Deep Learning Model to Predict Serious Infection Among Children With Central Venous Lines

Objective: Predict the onset of presumed serious infection, defined as a positive blood culture drawn and new antibiotic course of at least 4 days (PSI * ), among pediatric patients with Central Venous Lines (CVLs). Design: Retrospective cohort study. Setting: Single academic children's hospita...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Frontiers in pediatrics Jg. 9; S. 726870
Hauptverfasser: Tabaie, Azade, Orenstein, Evan W., Nemati, Shamim, Basu, Rajit K., Clifford, Gari D., Kamaleswaran, Rishikesan
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Switzerland Frontiers Media S.A 15.09.2021
Schlagworte:
ISSN:2296-2360, 2296-2360
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Objective: Predict the onset of presumed serious infection, defined as a positive blood culture drawn and new antibiotic course of at least 4 days (PSI * ), among pediatric patients with Central Venous Lines (CVLs). Design: Retrospective cohort study. Setting: Single academic children's hospital. Patients: All hospital encounters from January 2013 to December 2018, excluding the ones without a CVL or with a length-of-stay shorter than 24 h. Measurements and Main Results: Clinical features including demographics, laboratory results, vital signs, characteristics of the CVLs and medications used were extracted retrospectively from electronic medical records. Data were aggregated across all hospitals within a single pediatric health system and used to train a deep learning model to predict the occurrence of PSI * during the next 48 h of hospitalization. The proposed model prediction was compared to prediction of PSI * by a marker of illness severity (PELOD-2). The baseline prevalence of line infections was 0.34% over all segmented 48-h time windows. Events were identified among cases using onset time. All data from admission till the onset was used for cases and among controls we used all data from admission till discharge. The benchmarks were aggregated over all 48 h time windows [N=748,380 associated with 27,137 patient encounters]. The model achieved an area under the receiver operating characteristic curve of 0.993 (95% CI = [0.990, 0.996]), the enriched positive predictive value (PPV) was 23 times greater than the base prevalence. Conversely, prediction by PELOD-2 achieved a lower PPV of 1.5% [0.9%, 2.1%] which was 5 times the baseline prevalence. Conclusion: A deep learning model that employs common clinical features in the electronic health record can help predict the onset of CLABSI in hospitalized children with central venous line 48 hours prior to the time of specimen collection.
AbstractList Objective: Predict the onset of presumed serious infection, defined as a positive blood culture drawn and new antibiotic course of at least 4 days (PSI*), among pediatric patients with Central Venous Lines (CVLs). Design: Retrospective cohort study. Setting: Single academic children's hospital. Patients: All hospital encounters from January 2013 to December 2018, excluding the ones without a CVL or with a length-of-stay shorter than 24 h. Measurements and Main Results: Clinical features including demographics, laboratory results, vital signs, characteristics of the CVLs and medications used were extracted retrospectively from electronic medical records. Data were aggregated across all hospitals within a single pediatric health system and used to train a deep learning model to predict the occurrence of PSI* during the next 48 h of hospitalization. The proposed model prediction was compared to prediction of PSI* by a marker of illness severity (PELOD-2). The baseline prevalence of line infections was 0.34% over all segmented 48-h time windows. Events were identified among cases using onset time. All data from admission till the onset was used for cases and among controls we used all data from admission till discharge. The benchmarks were aggregated over all 48 h time windows [N=748,380 associated with 27,137 patient encounters]. The model achieved an area under the receiver operating characteristic curve of 0.993 (95% CI = [0.990, 0.996]), the enriched positive predictive value (PPV) was 23 times greater than the base prevalence. Conversely, prediction by PELOD-2 achieved a lower PPV of 1.5% [0.9%, 2.1%] which was 5 times the baseline prevalence. Conclusion: A deep learning model that employs common clinical features in the electronic health record can help predict the onset of CLABSI in hospitalized children with central venous line 48 hours prior to the time of specimen collection.
