Development and validation of predictive models for COVID-19 outcomes in a safety-net hospital population

To develop predictive models of coronavirus disease 2019 (COVID-19) outcomes, elucidate the influence of socioeconomic factors, and assess algorithmic racial fairness using a racially diverse patient population with high social needs. Data included 7,102 patients with positive (RT-PCR) severe acute...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Journal of the American Medical Informatics Association : JAMIA Ročník 29; číslo 7; s. 1253
Hlavní autori: Hao, Boran, Hu, Yang, Sotudian, Shahabeddin, Zad, Zahra, Adams, William G, Assoumou, Sabrina A, Hsu, Heather, Mishuris, Rebecca G, Paschalidis, Ioannis C
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: England 14.06.2022
Predmet:
ISSN:1527-974X, 1527-974X
On-line prístup:Zistit podrobnosti o prístupe
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract To develop predictive models of coronavirus disease 2019 (COVID-19) outcomes, elucidate the influence of socioeconomic factors, and assess algorithmic racial fairness using a racially diverse patient population with high social needs. Data included 7,102 patients with positive (RT-PCR) severe acute respiratory syndrome coronavirus 2 test at a safety-net system in Massachusetts. Linear and nonlinear classification methods were applied. A score based on a recurrent neural network and a transformer architecture was developed to capture the dynamic evolution of vital signs. Combined with patient characteristics, clinical variables, and hospital occupancy measures, this dynamic vital score was used to train predictive models. Hospitalizations can be predicted with an area under the receiver-operating characteristic curve (AUC) of 92% using symptoms, hospital occupancy, and patient characteristics, including social determinants of health. Parsimonious models to predict intensive care, mechanical ventilation, and mortality that used the most recent labs and vitals exhibited AUCs of 92.7%, 91.2%, and 94%, respectively. Early predictive models, using labs and vital signs closer to admission had AUCs of 81.1%, 84.9%, and 92%, respectively. The most accurate models exhibit racial bias, being more likely to falsely predict that Black patients will be hospitalized. Models that are only based on the dynamic vital score exhibited accuracies close to the best parsimonious models, although the latter also used laboratories. This large study demonstrates that COVID-19 severity may accurately be predicted using a score that accounts for the dynamic evolution of vital signs. Further, race, social determinants of health, and hospital occupancy play an important role.
AbstractList To develop predictive models of coronavirus disease 2019 (COVID-19) outcomes, elucidate the influence of socioeconomic factors, and assess algorithmic racial fairness using a racially diverse patient population with high social needs.OBJECTIVETo develop predictive models of coronavirus disease 2019 (COVID-19) outcomes, elucidate the influence of socioeconomic factors, and assess algorithmic racial fairness using a racially diverse patient population with high social needs.Data included 7,102 patients with positive (RT-PCR) severe acute respiratory syndrome coronavirus 2 test at a safety-net system in Massachusetts. Linear and nonlinear classification methods were applied. A score based on a recurrent neural network and a transformer architecture was developed to capture the dynamic evolution of vital signs. Combined with patient characteristics, clinical variables, and hospital occupancy measures, this dynamic vital score was used to train predictive models.MATERIALS AND METHODSData included 7,102 patients with positive (RT-PCR) severe acute respiratory syndrome coronavirus 2 test at a safety-net system in Massachusetts. Linear and nonlinear classification methods were applied. A score based on a recurrent neural network and a transformer architecture was developed to capture the dynamic evolution of vital signs. Combined with patient characteristics, clinical variables, and hospital occupancy measures, this dynamic vital score was used to train predictive models.Hospitalizations can be predicted with an area under the receiver-operating characteristic curve (AUC) of 92% using symptoms, hospital occupancy, and patient characteristics, including social determinants of health. Parsimonious models to predict intensive care, mechanical ventilation, and mortality that used the most recent labs and vitals exhibited AUCs of 92.7%, 91.2%, and 94%, respectively. Early predictive models, using labs and vital signs closer to admission had AUCs of 81.1%, 84.9%, and 92%, respectively.RESULTSHospitalizations can be predicted with an area under the receiver-operating characteristic curve (AUC) of 92% using symptoms, hospital occupancy, and patient characteristics, including social determinants of health. Parsimonious models to predict intensive care, mechanical ventilation, and mortality that used the most recent labs and vitals exhibited AUCs of 92.7%, 91.2%, and 94%, respectively. Early predictive models, using labs and vital signs closer to admission had AUCs of 81.1%, 84.9%, and 92%, respectively.The most accurate models exhibit racial bias, being more likely to falsely predict that Black patients will be hospitalized. Models that are only based on the dynamic vital score exhibited accuracies close to the best parsimonious models, although the latter also used laboratories.DISCUSSIONThe most accurate models exhibit racial bias, being more likely to falsely predict that Black patients will be hospitalized. Models that are only based on the dynamic vital score exhibited accuracies close to the best parsimonious models, although the latter also used laboratories.This large study demonstrates that COVID-19 severity may accurately be predicted using a score that accounts for the dynamic evolution of vital signs. Further, race, social determinants of health, and hospital occupancy play an important role.CONCLUSIONSThis large study demonstrates that COVID-19 severity may accurately be predicted using a score that accounts for the dynamic evolution of vital signs. Further, race, social determinants of health, and hospital occupancy play an important role.
