Clinical predictors of COVID-19 mortality.
Identifieur interne : 001465 ( Main/Corpus ); précédent : 001464; suivant : 001466Clinical predictors of COVID-19 mortality.
Auteurs : Arjun S. Yadaw ; Yan-Chak Li ; Sonali Bose ; Ravi Iyengar ; Supinda Bunyavanich ; Gaurav PandeySource :
- medRxiv : the preprint server for health sciences ; 2020.
Abstract
BACKGROUND
The coronavirus disease 2019 (COVID-19) pandemic has affected over millions of individuals and caused hundreds of thousands of deaths worldwide. It can be difficult to accurately predict mortality among COVID-19 patients presenting with a spectrum of complications, hindering the prognostication and management of the disease.
METHODS
We applied machine learning techniques to clinical data from a large cohort of 5,051 COVID-19 patients treated at the Mount Sinai Health System in New York City, the global COVID-19 epicenter, to predict mortality. Predictors were designed to classify patients into Deceased or Alive mortality classes and were evaluated in terms of the area under the receiver operating characteristic (ROC) curve (AUC score).
FINDINGS
Using a development cohort (n=3,841) and a systematic machine learning framework, we identified a COVID-19 mortality predictor that demonstrated high accuracy (AUC=0.91) when applied to test sets of retrospective (n= 961) and prospective (n=249) patients. This mortality predictor was based on five clinical features: age, minimum O2 saturation during encounter, type of patient encounter (inpatient vs. various types of outpatient and telehealth encounters), hydroxychloroquine use, and maximum body temperature.
INTERPRETATION
An accurate and parsimonious COVID-19 mortality predictor based on five features may have utility in clinical settings to guide the management and prognostication of patients affected by this disease.
DOI: 10.1101/2020.05.19.20103036
PubMed: 32511520
PubMed Central: PMC7273288
Links to Exploration step
pubmed:32511520Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Clinical predictors of COVID-19 mortality.</title><author><name sortKey="Yadaw, Arjun S" sort="Yadaw, Arjun S" uniqKey="Yadaw A" first="Arjun S" last="Yadaw">Arjun S. Yadaw</name><affiliation><nlm:affiliation>Department of Pharmacological Sciences, Icahn School of Medicine at Mount Sinai, One Gustave L. Levy Place, Box 1215, New York, NY 10029, USA.</nlm:affiliation></affiliation></author><author><name sortKey="Li, Yan Chak" sort="Li, Yan Chak" uniqKey="Li Y" first="Yan-Chak" last="Li">Yan-Chak Li</name><affiliation><nlm:affiliation>Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, One Gustave L. Levy Place, Box 1498, New York, NY 10029, USA.</nlm:affiliation></affiliation></author><author><name sortKey="Bose, Sonali" sort="Bose, Sonali" uniqKey="Bose S" first="Sonali" last="Bose">Sonali Bose</name><affiliation><nlm:affiliation>Department of Medicine, Icahn School of Medicine at Mount Sinai, One Gustave L. Levy Place, Box 1232, New York, NY 10029, USA.</nlm:affiliation></affiliation></author><author><name sortKey="Iyengar, Ravi" sort="Iyengar, Ravi" uniqKey="Iyengar R" first="Ravi" last="Iyengar">Ravi Iyengar</name><affiliation><nlm:affiliation>Department of Pharmacological Sciences, Icahn School of Medicine at Mount Sinai, One Gustave L. Levy Place, Box 1215, New York, NY 10029, USA.</nlm:affiliation></affiliation></author><author><name sortKey="Bunyavanich, Supinda" sort="Bunyavanich, Supinda" uniqKey="Bunyavanich S" first="Supinda" last="Bunyavanich">Supinda Bunyavanich</name><affiliation><nlm:affiliation>Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, One Gustave L. Levy Place, Box 1498, New York, NY 10029, USA.