Objective: Predict the onset of presumed serious infection, defined as a positive blood culture drawn and new antibiotic course of at least 4 days (PSI*), among pediatric patients with Central Venous Lines (CVLs). Design: Retrospective cohort study. Setting: Single academic children's hospital. Patients: All hospital encounters from January 2013 to December 2018, excluding the ones without a CVL or with a length-of-stay shorter than 24 h. Measurements and Main Results: Clinical features including demographics, laboratory results, vital signs, characteristics of the CVLs and medications used were extracted retrospectively from electronic medical records. Data were aggregated across all hospitals within a single pediatric health system and used to train a deep learning model to predict the occurrence of PSI* during the next 48 h of hospitalization. The proposed model prediction was compared to prediction of PSI* by a marker of illness severity (PELOD-2). The baseline prevalence of line infections was 0.34% over all segmented 48-h time windows. Events were identified among cases using onset time. All data from admission till the onset was used for cases and among controls we used all data from admission till discharge. The benchmarks were aggregated over all 48 h time windows [N=748,380 associated with 27,137 patient encounters]. The model achieved an area under the receiver operating characteristic curve of 0.993 (95% CI = [0.990, 0.996]), the enriched positive predictive value (PPV) was 23 times greater than the base prevalence. Conversely, prediction by PELOD-2 achieved a lower PPV of 1.5% [0.9%, 2.1%] which was 5 times the baseline prevalence. Conclusion: A deep learning model that employs common clinical features in the electronic health record can help predict the onset of CLABSI in hospitalized children with central venous line 48 hours prior to the time of specimen collection.Objective: Predict the onset of presumed serious infection, defined as a positive blood culture drawn and new antibiotic course of at least 4 days (PSI*), among pediatric patients with Central Venous Lines (CVLs). Design: Retrospective cohort study. Setting: Single academic children's hospital. Patients: All hospital encounters from January 2013 to December 2018, excluding the ones without a CVL or with a length-of-stay shorter than 24 h. Measurements and Main Results: Clinical features including demographics, laboratory results, vital signs, characteristics of the CVLs and medications used were extracted retrospectively from electronic medical records. Data were aggregated across all hospitals within a single pediatric health system and used to train a deep learning model to predict the occurrence of PSI* during the next 48 h of hospitalization. The proposed model prediction was compared to prediction of PSI* by a marker of illness severity (PELOD-2). The baseline prevalence of line infections was 0.34% over all segmented 48-h time windows. Events were identified among cases using onset time. All data from admission till the onset was used for cases and among controls we used all data from admission till discharge. The benchmarks were aggregated over all 48 h time windows [N=748,380 associated with 27,137 patient encounters]. The model achieved an area under the receiver operating characteristic curve of 0.993 (95% CI = [0.990, 0.996]), the enriched positive predictive value (PPV) was 23 times greater than the base prevalence. Conversely, prediction by PELOD-2 achieved a lower PPV of 1.5% [0.9%, 2.1%] which was 5 times the baseline prevalence. Conclusion: A deep learning model that employs common clinical features in the electronic health record can help predict the onset of CLABSI in hospitalized children with central venous line 48 hours prior to the time of specimen collection.
Objective: Predict the onset of presumed serious infection, defined as a positive blood culture drawn and new antibiotic course of at least 4 days (PSI * ), among pediatric patients with Central Venous Lines (CVLs). Design: Retrospective cohort study. Setting: Single academic children's hospital. Patients: All hospital encounters from January 2013 to December 2018, excluding the ones without a CVL or with a length-of-stay shorter than 24 h. Measurements and Main Results: Clinical features including demographics, laboratory results, vital signs, characteristics of the CVLs and medications used were extracted retrospectively from electronic medical records. Data were aggregated across all hospitals within a single pediatric health system and used to train a deep learning model to predict the occurrence of PSI * during the next 48 h of hospitalization. The proposed model prediction was compared to prediction of PSI * by a marker of illness severity (PELOD-2). The baseline prevalence of line infections was 0.34% over all segmented 48-h time windows. Events were identified among cases using onset time. All data from admission till the onset was used for cases and among controls we used all data from admission till discharge. The benchmarks were aggregated over all 48 h time windows [N=748,380 associated with 27,137 patient encounters]. The model achieved an area under the receiver operating characteristic curve of 0.993 (95% CI = [0.990, 0.996]), the enriched positive predictive value (PPV) was 23 times greater than the base prevalence. Conversely, prediction by PELOD-2 achieved a lower PPV of 1.5% [0.9%, 2.1%] which was 5 times the baseline prevalence. Conclusion: A deep learning model that employs common clinical features in the electronic health record can help predict the onset of CLABSI in hospitalized children with central venous line 48 hours prior to the time of specimen collection.