To develop predictive models of coronavirus disease 2019 (COVID-19) outcomes, elucidate the influence of socioeconomic factors, and assess algorithmic racial fairness using a racially diverse patient population with high social needs. Data included 7,102 patients with positive (RT-PCR) severe acute respiratory syndrome coronavirus 2 test at a safety-net system in Massachusetts. Linear and nonlinear classification methods were applied. A score based on a recurrent neural network and a transformer architecture was developed to capture the dynamic evolution of vital signs. Combined with patient characteristics, clinical variables, and hospital occupancy measures, this dynamic vital score was used to train predictive models. Hospitalizations can be predicted with an area under the receiver-operating characteristic curve (AUC) of 92% using symptoms, hospital occupancy, and patient characteristics, including social determinants of health. Parsimonious models to predict intensive care, mechanical ventilation, and mortality that used the most recent labs and vitals exhibited AUCs of 92.7%, 91.2%, and 94%, respectively. Early predictive models, using labs and vital signs closer to admission had AUCs of 81.1%, 84.9%, and 92%, respectively. The most accurate models exhibit racial bias, being more likely to falsely predict that Black patients will be hospitalized. Models that are only based on the dynamic vital score exhibited accuracies close to the best parsimonious models, although the latter also used laboratories. This large study demonstrates that COVID-19 severity may accurately be predicted using a score that accounts for the dynamic evolution of vital signs. Further, race, social determinants of health, and hospital occupancy play an important role.
Author Hao, Boran
Hsu, Heather
Adams, William G
Assoumou, Sabrina A
Zad, Zahra
Sotudian, Shahabeddin
Paschalidis, Ioannis C
Hu, Yang
Mishuris, Rebecca G
Author_xml – sequence: 1
  givenname: Boran
  surname: Hao
  fullname: Hao, Boran
  organization: Department of Electrical and Computer Engineering, Boston University, Boston, Massachusetts, USA
– sequence: 2
  givenname: Yang
  surname: Hu
  fullname: Hu, Yang
  organization: Department of Electrical and Computer Engineering, Boston University, Boston, Massachusetts, USA
– sequence: 3
  givenname: Shahabeddin
  surname: Sotudian
  fullname: Sotudian, Shahabeddin
  organization: Division of Systems Engineering, Boston University, Boston, Massachusetts, USA
– sequence: 4
  givenname: Zahra
  surname: Zad
  fullname: Zad, Zahra
  organization: Division of Systems Engineering, Boston University, Boston, Massachusetts, USA
– sequence: 5
  givenname: William G
  surname: Adams
  fullname: Adams, William G
  organization: Department of Pediatrics, Boston Medical Center and Boston University School of Medicine, Boston, Massachusetts, USA
– sequence: 6
  givenname: Sabrina A
  surname: Assoumou
  fullname: Assoumou, Sabrina A
  organization: Department of Medicine, Boston Medical Center and Boston University School of Medicine, Boston, Massachusetts, USA
– sequence: 7
  givenname: Heather
  surname: Hsu
  fullname: Hsu, Heather
  organization: Department of Pediatrics, Boston Medical Center and Boston University School of Medicine, Boston, Massachusetts, USA
– sequence: 8
  givenname: Rebecca G
  surname: Mishuris