</nlm:affiliation></affiliation></author><author><name sortKey="Pandey, Gaurav" sort="Pandey, Gaurav" uniqKey="Pandey G" first="Gaurav" last="Pandey">Gaurav Pandey</name><affiliation><nlm:affiliation>Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, One Gustave L. Levy Place, Box 1498, New York, NY 10029, USA.</nlm:affiliation></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">PubMed</idno><date when="2020">2020</date><idno type="RBID">pubmed:32511520</idno><idno type="pmid">32511520</idno><idno type="doi">10.1101/2020.05.19.20103036</idno><idno type="pmc">PMC7273288</idno><idno type="wicri:Area/Main/Corpus">001465</idno><idno type="wicri:explorRef" wicri:stream="Main" wicri:step="Corpus" wicri:corpus="PubMed">001465</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en">Clinical predictors of COVID-19 mortality.</title><author><name sortKey="Yadaw, Arjun S" sort="Yadaw, Arjun S" uniqKey="Yadaw A" first="Arjun S" last="Yadaw">Arjun S. Yadaw</name><affiliation><nlm:affiliation>Department of Pharmacological Sciences, Icahn School of Medicine at Mount Sinai, One Gustave L. Levy Place, Box 1215, New York, NY 10029, USA.</nlm:affiliation></affiliation></author><author><name sortKey="Li, Yan Chak" sort="Li, Yan Chak" uniqKey="Li Y" first="Yan-Chak" last="Li">Yan-Chak Li</name><affiliation><nlm:affiliation>Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, One Gustave L. Levy Place, Box 1498, New York, NY 10029, USA.</nlm:affiliation></affiliation></author><author><name sortKey="Bose, Sonali" sort="Bose, Sonali" uniqKey="Bose S" first="Sonali" last="Bose">Sonali Bose</name><affiliation><nlm:affiliation>Department of Medicine, Icahn School of Medicine at Mount Sinai, One Gustave L. Levy Place, Box 1232, New York, NY 10029, USA.</nlm:affiliation></affiliation></author><author><name sortKey="Iyengar, Ravi" sort="Iyengar, Ravi" uniqKey="Iyengar R" first="Ravi" last="Iyengar">Ravi Iyengar</name><affiliation><nlm:affiliation>Department of Pharmacological Sciences, Icahn School of Medicine at Mount Sinai, One Gustave L. Levy Place, Box 1215, New York, NY 10029, USA.</nlm:affiliation></affiliation></author><author><name sortKey="Bunyavanich, Supinda" sort="Bunyavanich, Supinda" uniqKey="Bunyavanich S" first="Supinda" last="Bunyavanich">Supinda Bunyavanich</name><affiliation><nlm:affiliation>Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, One Gustave L. Levy Place, Box 1498, New York, NY 10029, USA.</nlm:affiliation></affiliation></author><author><name sortKey="Pandey, Gaurav" sort="Pandey, Gaurav" uniqKey="Pandey G" first="Gaurav" last="Pandey">Gaurav Pandey</name><affiliation><nlm:affiliation>Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, One Gustave L. Levy Place, Box 1498, New York, NY 10029, USA.</nlm:affiliation></affiliation></author></analytic><series><title level="j">medRxiv : the preprint server for health sciences</title><imprint><date when="2020" type="published">2020</date></imprint></series></biblStruct></sourceDesc></fileDesc><profileDesc><textClass></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en"><p><b>BACKGROUND</b></p><p>The coronavirus disease 2019 (COVID-19) pandemic has affected over millions of individuals and caused hundreds of thousands of deaths worldwide. It can be difficult to accurately predict mortality among COVID-19 patients presenting with a spectrum of complications, hindering the prognostication and management of the disease.</p></div><div type="abstract" xml:lang="en"><p><b>METHODS</b></p><p>We applied machine learning techniques to clinical data from a large cohort of 5,051 COVID-19 patients treated at the Mount Sinai Health System in New York City, the global COVID-19 epicenter, to predict mortality. Predictors were designed to classify patients into Deceased or Alive mortality classes and were evaluated in terms of the area under the receiver operating characteristic (ROC) curve (AUC score).