Predict the onset of presumed serious infection, defined as a positive blood culture drawn and new antibiotic course of at least 4 days (PSI ), among pediatric patients with Central Venous Lines (CVLs). Retrospective cohort study. Single academic children's hospital. All hospital encounters from January 2013 to December 2018, excluding the ones without a CVL or with a length-of-stay shorter than 24 h. Clinical features including demographics, laboratory results, vital signs, characteristics of the CVLs and medications used were extracted retrospectively from electronic medical records. Data were aggregated across all hospitals within a single pediatric health system and used to train a deep learning model to predict the occurrence of PSI during the next 48 h of hospitalization. The proposed model prediction was compared to prediction of PSI by a marker of illness severity (PELOD-2). The baseline prevalence of line infections was 0.34% over all segmented 48-h time windows. Events were identified among cases using onset time. All data from admission till the onset was used for cases and among controls we used all data from admission till discharge. The benchmarks were aggregated over all 48 h time windows [N=748,380 associated with 27,137 patient encounters]. The model achieved an area under the receiver operating characteristic curve of 0.993 (95% CI = [0.990, 0.996]), the enriched positive predictive value (PPV) was 23 times greater than the base prevalence. Conversely, prediction by PELOD-2 achieved a lower PPV of 1.5% [0.9%, 2.1%] which was 5 times the baseline prevalence. A deep learning model that employs common clinical features in the electronic health record can help predict the onset of CLABSI in hospitalized children with central venous line 48 hours prior to the time of specimen collection.
Author Clifford, Gari D.
Kamaleswaran, Rishikesan
Orenstein, Evan W.
Nemati, Shamim
Tabaie, Azade
Basu, Rajit K.
AuthorAffiliation 2 Department of Pediatrics, Emory University School of Medicine , Atlanta, GA , United States
1 Department of Biomedical Informatics, Emory School of Medicine , Atlanta, GA , United States
4 Department of Biomedical Engineering, Georgia Institute of Technology and Emory School of Medicine , Atlanta, GA , United States
3 Department of Biomedical Informatics, University of California, San Diego , San Diego, CA , United States
AuthorAffiliation_xml – name: 1 Department of Biomedical Informatics, Emory School of Medicine , Atlanta, GA , United States
– name: 2 Department of Pediatrics, Emory University School of Medicine , Atlanta, GA , United States
– name: 4 Department of Biomedical Engineering, Georgia Institute of Technology and Emory School of Medicine , Atlanta, GA , United States
– name: 3 Department of Biomedical Informatics, University of California, San Diego , San Diego, CA , United States
Author_xml – sequence: 1
  givenname: Azade
  surname: Tabaie
  fullname: Tabaie, Azade
– sequence: 2
  givenname: Evan W.
  surname: Orenstein
  fullname: Orenstein, Evan W.
– sequence: 3
  givenname: Shamim
  surname: Nemati
  fullname: Nemati, Shamim
– sequence: 4
  givenname: Rajit K.
  surname: Basu
  fullname: Basu, Rajit K.
– sequence: 5
  givenname: Gari D.
  surname: Clifford
  fullname: Clifford, Gari D.