  fullname: Mishuris, Rebecca G
  organization: Department of Medicine, Boston Medical Center and Boston University School of Medicine, Boston, Massachusetts, USA
– sequence: 9
  givenname: Ioannis C
  surname: Paschalidis
  fullname: Paschalidis, Ioannis C
  organization: Department of Biomedical Engineering, Boston University, Boston, Massachusetts, USA
BackLink https://www.ncbi.nlm.nih.gov/pubmed/35441692$$D View this record in MEDLINE/PubMed
BookMark eNpNkDtPwzAYRS1URB8wsiKPLKF-xE48opZHpUpdALFFjvNFuHLsEDuV-u9BUCSme4ajM9w5mvjgAaFrSu4oUXy5153Vy2C0IZKdoRkVrMhUkb9P_vEUzWPcE0Il4-ICTbnIcyoVmyG7hgO40HfgE9a-wQftbKOTDR6HFvcDNNYkewDchQZcxG0Y8Gr3tllnVOEwJhM6iNh6rHHULaRj5iHhjxB7m7TDfehH95O7ROetdhGuTrtAr48PL6vnbLt72qzut5nJGUkZ07oVOZFUKUnqQpgSOKnLum0pSMJKUSiq65KXALJkqjCy5sIwyg1TQKRmC3T72-2H8DlCTFVnowHntIcwxopJwUrJCya-1ZuTOtYdNFU_2E4Px-rvHvYFxsNqEQ
CitedBy_id crossref_primary_10_3389_frai_2024_1495074
crossref_primary_10_1371_journal_pone_0294289
crossref_primary_10_1016_j_avsg_2024_07_113
crossref_primary_10_1016_j_compbiomed_2024_108312
crossref_primary_10_1007_s10654_023_00973_x
crossref_primary_10_1016_j_jclinepi_2024_111606
crossref_primary_10_1097_CCE_0000000000001059
crossref_primary_10_3390_healthcare12020125
crossref_primary_10_1371_journal_pone_0294362
crossref_primary_10_1007_s12063_025_00558_9
crossref_primary_10_1186_s12913_022_08784_8
crossref_primary_10_3390_children12091255
crossref_primary_10_1016_j_jbi_2024_104706
ContentType Journal Article
Copyright The Author(s) 2022. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For permissions, please email: journals.permissions@oup.com.
Copyright_xml – notice: The Author(s) 2022. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For permissions, please email: journals.permissions@oup.com.
DBID NPM
7X8
DOI 10.1093/jamia/ocac062
DatabaseName PubMed
MEDLINE - Academic
DatabaseTitle PubMed
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic
PubMed
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod no_fulltext_linktorsrc
Discipline Medicine
EISSN 1527-974X
ExternalDocumentID 35441692
Genre Journal Article
GrantInformation_xml – fundername: NIH HHS
  grantid: R01 GM135930
– fundername: Boston University Clinical and Translational Science Award (CTSA)
  grantid: NIH/NCATS
– fundername: Office of Naval Research
  grantid: N00014-19-1-2571
– fundername: Boston University Rafik B. Hariri Institute for Computing and Computational Science and Engineering
– fundername: National Science Foundation
  grantid: IIS-1914792
GroupedDBID ---
.DC
0R~
18M
29L
2WC
4.4
48X
53G
5GY
5RE
5WD
6PF
7~T
AABZA
AACZT
AAMVS
AAOGV
AAPQZ
AAPXW
AARHZ
AAUAY
AAVAP
AAWTL
ABDFA
ABEJV
ABEUO
ABGNP
ABIXL
ABJNI
ABNHQ
ABOCM
ABPTD
ABQLI
ABQNK
ABVGC
ABWST
ABXVV
ACGFO
ACGFS
ACGOD
ACHQT
ACUFI
ACUTJ
ACYHN
ADBBV
ADGZP
ADHKW
ADHZD
ADIPN
ADJQC
ADQBN
ADRIX
ADRTK
ADVEK
ADYVW
AEGPL
AEJOX
AEKSI
AEMDU
AENEX
AENZO
AEPUE
AETBJ
AEWNT
AFFZL
AFIYH
AFOFC
AFXEN
AGINJ
AGQXC
AGSYK
AGUTN
AHMBA
AHMMS
AJEEA
ALIPV
ALMA_UNASSIGNED_HOLDINGS
ALUQC
APIBT
ATGXG
AVWKF
AXUDD
AYCSE
BAWUL
BAYMD
BCRHZ
BEYMZ
BHONS
BTRTY
BVRKM
C45
CDBKE
CS3
DAKXR
DIK
DILTD
DU5
E3Z
EBD
EBS
EMOBN
ENERS
F5P
FDB
FECEO
FLUFQ
FOEOM
FOTVD
FQBLK
G-Q
GAUVT
GJXCC
GX1
H13
HAR
IH2
IHE
J21
KOP
KSI
KSN
LSO
MHKGH
NOMLY
NOYVH
NPM
NQ-
O9-
OAUYM
OAWHX
OCZFY
ODMLO
OJQWA
OJZSN
OK1
OPAEJ
OVD
OWPYF
P2P
PAFKI
PEELM
Q5Y
ROX
ROZ
RPM
RPZ
RUSNO
RWL
RXO
