Hypothetical case replacement can be used to quantify the robustness of trial results.
Identifieur interne : 000216 ( Main/Corpus ); précédent : 000215; suivant : 000217Hypothetical case replacement can be used to quantify the robustness of trial results.
Auteurs : Kenneth A. Frank ; Qinyun Lin ; Spiro Maroulis ; Anna S. Mueller ; Ran Xu ; Joshua M. Rosenberg ; Christopher S. Hayter ; Ramy A. Mahmoud ; Marynia Kolak ; Thomas Dietz ; Lixin ZhangSource :
- Journal of clinical epidemiology [ 1878-5921 ] ; 2021.
Abstract
OBJECTIVES
We apply a general case replacement framework for quantifying the robustness of causal inferences to characterize the uncertainty of findings from clinical trials.
STUDY DESIGN AND SETTING
We express the robustness of inferences as the amount of data that must be replaced to change the conclusion and relate this to the fragility of trial results used for dichotomous outcomes. We illustrate our approach in the context of an RCT of hydroxychloroquine on pneumonia in COVID-19 patients and a cumulative meta-analysis of the effect of antihypertensive treatments on stroke.
RESULTS
We developed the Robustness of an Inference to Replacement (RIR), which quantifies how many treatment cases with positive outcomes would have to be replaced with hypothetical patients who did not receive a treatment to change an inference. The RIR addresses known limitations of the Fragility Index by accounting for the observed rates of outcomes. It can be used for varying thresholds for inference, including clinical importance.
CONCLUSION
Because the RIR expresses uncertainty in terms of patient experiences, it is more relatable to stakeholders than P-values alone. It helps identify when results are statistically significant, but conclusions are not robust, while considering the rareness of events in the underlying data.
DOI: 10.1016/j.jclinepi.2021.01.025
PubMed: 33737070
Links to Exploration step
pubmed:33737070Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Hypothetical case replacement can be used to quantify the robustness of trial results.</title><author><name sortKey="Frank, Kenneth A" sort="Frank, Kenneth A" uniqKey="Frank K" first="Kenneth A" last="Frank">Kenneth A. Frank</name><affiliation><nlm:affiliation>Measurement and Quantitative Methods, Education; Agriculture and Natural Resources, Michigan State University, East Lansing, MI. Electronic address: kenfrank@msu.edu.</nlm:affiliation></affiliation></author><author><name sortKey="Lin, Qinyun" sort="Lin, Qinyun" uniqKey="Lin Q" first="Qinyun" last="Lin">Qinyun Lin</name><affiliation><nlm:affiliation>Center for Spatial Data Science, University of Chicago, Chicago IL.</nlm:affiliation></affiliation></author><author><name sortKey="Maroulis, Spiro" sort="Maroulis, Spiro" uniqKey="Maroulis S" first="Spiro" last="Maroulis">Spiro Maroulis</name><affiliation><nlm:affiliation>School of Public Affairs, Arizona State University, Phoenix, AZ.</nlm:affiliation></affiliation></author><author><name sortKey="Mueller, Anna S" sort="Mueller, Anna S" uniqKey="Mueller A" first="Anna S" last="Mueller">Anna S. Mueller</name><affiliation><nlm:affiliation>Department of Sociology, Indiana University, Bloomington, IN.</nlm:affiliation></affiliation></author><author><name sortKey="Xu, Ran" sort="Xu, Ran" uniqKey="Xu R" first="Ran" last="Xu">Ran Xu</name><affiliation><nlm:affiliation>Department of Allied Health Sciences, University of Connecticut, Storrs, CT.</nlm:affiliation></affiliation></author><author><name sortKey="Rosenberg, Joshua M" sort="Rosenberg, Joshua M" uniqKey="Rosenberg J" first="Joshua M" last="Rosenberg">Joshua M. Rosenberg</name><affiliation><nlm:affiliation>Education, Health and Human Sciences, University of Tennessee, Knoxville.</nlm:affiliation></affiliation></author><author><name sortKey="Hayter, Christopher S" sort="Hayter, Christopher S" uniqKey="Hayter C" first="Christopher S" last="Hayter">Christopher S. Hayter</name><affiliation><nlm:affiliation>School of Public Affairs, Arizona State University, Phoenix, AZ.</nlm:affiliation></affiliation></author><author><name sortKey="Mahmoud, Ramy A" sort="Mahmoud, Ramy A" uniqKey="Mahmoud R" first="Ramy A" last="Mahmoud">Ramy A. Mahmoud</name><affiliation><nlm:affiliation>Optinose, Inc. Yardley, PA.</nlm:affiliation></affiliation></author><author><name sortKey="Kolak, Marynia" sort="Kolak, Marynia" uniqKey="Kolak M" first="Marynia" last="Kolak">Marynia Kolak</name><affiliation><nlm:affiliation>Center for Spatial Data Science, University of Chicago, Chicago IL.