– sequence: 6
  givenname: Rishikesan
  surname: Kamaleswaran
  fullname: Kamaleswaran, Rishikesan
BackLink https://www.ncbi.nlm.nih.gov/pubmed/34604142$$D View this record in MEDLINE/PubMed
BookMark eNp1ks9vFCEUx4mpsbX27slw9LLrgwFm5mLSrFo3WaOJv-KJMPDYpZmFlZk18b8v49SmNZELBD7f7wPe9yk5iSkiIc8ZLKuqaV_5A7olB86WNVdNDY_IGeetWvBKwcm99Sm5GIZrKKOtQTL5hJxWQoFggp-RH28QD3SDJscQt_RDctjTMdFPGV2wI_2MOaTjQNfRox1DivRynwq42oXeZYz0exh3dIVxzKan3zBO8CZEHJ6Rx970A17czufk67u3X1bvF5uPV-vV5WZhheLjwgnvnBQgVe2FkR5qxAa8lGAqJ4CxtuussNJAI52vCog1ONkpXiStFNU5Wc--Lplrfchhb_JvnUzQfzZS3mqTx2B71MIIy1jVSWOkYEyZujPoUdXAvFS8LV6vZ6_Dsdujs_OzHpg-PIlhp7fpl25EA1w2xeDlrUFOP484jHofBot9byKWn9Fc1i20IKsJfXG_1l2Rv70pAMyAzWkYMvo7hIGeEqCnBOgpAXpOQJGofyQ2jGZqW7lt6P8vvAHN2rUl
CitedBy_id crossref_primary_10_1080_14787210_2024_2386669
crossref_primary_10_1186_s12879_023_08409_3
crossref_primary_10_1016_j_artmed_2023_102715
crossref_primary_10_1017_ice_2025_1
crossref_primary_10_17049_jnursology_1524051
crossref_primary_10_1038_s41390_022_02116_6
crossref_primary_10_1038_s41598_024_74585_0
Cites_doi 10.1016/j.jcrc.2018.02.010
10.1016/j.annemergmed.2011.07.035
10.1109/JBHI.2019.2894570
10.3389/fped.2019.00413
10.1038/s41746-020-00318-y
10.1093/cid/cir257
10.1017/ice.2019.205
10.1542/peds.2019-1790
10.1542/peds.2009-1382
10.1097/00003246-199605000-00004
10.1097/CCM.0000000000003020
10.1097/CCM.0000000000004246
10.1038/s41598-020-67629-8
10.1097/CCM.0000000000002936
10.1097/INF.0000000000001884
10.1097/PEC.0000000000001835
10.1016/j.idc.2016.07.001
10.4103/0974-2700.66528
10.1164/ajrccm.163.7.9912080
10.1016/j.ajic.2018.04.233
10.1162/neco.1997.9.8.1735
10.1136/bmjqs-2018-008331
10.1017/ice.2015.264
10.22489/CinC.2019.412
10.1164/rccm.201412-2323OC
10.1016/j.compbiomed.2021.104289
10.1186/s13023-020-01424-6
10.1097/CCM.0b013e31828a2bbd
10.1097/PCC.0000000000002106
10.2196/medinform.5909
10.1109/78.650093
ContentType Journal Article
Copyright Copyright © 2021 Tabaie, Orenstein, Nemati, Basu, Clifford and Kamaleswaran.
Copyright © 2021 Tabaie, Orenstein, Nemati, Basu, Clifford and Kamaleswaran. 2021 Tabaie, Orenstein, Nemati, Basu, Clifford and Kamaleswaran
Copyright_xml – notice: Copyright © 2021 Tabaie, Orenstein, Nemati, Basu, Clifford and Kamaleswaran.