</p></div><div type="abstract" xml:lang="en"><p><b>FINDINGS</b></p><p>Using a development cohort (n=3,841) and a systematic machine learning framework, we identified a COVID-19 mortality predictor that demonstrated high accuracy (AUC=0.91) when applied to test sets of retrospective (n= 961) and prospective (n=249) patients. This mortality predictor was based on five clinical features: age, minimum O2 saturation during encounter, type of patient encounter (inpatient vs. various types of outpatient and telehealth encounters), hydroxychloroquine use, and maximum body temperature.</p></div><div type="abstract" xml:lang="en"><p><b>INTERPRETATION</b></p><p>An accurate and parsimonious COVID-19 mortality predictor based on five features may have utility in clinical settings to guide the management and prognostication of patients affected by this disease.</p></div></front></TEI><pubmed><MedlineCitation Status="PubMed-not-MEDLINE" Owner="NLM"><PMID Version="1">32511520</PMID><DateRevised><Year>2021</Year><Month>01</Month><Day>10</Day></DateRevised><Article PubModel="Electronic"><Journal><JournalIssue CitedMedium="Internet"><PubDate><Year>2020</Year><Month>May</Month><Day>22</Day></PubDate></JournalIssue><Title>medRxiv : the preprint server for health sciences</Title><ISOAbbreviation>medRxiv</ISOAbbreviation></Journal><ArticleTitle>Clinical predictors of COVID-19 mortality.</ArticleTitle><ELocationID EIdType="pii" ValidYN="Y">2020.05.19.20103036</ELocationID><ELocationID EIdType="doi" ValidYN="Y">10.1101/2020.05.19.20103036</ELocationID><Abstract><AbstractText Label="BACKGROUND" NlmCategory="BACKGROUND">The coronavirus disease 2019 (COVID-19) pandemic has affected over millions of individuals and caused hundreds of thousands of deaths worldwide. It can be difficult to accurately predict mortality among COVID-19 patients presenting with a spectrum of complications, hindering the prognostication and management of the disease.</AbstractText><AbstractText Label="METHODS" NlmCategory="METHODS">We applied machine learning techniques to clinical data from a large cohort of 5,051 COVID-19 patients treated at the Mount Sinai Health System in New York City, the global COVID-19 epicenter, to predict mortality. Predictors were designed to classify patients into Deceased or Alive mortality classes and were evaluated in terms of the area under the receiver operating characteristic (ROC) curve (AUC score).</AbstractText><AbstractText Label="FINDINGS" NlmCategory="RESULTS">Using a development cohort (n=3,841) and a systematic machine learning framework, we identified a COVID-19 mortality predictor that demonstrated high accuracy (AUC=0.91) when applied to test sets of retrospective (n= 961) and prospective (n=249) patients. This mortality predictor was based on five clinical features: age, minimum O2 saturation during encounter, type of patient encounter (inpatient vs. various types of outpatient and telehealth encounters), hydroxychloroquine use, and maximum body temperature.</AbstractText><AbstractText Label="INTERPRETATION" NlmCategory="CONCLUSIONS">An accurate and parsimonious COVID-19 mortality predictor based on five features may have utility in clinical settings to guide the management and prognostication of patients affected by this disease.</AbstractText></Abstract><AuthorList CompleteYN="Y"><Author ValidYN="Y"><LastName>Yadaw</LastName><ForeName>Arjun S</ForeName><Initials>AS</Initials><AffiliationInfo><Affiliation>Department of Pharmacological Sciences, Icahn School of Medicine at Mount Sinai, One Gustave L. Levy Place, Box 1215, New York, NY 10029, USA.