</nlm:affiliation></affiliation></author><author><name sortKey="Dietz, Thomas" sort="Dietz, Thomas" uniqKey="Dietz T" first="Thomas" last="Dietz">Thomas Dietz</name><affiliation><nlm:affiliation>Environmental Science and Policy, Sociology, Animal Studies, Michigan State University, East Lansing, MI.</nlm:affiliation></affiliation></author><author><name sortKey="Zhang, Lixin" sort="Zhang, Lixin" uniqKey="Zhang L" first="Lixin" last="Zhang">Lixin Zhang</name><affiliation><nlm:affiliation>Epidemiology and Biostatistics, Microbiology and Molecular Genetics, Michigan State University, East Lansing, MI.</nlm:affiliation></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">PubMed</idno><date when="2021">2021</date><idno type="RBID">pubmed:33737070</idno><idno type="pmid">33737070</idno><idno type="doi">10.1016/j.jclinepi.2021.01.025</idno><idno type="wicri:Area/Main/Corpus">000216</idno><idno type="wicri:explorRef" wicri:stream="Main" wicri:step="Corpus" wicri:corpus="PubMed">000216</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en">Hypothetical case replacement can be used to quantify the robustness of trial results.</title><author><name sortKey="Frank, Kenneth A" sort="Frank, Kenneth A" uniqKey="Frank K" first="Kenneth A" last="Frank">Kenneth A. Frank</name><affiliation><nlm:affiliation>Measurement and Quantitative Methods, Education; Agriculture and Natural Resources, Michigan State University, East Lansing, MI. Electronic address: kenfrank@msu.edu.</nlm:affiliation></affiliation></author><author><name sortKey="Lin, Qinyun" sort="Lin, Qinyun" uniqKey="Lin Q" first="Qinyun" last="Lin">Qinyun Lin</name><affiliation><nlm:affiliation>Center for Spatial Data Science, University of Chicago, Chicago IL.</nlm:affiliation></affiliation></author><author><name sortKey="Maroulis, Spiro" sort="Maroulis, Spiro" uniqKey="Maroulis S" first="Spiro" last="Maroulis">Spiro Maroulis</name><affiliation><nlm:affiliation>School of Public Affairs, Arizona State University, Phoenix, AZ.</nlm:affiliation></affiliation></author><author><name sortKey="Mueller, Anna S" sort="Mueller, Anna S" uniqKey="Mueller A" first="Anna S" last="Mueller">Anna S. Mueller</name><affiliation><nlm:affiliation>Department of Sociology, Indiana University, Bloomington, IN.</nlm:affiliation></affiliation></author><author><name sortKey="Xu, Ran" sort="Xu, Ran" uniqKey="Xu R" first="Ran" last="Xu">Ran Xu</name><affiliation><nlm:affiliation>Department of Allied Health Sciences, University of Connecticut, Storrs, CT.</nlm:affiliation></affiliation></author><author><name sortKey="Rosenberg, Joshua M" sort="Rosenberg, Joshua M" uniqKey="Rosenberg J" first="Joshua M" last="Rosenberg">Joshua M. Rosenberg</name><affiliation><nlm:affiliation>Education, Health and Human Sciences, University of Tennessee, Knoxville.</nlm:affiliation></affiliation></author><author><name sortKey="Hayter, Christopher S" sort="Hayter, Christopher S" uniqKey="Hayter C" first="Christopher S" last="Hayter">Christopher S. Hayter</name><affiliation><nlm:affiliation>School of Public Affairs, Arizona State University, Phoenix, AZ.</nlm:affiliation></affiliation></author><author><name sortKey="Mahmoud, Ramy A" sort="Mahmoud, Ramy A" uniqKey="Mahmoud R" first="Ramy A" last="Mahmoud">Ramy A. Mahmoud</name><affiliation><nlm:affiliation>Optinose, Inc. Yardley, PA.</nlm:affiliation></affiliation></author><author><name sortKey="Kolak, Marynia" sort="Kolak, Marynia" uniqKey="Kolak M" first="Marynia" last="Kolak">Marynia Kolak</name><affiliation><nlm:affiliation>Center for Spatial Data Science, University of Chicago, Chicago IL.</nlm:affiliation></affiliation></author><author><name sortKey="Dietz, Thomas" sort="Dietz, Thomas" uniqKey="Dietz T" first="Thomas" last="Dietz">Thomas Dietz</name><affiliation><nlm:affiliation>Environmental Science and Policy, Sociology, Animal Studies, Michigan State University, East Lansing, MI.</nlm:affiliation></affiliation></author><author><name sortKey="Zhang, Lixin" sort="Zhang, Lixin" uniqKey="Zhang L" first="Lixin" last="Zhang">Lixin Zhang</name><affiliation><nlm:affiliation>Epidemiology and Biostatistics, Microbiology and Molecular Genetics, Michigan State University, East Lansing, MI.