– notice: Copyright © 2021 Tabaie, Orenstein, Nemati, Basu, Clifford and Kamaleswaran. 2021 Tabaie, Orenstein, Nemati, Basu, Clifford and Kamaleswaran
DBID AAYXX
CITATION
NPM
7X8
5PM
DOA
DOI 10.3389/fped.2021.726870
DatabaseName CrossRef
PubMed
MEDLINE - Academic
PubMed Central (Full Participant titles)
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
PubMed
MEDLINE - Academic
DatabaseTitleList
MEDLINE - Academic
CrossRef

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 2296-2360
ExternalDocumentID oai_doaj_org_article_4a4c113b5aa54116a7baefe6701f5629
PMC8480258
34604142
10_3389_fped_2021_726870
Genre Journal Article
GroupedDBID 53G
5VS
9T4
AAFWJ
AAYXX
ACGFO
ACGFS
ADBBV
ADRAZ
AFPKN
ALMA_UNASSIGNED_HOLDINGS
AOIJS
BAWUL
BCNDV
CITATION
DIK
GROUPED_DOAJ
GX1
HYE
KQ8
M48
M~E
OK1
PGMZT
RNS
RPM
ACXDI
EMOBN
IPNFZ
NPM
RIG
7X8
5PM
ID FETCH-LOGICAL-c462t-d4fdd540567f4a5f07ee80f550a3d40119bbc4c5a085df3405e70d5b620569543
IEDL.DBID DOA
ISICitedReferencesCount 9
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000701299700001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2296-2360
IngestDate Fri Oct 03 12:42:28 EDT 2025
Tue Sep 30 16:34:58 EDT 2025
Thu Sep 04 20:33:45 EDT 2025
Sun Jul 20 01:30:39 EDT 2025
Sat Nov 29 02:51:46 EST 2025
Tue Nov 18 22:17:48 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords infection
predictive model
explainable machine learning
sepsis
PSI
Language English
License Copyright © 2021 Tabaie, Orenstein, Nemati, Basu, Clifford and Kamaleswaran.
This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c462t-d4fdd540567f4a5f07ee80f550a3d40119bbc4c5a085df3405e70d5b620569543
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
Reviewed by: Robert Kelly, Children's Hospital of Orange County, United States; Luc Morin, Université Paris Saclay, France
Edited by: Brenda M. Morrow, University of Cape Town, South Africa
This article was submitted to Pediatric Critical Care, a section of the journal Frontiers in Pediatrics
OpenAccessLink https://doaj.org/article/4a4c113b5aa54116a7baefe6701f5629
PMID 34604142
PQID 2579090538
PQPubID 23479
ParticipantIDs doaj_primary_oai_doaj_org_article_4a4c113b5aa54116a7baefe6701f5629
pubmedcentral_primary_oai_pubmedcentral_nih_gov_8480258
proquest_miscellaneous_2579090538
pubmed_primary_34604142
crossref_primary_10_3389_fped_2021_726870
crossref_citationtrail_10_3389_fped_2021_726870
PublicationCentury 2000
PublicationDate 2021-09-15
PublicationDateYYYYMMDD 2021-09-15
PublicationDate_xml – month: 09
  year: 2021
  text: 2021-09-15
  day: 15
PublicationDecade 2020
PublicationPlace Switzerland
PublicationPlace_xml – name: Switzerland
PublicationTitle Frontiers in pediatrics
PublicationTitleAlternate Front Pediatr
PublicationYear 2021
Publisher Frontiers Media S.A
Publisher_xml – name: Frontiers Media S.A
References Leteurtre (B22) 2013; 41
McDermott (B29) 2018
Van Wyk (B21) 2019; 23
Dewan (B33) 2020; 21
Chaudhary (B36) 2018; 46
Bagchi (B8) 2018; 46
Shashikumar (B25) 2019
O'grady (B1) 2011; 52
Larsen (B7) 2019; 40
Hsu (B9) 2019; 144
Rhee (B10) 2019; 28
Nemati (B20) 2018; 46
Lin (B26) 2017
Bahdanau (B27) 2014
Le (B12) 2019; 7
Alten (B17) 2018; 37
Rupp (B3) 2016; 30
Figueroa-Phillips (B18) 2020; 36
Tabaie (B11) 2021; 132
Rhee (B14) 2016; 37
Desautels (B13) 2016; 4
(B4) 2011; 58
Pollack (B30) 1996; 24
Lundberg (B28) 2017
Miller (B5) 2010; 125
Weiss (B32) 2015; 191
Schuster (B24) 1997; 45
Reyna (B6) 2019
Schaefer (B16) 2020; 15
Hochreiter (B23) 1997; 9
Leisman (B31) 2020; 48
Raita (B15) 2020; 10
Parreco (B19) 2018; 45
Renaud (B2) 2001; 163
Tress (B34) 2010; 3
Li (B35) 2020; 3
References_xml – volume-title: Human-machine teaming systems engineering guide
  year: 2018
  ident: B29
– volume: 45
  start-page: 156
  year: 2018
  ident: B19
  article-title: Predicting central line-associated bloodstream infections and mortality using supervised machine learning
  publication-title: J Crit Care.