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Li</LastName><ForeName>Yan-Chak</ForeName><Initials>YC</Initials><AffiliationInfo><Affiliation>Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, One Gustave L. Levy Place, Box 1498, New York, NY 10029, USA.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Bose</LastName><ForeName>Sonali</ForeName><Initials>S</Initials><AffiliationInfo><Affiliation>Department of Medicine, Icahn School of Medicine at Mount Sinai, One Gustave L. Levy Place, Box 1232, New York, NY 10029, USA.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Iyengar</LastName><ForeName>Ravi</ForeName><Initials>R</Initials><AffiliationInfo><Affiliation>Department of Pharmacological Sciences, Icahn School of Medicine at Mount Sinai, One Gustave L. Levy Place, Box 1215, New York, NY 10029, USA.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Bunyavanich</LastName><ForeName>Supinda</ForeName><Initials>S</Initials><AffiliationInfo><Affiliation>Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, One Gustave L. Levy Place, Box 1498, New York, NY 10029, USA.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Pandey</LastName><ForeName>Gaurav</ForeName><Initials>G</Initials><AffiliationInfo><Affiliation>Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, One Gustave L. Levy Place, Box 1498, New York, NY 10029, USA.</Affiliation></AffiliationInfo></Author></AuthorList><Language>eng</Language><GrantList CompleteYN="Y"><Grant><GrantID>R01 AI147028</GrantID><Acronym>AI</Acronym><Agency>NIAID NIH HHS</Agency><Country>United States</Country></Grant><Grant><GrantID>U19 AI136053</GrantID><Acronym>AI</Acronym><Agency>NIAID NIH HHS</Agency><Country>United States</Country></Grant><Grant><GrantID>P50 GM071558</GrantID><Acronym>GM</Acronym><Agency>NIGMS NIH HHS</Agency><Country>United States</Country></Grant><Grant><GrantID>R01 AI118833</GrantID><Acronym>AI</Acronym><Agency>NIAID NIH HHS</Agency><Country>United States</Country></Grant><Grant><GrantID>UG3 OD023337</GrantID><Acronym>OD</Acronym><Agency>NIH HHS</Agency><Country>United States</Country></Grant><Grant><GrantID>R01 HL147328</GrantID><Acronym>HL</Acronym><Agency>NHLBI NIH HHS</Agency><Country>United States</Country></Grant><Grant><GrantID>U54 HG008098</GrantID><Acronym>HG</Acronym><Agency>NHGRI NIH HHS</Agency><Country>United States</Country></Grant></GrantList><PublicationTypeList><PublicationType UI="D000076942">Preprint</PublicationType></PublicationTypeList><ArticleDate DateType="Electronic"><Year>2020</Year><Month>05</Month><Day>22</Day></ArticleDate></Article><MedlineJournalInfo><Country>United States</Country><MedlineTA>medRxiv</MedlineTA><NlmUniqueID>101767986</NlmUniqueID></MedlineJournalInfo><CommentsCorrectionsList><CommentsCorrections RefType="UpdateIn"><RefSource>Lancet Digit Health. 2020 Oct;2(10):e516-e525</RefSource><PMID Version="1">32984797</PMID></CommentsCorrections></CommentsCorrectionsList></MedlineCitation><PubmedData><History><PubMedPubDate PubStatus="entrez"><Year>2020</Year><Month>6</Month><Day>9</Day><Hour>6</Hour><Minute>0</Minute></PubMedPubDate><PubMedPubDate PubStatus="pubmed"><Year>2020</Year><Month>6</Month><Day>9</Day><Hour>6</Hour><Minute>0</Minute></PubMedPubDate><PubMedPubDate PubStatus="medline"><Year>2020</Year><Month>6</Month><Day>9</Day><Hour>6</Hour><Minute>1</Minute></PubMedPubDate></History><PublicationStatus>epublish</PublicationStatus><ArticleIdList><ArticleId IdType="pubmed">32511520</ArticleId><ArticleId IdType="doi">10.1101/2020.05.19.20103036</ArticleId><ArticleId IdType="pmc">PMC7273288</ArticleId></ArticleIdList><ReferenceList><Reference><Citation>Chest. 