKPIzW1tZTYTX14l5R-O9RH9E42HqVZnybsIt7bN-shKof7P5NZykmHTXZPww8WqswbcpuNXhsx_52DXdi0IcWY72tVPJkvf_C3H-XTh5JXtqD6XRXfjaL6etRfk-mDV8IH5eYXq81nq34E4HVdHbVuQe3JDFfdgcd8n4B_DFjLQEFChfYfZEtazqvEbV1IgaxSN2flpO8-ZsgmyXiho1JarZD7SY_z5AWVks5r8aZH7vLeYXD-F49P7z3r7btWlwhYZ7jRsKESnf4Bw_xCEhCRMaxCgSK8wDofdKitiXQhKmwQ1jw5BI33Sxwj7HcUri8BFsFGUhHwPSi5TEnJ9cMZylGdPREGNRkETa0oQYOvC6VxOtWjYOarPoYUJb_VKtX2r1S4kDu0aTS0nDpG0flNNT2u0vJUkUsITrLRYcZzr85BpDMSWwyZdGnDuw09sB7dy7pqb1HyHmeo0DL5fD2jFNtoUVspxZGYOeUyOz3ZrNcia92TkQrxnU2lTXR7RtWPLvzhYceNOb3p9p_X8rnlz7RS9g8-jdiH46OPz4FG4H1n1Mkd0ObDTTmXymIVnDn1vnuwSiWjcD
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=Artificial+intelligence+sepsis+prediction+algorithm+learns+to+say+%E2%80%9CI+don%E2%80%99t+know%E2%80%9D&rft.jtitle=NPJ+digital+medicine&rft.au=Supreeth+P.+Shashikumar&rft.au=Gabriel+Wardi&rft.au=Atul+Malhotra&rft.au=Shamim+Nemati&rft.date=2021-09-09&rft.pub=Nature+Portfolio&rft.eissn=2398-6352&rft.volume=4&rft.issue=1&rft.spage=1&rft.epage=9&rft_id=info:doi/10.1038%2Fs41746-021-00504-6&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_6852a8b842cb4d289b750afc458515bb
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2398-6352&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2398-6352&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2398-6352&client=summon