  doi: 10.1016/j.jcrc.2018.02.010
– volume: 58
  start-page: 447
  year: 2011
  ident: B4
  article-title: Vital signs: central line–associated blood stream infections—United States, 2001, 2008, and 2009
  publication-title: Ann Emer Med
  doi: 10.1016/j.annemergmed.2011.07.035
– volume: 23
  start-page: 978
  year: 2019
  ident: B21
  article-title: Improving prediction performance using hierarchical analysis of real-time data: a sepsis case study
  publication-title: IEEE J Biomed Health Inform.
  doi: 10.1109/JBHI.2019.2894570
– volume: 7
  start-page: 413
  year: 2019
  ident: B12
  article-title: Pediatric severe sepsis prediction using machine learning
  publication-title: Front Pediatrics.
  doi: 10.3389/fped.2019.00413
– volume: 3
  start-page: 1
  year: 2020
  ident: B35
  article-title: Developing a delivery science for artificial intelligence in healthcare
  publication-title: NPJ Digital Medicine.
  doi: 10.1038/s41746-020-00318-y
– volume: 52
  start-page: e162
  year: 2011
  ident: B1
  article-title: Guidelines for the prevention of intravascular catheter-related infections
  publication-title: Clin Infect Dis
  doi: 10.1093/cid/cir257
– volume: 40
  start-page: 1100
  year: 2019
  ident: B7
  article-title: A systematic review of central-line–associated bloodstream infection (CLABSI) diagnostic reliability and error
  publication-title: Infec Control Hospital Epidemiol.
  doi: 10.1017/ice.2019.205
– start-page: 2980
  volume-title: Proceedings of the IEEE International Conference on Computer Vision
  year: 2017
  ident: B26
  article-title: Focal loss for dense object detection
– volume: 144
  start-page: e20191790
  year: 2019
  ident: B9
  article-title: A national approach to pediatric sepsis surveillance
  publication-title: Pediatrics
  doi: 10.1542/peds.2019-1790
– volume: 125
  start-page: 206
  year: 2010
  ident: B5
  article-title: Decreasing PICU catheter-associated bloodstream infections: NACHRI's quality transformation efforts
  publication-title: Pediatrics.
  doi: 10.1542/peds.2009-1382
– volume: 24
  start-page: 743
  year: 1996
  ident: B30
  article-title: PRISM III an updated Pediatric Risk of Mortality score
  publication-title: Crit Care Med.
  doi: 10.1097/00003246-199605000-00004
– volume: 46
  start-page: 878
  year: 2018
  ident: B36
  article-title: Racial differences in sepsis mortality at United States academic medical center-affiliated hospitals
  publication-title: Crit Care Med.
  doi: 10.1097/CCM.0000000000003020
– volume: 48
  start-page: 623
  year: 2020
  ident: B31
  article-title: Development and reporting of prediction models: guidance for authors from editors of respiratory, sleep, and critical care journals
  publication-title: Crit Care Med.
  doi: 10.1097/CCM.0000000000004246
– volume: 10
  start-page: 1
  year: 2020
  ident: B15
  article-title: Machine learning-based prediction of acute severity in infants hospitalized for bronchiolitis: a multicenter prospective study
  publication-title: Sci Rep.
  doi: 10.1038/s41598-020-67629-8
– volume: 46
  start-page: 547
  year: 2018
  ident: B20
  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
– volume: 37
  start-page: 768
  year: 2018
  ident: B17
  article-title: The epidemiology of health-care associated infections in pediatric cardiac intensive care units
  publication-title: Pediatr Infect Dis J.