</nlm:affiliation></affiliation></author></analytic><series><title level="j">Journal of clinical epidemiology</title><idno type="eISSN">1878-5921</idno><imprint><date when="2021" type="published">2021</date></imprint></series></biblStruct></sourceDesc></fileDesc><profileDesc><textClass></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en"><p><b>OBJECTIVES</b></p><p>We apply a general case replacement framework for quantifying the robustness of causal inferences to characterize the uncertainty of findings from clinical trials.</p></div><div type="abstract" xml:lang="en"><p><b>STUDY DESIGN AND SETTING</b></p><p>We express the robustness of inferences as the amount of data that must be replaced to change the conclusion and relate this to the fragility of trial results used for dichotomous outcomes. We illustrate our approach in the context of an RCT of hydroxychloroquine on pneumonia in COVID-19 patients and a cumulative meta-analysis of the effect of antihypertensive treatments on stroke.</p></div><div type="abstract" xml:lang="en"><p><b>RESULTS</b></p><p>We developed the Robustness of an Inference to Replacement (RIR), which quantifies how many treatment cases with positive outcomes would have to be replaced with hypothetical patients who did not receive a treatment to change an inference. The RIR addresses known limitations of the Fragility Index by accounting for the observed rates of outcomes. It can be used for varying thresholds for inference, including clinical importance.</p></div><div type="abstract" xml:lang="en"><p><b>CONCLUSION</b></p><p>Because the RIR expresses uncertainty in terms of patient experiences, it is more relatable to stakeholders than P-values alone. It helps identify when results are statistically significant, but conclusions are not robust, while considering the rareness of events in the underlying data.</p></div></front></TEI><pubmed><MedlineCitation Status="In-Data-Review" Owner="NLM"><PMID Version="1">33737070</PMID><DateRevised><Year>2021</Year><Month>05</Month><Day>21</Day></DateRevised><Article PubModel="Print-Electronic"><Journal><ISSN IssnType="Electronic">1878-5921</ISSN><JournalIssue CitedMedium="Internet"><Volume>134</Volume><PubDate><Year>2021</Year><Month>Jun</Month></PubDate></JournalIssue><Title>Journal of clinical epidemiology</Title><ISOAbbreviation>J Clin Epidemiol</ISOAbbreviation></Journal><ArticleTitle>Hypothetical case replacement can be used to quantify the robustness of trial results.</ArticleTitle><Pagination><MedlinePgn>150-159</MedlinePgn></Pagination><ELocationID EIdType="pii" ValidYN="Y">S0895-4356(21)00036-6</ELocationID><ELocationID EIdType="doi" ValidYN="Y">10.1016/j.jclinepi.2021.01.025</ELocationID><Abstract><AbstractText Label="OBJECTIVES" NlmCategory="OBJECTIVE">We apply a general case replacement framework for quantifying the robustness of causal inferences to characterize the uncertainty of findings from clinical trials.</AbstractText><AbstractText Label="STUDY DESIGN AND SETTING" NlmCategory="METHODS">We express the robustness of inferences as the amount of data that must be replaced to change the conclusion and relate this to the fragility of trial results used for dichotomous outcomes. We illustrate our approach in the context of an RCT of hydroxychloroquine on pneumonia in COVID-19 patients and a cumulative meta-analysis of the effect of antihypertensive treatments on stroke.</AbstractText><AbstractText Label="RESULTS" NlmCategory="RESULTS">We developed the Robustness of an Inference to Replacement (RIR), which quantifies how many treatment cases with positive outcomes would have to be replaced with hypothetical patients who did not receive a treatment to change an inference. The RIR addresses known limitations of the Fragility Index by accounting for the observed rates of outcomes. It can be used for varying thresholds for inference, including clinical importance.</AbstractText><AbstractText Label="CONCLUSION" NlmCategory="CONCLUSIONS">Because the RIR expresses uncertainty in terms of patient experiences, it is more relatable to stakeholders than P-values alone. It helps identify when results are statistically significant, but conclusions are not robust, while considering the rareness of events in the underlying data.</AbstractText><CopyrightInformation>Copyright © 2021 Elsevier Inc. All rights reserved.</CopyrightInformation></Abstract><AuthorList CompleteYN="Y"><Author ValidYN="Y"><LastName>Frank</LastName><ForeName>Kenneth A</ForeName><Initials>KA</Initials><AffiliationInfo><Affiliation>Measurement and Quantitative Methods, Education; Agriculture and Natural Resources, Michigan State University, East Lansing, MI. Electronic address: kenfrank@msu.edu.