SV3
TAE
TEORI
TJX
TMA
WOW
YAYTL
YKOAZ
YXANX
~S-
77I
7X8
ABPQP
ADNBA
AEMQT
AFXAL
AFYAG
AHGBF
AJBYB
AJNCP
ALXQX
JXSIZ
KBUDW
ID FETCH-LOGICAL-c420t-2aaf540619960b75c8e30b8bff1e60285791ab838ee68297c6b35c213c29e06a2
IEDL.DBID 7X8
ISICitedReferencesCount 13
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000792554500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1527-974X
IngestDate Thu Oct 02 10:40:47 EDT 2025
Wed Feb 19 02:26:36 EST 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 7
Keywords COVID-19
AI
social determinants of health
predictive modeling
racial bias
Language English
License The Author(s) 2022. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For permissions, please email: journals.permissions@oup.com.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c420t-2aaf540619960b75c8e30b8bff1e60285791ab838ee68297c6b35c213c29e06a2
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
OpenAccessLink https://academic.oup.com/jamia/article-pdf/29/7/1253/44062199/ocac062.pdf
PMID 35441692
PQID 2652863725
PQPubID 23479
ParticipantIDs proquest_miscellaneous_2652863725
pubmed_primary_35441692
PublicationCentury 2000
PublicationDate 2022-06-14
PublicationDateYYYYMMDD 2022-06-14
PublicationDate_xml – month: 06
  year: 2022
  text: 2022-06-14
  day: 14
PublicationDecade 2020
PublicationPlace England
PublicationPlace_xml – name: England
PublicationTitle Journal of the American Medical Informatics Association : JAMIA
PublicationTitleAlternate J Am Med Inform Assoc
PublicationYear 2022
SSID ssj0016235
Score 2.445411
Snippet To develop predictive models of coronavirus disease 2019 (COVID-19) outcomes, elucidate the influence of socioeconomic factors, and assess algorithmic racial...
SourceID proquest
pubmed
SourceType Aggregation Database
Index Database
StartPage 1253
Title Development and validation of predictive models for COVID-19 outcomes in a safety-net hospital population
URI https://www.ncbi.nlm.nih.gov/pubmed/35441692
https://www.proquest.com/docview/2652863725
Volume 29
WOSCitedRecordID wos000792554500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8QwEA7qinjx_VhfRPAatk2aNj2JrC4K7roHld5KmibYS1u3XcF_76Ttul4EwUtPKYRkMvNNZvJ9CF1x7YgU_D6hgNyIx4xLJBUJZK1ChypwjVQNZf5jMJmIKAqn3YVb1bVVLnxi46jTQtk78gH1ORU-Cyi_Lt-JVY2y1dVOQmMV9RhAGdvSFUTLKgKEdt7wpdKAAG6OOo5NSOIt61AmBxAulGOFcn5Dl02UGW3_d347aKvDl_imNYhdtKLzPbQx7iro-yj70SWEZZ5isLSs1VXChcHlzI60LhA3GjkVBlCLh0-vD7fEDXExr2E2usJZjiWupNH1J8l1jd86-RFcfguCHaCX0d3z8J50cgtEedSpCZXScBvfLWFLEnAlNHMSkRjjah9gCA9CVyaCCa19-yBX-QnjirpM0VA7vqSHaC0vcn2MsPZSkTqeEh4kvb5yhfIkCxUXVEnIJ5M-ulwsYgzmbGsUMtfFvIqXy9hHR-1OxGXLuxEzq5fmh_TkD3-fok1qHypYlSHvDPUMHGZ9jtbVR51Vs4vGTuA7mY6_AMRYyIA
linkProvider ProQuest
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=Development+and+validation+of+predictive+models+for+COVID-19+outcomes+in+a+safety-net+hospital+population&rft.jtitle=Journal+of+the+American+Medical+Informatics+Association+%3A+JAMIA&rft.au=Hao%2C+Boran&rft.au=Hu%2C+Yang&rft.au=Sotudian%2C+Shahabeddin&rft.au=Zad%2C+Zahra&rft.date=2022-06-14&rft.issn=1527-974X&rft.eissn=1527-974X&rft.volume=29&rft.issue=7&rft.spage=1253&rft_id=info:doi/10.1093%2Fjamia%2Focac062&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1527-974X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1527-974X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1527-974X&client=summon