  doi: 10.1097/INF.0000000000001884
– volume: 36
  start-page: e600
  year: 2020
  ident: B18
  article-title: Development of a clinical prediction model for central line–associated bloodstream infection in children presenting to the emergency department
  publication-title: Pediatr Emerg Care.
  doi: 10.1097/PEC.0000000000001835
– volume: 30
  start-page: 853
  year: 2016
  ident: B3
  article-title: Prevention of vascular catheter-related bloodstream infections
  publication-title: Infect Dis Clin.
  doi: 10.1016/j.idc.2016.07.001
– volume: 3
  start-page: 267
  year: 2010
  ident: B34
  article-title: Cardiac arrest in children
  publication-title: J Emer Trauma Shock.
  doi: 10.4103/0974-2700.66528
– volume: 163
  start-page: 1584
  year: 2001
  ident: B2
  article-title: Outcomes of primary and catheter-related bacteremia: a cohort and case–control study in critically ill patients
  publication-title: Am J Respir Crit Care Med.
  doi: 10.1164/ajrccm.163.7.9912080
– volume: 46
  start-page: 1290
  year: 2018
  ident: B8
  article-title: State health department validations of central line–associated bloodstream infection events reported via the National Healthcare Safety Network
  publication-title: Am J Infect Control.
  doi: 10.1016/j.ajic.2018.04.233
– volume: 9
  start-page: 1735
  year: 1997
  ident: B23
  article-title: Long short-term memory
  publication-title: Neural Comput.
  doi: 10.1162/neco.1997.9.8.1735
– year: 2019
  ident: B25
  article-title: DeepAISE–An end-to-end development and deployment of a recurrent neural survival model for early prediction of sepsis
– volume: 28
  start-page: 305
  year: 2019
  ident: B10
  article-title: Using objective clinical data to track progress on preventing and treating sepsis: CDC's new ‘Adult Sepsis Event'surveillance strategy
  publication-title: BMJ Qual Saf.
  doi: 10.1136/bmjqs-2018-008331
– year: 2017
  ident: B28
  article-title: A unified approach to interpreting model predictions
– year: 2014
  ident: B27
  article-title: Neural machine translation by jointly learning to align and translate
– volume: 37
  start-page: 163
  year: 2016
  ident: B14
  article-title: Objective sepsis surveillance using electronic clinical data
  publication-title: Infect Control Hospital Epidemiol.
  doi: 10.1017/ice.2015.264
– volume-title: 2019 Computing in Cardiology (CinC).
  year: 2019
  ident: B6
  article-title: Early prediction of sepsis from clinical data: the PhysioNet/Computing in Cardiology Challenge 2019
  doi: 10.22489/CinC.2019.412
– volume: 191
  start-page: 1147
  year: 2015
  ident: B32
  article-title: Global epidemiology of pediatric severe sepsis: the sepsis prevalence, outcomes, and therapies study
  publication-title: Am J Respir Crit Care Med.
  doi: 10.1164/rccm.201412-2323OC
– volume: 132
  start-page: 104289
  year: 2021
  ident: B11
  article-title: Predicting presumed serious infection among hospitalized children on central venous lines with machine learning
  publication-title: Comput Biol Med.
  doi: 10.1016/j.compbiomed.2021.104289
– volume: 15
  start-page: 1
  year: 2020
  ident: B16
  article-title: The use of machine learning in rare diseases: a scoping review
  publication-title: Orphanet J Rare Dis.
  doi: 10.1186/s13023-020-01424-6
– volume: 41
  start-page: 1761
  year: 2013
  ident: B22
  article-title: Réanimation et d'Urgences Pédiatriques (GFRUP. PELOD-2: an update of the PEdiatric logistic organ dysfunction score
  publication-title: Critic Care Med.
  doi: 10.1097/CCM.0b013e31828a2bbd
– volume: 21
  start-page: 129
  year: 2020
  ident: B33
  article-title: Performance of a clinical decision support tool to identify PICU patients at high risk for clinical deterioration
  publication-title: Pediatric Critical Care Medicine.
  doi: 10.1097/PCC.0000000000002106
– volume: 4
  start-page: e5909
  year: 2016
  ident: B13
  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
– volume: 45
  start-page: 2673
  year: 1997
  ident: B24
  article-title: Bidirectional recurrent neural networks
  publication-title: IEEE Trans Signal Processing.
  doi: 10.1109/78.650093
SSID ssj0000970515
Score 2.2428832
Snippet Objective: Predict the onset of presumed serious infection, defined as a positive blood culture drawn and new antibiotic course of at least 4 days (PSI * ),...