2020 Aug;158(2):603-607</Citation><ArticleIdList><ArticleId IdType="pubmed">32339510</ArticleId></ArticleIdList></Reference><Reference><Citation>JAMA. 2020 Apr 28;323(16):1574-1581</Citation><ArticleIdList><ArticleId IdType="pubmed">32250385</ArticleId></ArticleIdList></Reference><Reference><Citation>N Engl J Med. 2020 Apr 30;382(18):1708-1720</Citation><ArticleIdList><ArticleId IdType="pubmed">32109013</ArticleId></ArticleIdList></Reference><Reference><Citation>Respir Res. 2020 Apr 15;21(1):83</Citation><ArticleIdList><ArticleId IdType="pubmed">32293449</ArticleId></ArticleIdList></Reference><Reference><Citation>EGEMS (Wash DC). 2013 Dec 17;1(3):1035</Citation><ArticleIdList><ArticleId IdType="pubmed">25848578</ArticleId></ArticleIdList></Reference><Reference><Citation>Intensive Care Med. 2020 May;46(5):846-848</Citation><ArticleIdList><ArticleId IdType="pubmed">32125452</ArticleId></ArticleIdList></Reference><Reference><Citation>Clin Infect Dis. 2020 Jul 28;71(15):833-840</Citation><ArticleIdList><ArticleId IdType="pubmed">32296824</ArticleId></ArticleIdList></Reference><Reference><Citation>BMJ. 2020 Apr 7;369:m1328</Citation><ArticleIdList><ArticleId IdType="pubmed">32265220</ArticleId></ArticleIdList></Reference><Reference><Citation>Lancet Infect Dis. 2020 May;20(5):533-534</Citation><ArticleIdList><ArticleId IdType="pubmed">32087114</ArticleId></ArticleIdList></Reference><Reference><Citation>N Engl J Med. 2020 Jun 25;382(26):2582</Citation><ArticleIdList><ArticleId IdType="pubmed">32501665</ArticleId></ArticleIdList></Reference><Reference><Citation>Lancet. 2020 Feb 15;395(10223):497-506</Citation><ArticleIdList><ArticleId IdType="pubmed">31986264</ArticleId></ArticleIdList></Reference><Reference><Citation>Int J Antimicrob Agents. 2020 Apr;55(4):105932</Citation><ArticleIdList><ArticleId IdType="pubmed">32145363</ArticleId></ArticleIdList></Reference><Reference><Citation>JAMA. 2020 May 12;323(18):1824-1836</Citation><ArticleIdList><ArticleId IdType="pubmed">32282022</ArticleId></ArticleIdList></Reference><Reference><Citation>Lancet. 2020 Feb 15;395(10223):507-513</Citation><ArticleIdList><ArticleId IdType="pubmed">32007143</ArticleId></ArticleIdList></Reference><Reference><Citation>N Engl J Med. 2020 May 21;382(21):2012-2022</Citation><ArticleIdList><ArticleId IdType="pubmed">32227758</ArticleId></ArticleIdList></Reference><Reference><Citation>Eur Respir J. 2020 May 7;55(5):</Citation><ArticleIdList><ArticleId IdType="pubmed">32269088</ArticleId></ArticleIdList></Reference><Reference><Citation>Bioinformatics. 2007 Oct 1;23(19):2507-17</Citation><ArticleIdList><ArticleId IdType="pubmed">17720704</ArticleId></ArticleIdList></Reference><Reference><Citation>JAMA. 2020 May 26;323(20):2052-2059</Citation><ArticleIdList><ArticleId IdType="pubmed">32320003</ArticleId></ArticleIdList></Reference><Reference><Citation>Lancet. 2020 Mar 28;395(10229):1054-1062</Citation><ArticleIdList><ArticleId IdType="pubmed">32171076</ArticleId></ArticleIdList></Reference><Reference><Citation>N Engl J Med. 2020 May 7;382(19):1859</Citation><ArticleIdList><ArticleId IdType="pubmed">32220202</ArticleId></ArticleIdList></Reference><Reference><Citation>BMJ. 2020 Mar 26;368:m1091</Citation><ArticleIdList><ArticleId IdType="pubmed">32217556</ArticleId></ArticleIdList></Reference></ReferenceList></PubmedData></pubmed></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Sante/explor/CovidChloroV1/Data/Main/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 001465 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Corpus/biblio.hfd -nk 001465 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Sante
|area= CovidChloroV1
|flux= Main
|étape= Corpus
|type= RBID
|clé= pubmed:32511520
|texte= Clinical predictors of COVID-19 mortality.
}}
Pour générer des pages wiki
HfdIndexSelect -h $EXPLOR_AREA/Data/Main/Corpus/RBID.i -Sk "pubmed:32511520" \
| HfdSelect -Kh $EXPLOR_AREA/Data/Main/Corpus/biblio.hfd \
| NlmPubMed2Wicri -a CovidChloroV1
| This area was generated with Dilib version V0.6.38. |  |