Afficher la notice abrégée

Validation of an Internationally Derived Patient Severity Phenotype to Support COVID-19 Analytics from Electronic Health Record Data

dc.rights.licenseopenen_US
dc.contributor.authorKLANN, Jeffrey G.
dc.contributor.authorWEBER, Griffin M.
dc.contributor.authorESTIRI, Hossein
dc.contributor.authorMOAL, Bertrand
dc.contributor.authorAVILLACH, Paul
dc.contributor.authorHONG, Chuan
dc.contributor.authorCASTRO, Victor
dc.contributor.authorMAULHARDT, Thomas
dc.contributor.authorTAN, Amelia L. M.
dc.contributor.authorGEVA, Alon
dc.contributor.authorBEAULIEU-JONES, Brett K.
dc.contributor.authorMALOVINI, Alberto
dc.contributor.authorSOUTH, Andrew M.
dc.contributor.authorVISWESWARAN, Shyam
dc.contributor.authorOMENN, Gilbert S.
dc.contributor.authorNGIAM, Kee Yuan
dc.contributor.authorMANDL, Kenneth D.
dc.contributor.authorBOEKER, Martin
dc.contributor.authorOLSON, Karen L.
dc.contributor.authorMOWERY, Danielle L.
dc.contributor.authorMORRIS, Michele
dc.contributor.authorFOLLETT, Robert W.
dc.contributor.authorHANAUER, David A.
dc.contributor.authorBELLAZZI, Riccardo
dc.contributor.authorMOORE, Jason H.
dc.contributor.authorLOH, Ne-Hooi Will
dc.contributor.authorBELL, Douglas S.
dc.contributor.authorWAGHOLIKAR, Kavishwar B.
dc.contributor.authorCHIOVATO, Luca
dc.contributor.authorTIBOLLO, Valentina
dc.contributor.authorRIEG, Siegbert
dc.contributor.authorLI, Anthony L. L. J.
hal.structure.identifierBordeaux population health [BPH]
dc.contributor.authorJOUHET, Vianney
dc.contributor.authorSCHRIVER, Emily
dc.contributor.authorSAMAYAMUTHU, Malarkodi J.
dc.contributor.authorXIA, Zongqi
dc.contributor.authorHUTCH, Meghan
dc.contributor.authorLUO, Yuan
dc.contributor.authorKOHANE, Isaac S.
dc.contributor.authorBRAT, Gabriel A.
dc.contributor.authorMURPHY, Shawn N.
dc.date.accessioned2021-04-02T13:19:42Z
dc.date.available2021-04-02T13:19:42Z
dc.date.issued2021-02-10
dc.identifier.issn1067-5027en_US
dc.identifier.urihttps://oskar-bordeaux.fr/handle/20.500.12278/26866
dc.description.abstractEnINTRODUCTION: The Consortium for Clinical Characterization of COVID-19 by EHR (4CE) is an international collaboration addressing COVID-19 with federated analyses of electronic health record (EHR) data. OBJECTIVE: We sought to develop and validate a computable phenotype for COVID-19 severity. METHODS: Twelve 4CE sites participated. First we developed an EHR-based severity phenotype consisting of six code classes, and we validated it on patient hospitalization data from the 12 4CE clinical sites against the outcomes of ICU admission and/or death. We also piloted an alternative machine-learning approach and compared selected predictors of severity to the 4CE phenotype at one site. RESULTS: The full 4CE severity phenotype had pooled sensitivity of 0.73 and specificity 0.83 for the combined outcome of ICU admission and/or death. The sensitivity of individual code categories for acuity had high variability - up to 0.65 across sites. At one pilot site, the expert-derived phenotype had mean AUC 0.903 (95% CI: 0.886, 0.921), compared to AUC 0.956 (95% CI: 0.952, 0.959) for the machine-learning approach. Billing codes were poor proxies of ICU admission, with as low as 49% precision and recall compared to chart review. DISCUSSION: We developed a severity phenotype using 6 code classes that proved resilient to coding variability across international institutions. In contrast, machine-learning approaches may overfit hospital-specific orders. Manual chart review revealed discrepancies even in the gold-standard outcomes, possibly due to heterogeneous pandemic conditions. CONCLUSION: We developed an EHR-based severity phenotype for COVID-19 in hospitalized patients and validated it at 12 international sites.
dc.language.isoENen_US
dc.rightsAttribution-NonCommercial 3.0 United States*
dc.rights.urihttp://creativecommons.org/licenses/by-nc/3.0/us/*
dc.subject.enNovel coronavirus
dc.subject.enDisease severity
dc.subject.enComputable phenotype
dc.subject.enMedical informatics
dc.subject.enData networking
dc.subject.enData interoperability
dc.title.enValidation of an Internationally Derived Patient Severity Phenotype to Support COVID-19 Analytics from Electronic Health Record Data
dc.title.alternativeJ Am Med Inform Assocen_US
dc.typeArticle de revueen_US
dc.identifier.doi10.1093/jamia/ocab018en_US
dc.subject.halSciences du Vivant [q-bio]/Santé publique et épidémiologieen_US
dc.identifier.pubmed33566082en_US
bordeaux.journalJournal of the American Medical Informatics Associationen_US
bordeaux.hal.laboratoriesBordeaux Population Health Research Center (BPH) - UMR 1219en_US
bordeaux.institutionUniversité de Bordeauxen_US
bordeaux.teamERIASen_US
bordeaux.peerReviewedouien_US
bordeaux.inpressnonen_US
hal.identifierhal-03188882
hal.version1
hal.date.transferred2021-04-02T13:19:56Z
hal.audienceInternationale
hal.exporttrue
bordeaux.COinSctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.jtitle=Journal%20of%20the%20American%20Medical%20Informatics%20Association&rft.date=2021-02-10&rft.eissn=1067-5027&rft.issn=1067-5027&rft.au=KLANN,%20Jeffrey%20G.&WEBER,%20Griffin%20M.&ESTIRI,%20Hossein&MOAL,%20Bertrand&AVILLACH,%20Paul&rft.genre=article


Fichier(s) constituant ce document

Thumbnail
Nom:
BPH_JAMIA_2021_Klann.pdf
Taille:
1.108Mo
Format:
PDF
Voir/Ouvrir
Thumbnail
Nom:
license_rdf
Taille:
920octets
Format:
application/rdf+xml
Voir/Ouvrir

Ce document figure dans la(les) collection(s) suivante(s)

Afficher la notice abrégée