Predict the onset of presumed serious infection, defined as a positive blood culture drawn and new antibiotic course of at least 4 days (PSI ), among pediatric...
Objective: Predict the onset of presumed serious infection, defined as a positive blood culture drawn and new antibiotic course of at least 4 days (PSI*),...
SourceID doaj
pubmedcentral
proquest
pubmed
crossref
SourceType Open Website
Open Access Repository
Aggregation Database
Index Database
Enrichment Source
StartPage 726870
SubjectTerms explainable machine learning
infection
Pediatrics
predictive model
PSI
sepsis
Title Deep Learning Model to Predict Serious Infection Among Children With Central Venous Lines
URI https://www.ncbi.nlm.nih.gov/pubmed/34604142
https://www.proquest.com/docview/2579090538
https://pubmed.ncbi.nlm.nih.gov/PMC8480258
https://doaj.org/article/4a4c113b5aa54116a7baefe6701f5629
Volume 9
WOSCitedRecordID wos000701299700001&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: 2296-2360
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000970515
  issn: 2296-2360
  databaseCode: DOA
  dateStart: 20130101
  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: 2296-2360
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000970515
  issn: 2296-2360
  databaseCode: M~E
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9QwEB5BhRAXxJsUqIzEhUPY-BE_jqW0AolWPfBYTpbt2O1KVbpaQo_8djyJu9pFCC5cckgmijUzsWc84-8DeBWS847qVEcveS1UDLUzJtSqDYxzT4WT3Ug2oU5O9HxuTjeovrAnbIIHnhQ3E04ESrlvnWsFpdIp72KKUjU05bV7PLqXo56NZGqcg41C8pKpLpmzMDNLy4jAoIy-UUxq5CbeWIdGuP4_xZi_t0purD1H9-BuCRrJ_jTY-3Aj9g_g9nEpiz-Eb-9iXJIClXpGkN_sggyX5HSFIgPBLbCc4ZMPpfOqJ_vIMUQOyklu8nUxnJOy0Uu-jLCt5CM2xD-Cz0eHnw7e14UzoQ5CsqHuROo6jMKkSsK1qVEx6iblPMTxTiDAm_dBhNblUKtLPAtG1XStlyy_YlrBH8NOf9nHp0CkZjTyGLFUKAxzJs-EyUThA5NKUlrB7FqDNhRAceS1uLA5sUCdW9S5RZ3bSecVvF6_sZzANP4i-xaNspZDGOzxRnYOW5zD_ss5Knh5bVKbfxushbg-Zh3aPFOZxuQZSFfwZDLx-lNcyEZQwSpQW8bfGsv2k35xPkJza6FzEKl3_8fgn8Ed1Ac2p9D2OewMqx_xBdwKV8Pi-2oPbqq53hu9Pl-Pfx7-AjCcB1Q
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=Deep+Learning+Model+to+Predict+Serious+Infection+Among+Children+With+Central+Venous+Lines&rft.jtitle=Frontiers+in+pediatrics&rft.au=Azade+Tabaie&rft.au=Evan+W.+Orenstein&rft.au=Shamim+Nemati&rft.au=Rajit+K.+Basu&rft.date=2021-09-15&rft.pub=Frontiers+Media+S.A&rft.eissn=2296-2360&rft.volume=9&rft_id=info:doi/10.3389%2Ffped.2021.726870&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_4a4c113b5aa54116a7baefe6701f5629
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2296-2360&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2296-2360&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2296-2360&client=summon