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Lin</LastName><ForeName>Qinyun</ForeName><Initials>Q</Initials><AffiliationInfo><Affiliation>Center for Spatial Data Science, University of Chicago, Chicago IL.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Maroulis</LastName><ForeName>Spiro</ForeName><Initials>S</Initials><AffiliationInfo><Affiliation>School of Public Affairs, Arizona State University, Phoenix, AZ.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Mueller</LastName><ForeName>Anna S</ForeName><Initials>AS</Initials><AffiliationInfo><Affiliation>Department of Sociology, Indiana University, Bloomington, IN.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Xu</LastName><ForeName>Ran</ForeName><Initials>R</Initials><AffiliationInfo><Affiliation>Department of Allied Health Sciences, University of Connecticut, Storrs, CT.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Rosenberg</LastName><ForeName>Joshua M</ForeName><Initials>JM</Initials><AffiliationInfo><Affiliation>Education, Health and Human Sciences, University of Tennessee, Knoxville.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Hayter</LastName><ForeName>Christopher S</ForeName><Initials>CS</Initials><AffiliationInfo><Affiliation>School of Public Affairs, Arizona State University, Phoenix, AZ.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Mahmoud</LastName><ForeName>Ramy A</ForeName><Initials>RA</Initials><AffiliationInfo><Affiliation>Optinose, Inc. Yardley, PA.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Kolak</LastName><ForeName>Marynia</ForeName><Initials>M</Initials><AffiliationInfo><Affiliation>Center for Spatial Data Science, University of Chicago, Chicago IL.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Dietz</LastName><ForeName>Thomas</ForeName><Initials>T</Initials><AffiliationInfo><Affiliation>Environmental Science and Policy, Sociology, Animal Studies, Michigan State University, East Lansing, MI.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Zhang</LastName><ForeName>Lixin</ForeName><Initials>L</Initials><AffiliationInfo><Affiliation>Epidemiology and Biostatistics, Microbiology and Molecular Genetics, Michigan State University, East Lansing, MI.</Affiliation></AffiliationInfo></Author></AuthorList><Language>eng</Language><PublicationTypeList><PublicationType UI="D016428">Journal Article</PublicationType></PublicationTypeList><ArticleDate DateType="Electronic"><Year>2021</Year><Month>03</Month><Day>15</Day></ArticleDate></Article><MedlineJournalInfo><Country>United States</Country><MedlineTA>J Clin Epidemiol</MedlineTA><NlmUniqueID>8801383</NlmUniqueID><ISSNLinking>0895-4356</ISSNLinking></MedlineJournalInfo><CitationSubset>IM</CitationSubset><KeywordList Owner="NOTNLM"><Keyword MajorTopicYN="N">Case replacement</Keyword><Keyword MajorTopicYN="N">Clinical importance</Keyword><Keyword MajorTopicYN="N">Fragility</Keyword><Keyword MajorTopicYN="N">Randomized controlled trials</Keyword><Keyword MajorTopicYN="N">Robustness of findings</Keyword><Keyword MajorTopicYN="N">Statistical significance</Keyword></KeywordList></MedlineCitation><PubmedData><History><PubMedPubDate PubStatus="received"><Year>2020</Year><Month>08</Month><Day>24</Day></PubMedPubDate><PubMedPubDate PubStatus="revised"><Year>2020</Year><Month>12</Month><Day>02</Day></PubMedPubDate><PubMedPubDate PubStatus="accepted"><Year>2021</Year><Month>01</Month><Day>08</Day></PubMedPubDate><PubMedPubDate PubStatus="pubmed"><Year>2021</Year><Month>3</Month><Day>20</Day><Hour>6</Hour><Minute>0</Minute></PubMedPubDate><PubMedPubDate PubStatus="medline"><Year>2021</Year><Month>3</Month><Day>20</Day><Hour>6</Hour><Minute>0</Minute></PubMedPubDate><PubMedPubDate PubStatus="entrez"><Year>2021</Year><Month>3</Month><Day>19</Day><Hour>6</Hour><Minute>17</Minute></PubMedPubDate></History><PublicationStatus>ppublish</PublicationStatus><ArticleIdList><ArticleId IdType="pubmed">33737070</ArticleId><ArticleId IdType="pii">S0895-4356(21)00036-6</ArticleId><ArticleId IdType="doi">10.1016/j.jclinepi.2021.01.025</ArticleId></ArticleIdList></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 000216 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Corpus/biblio.hfd -nk 000216 | 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:33737070
|texte= Hypothetical case replacement can be used to quantify the robustness of trial results.
}}
Pour générer des pages wiki
HfdIndexSelect -h $EXPLOR_AREA/Data/Main/Corpus/RBID.i -Sk "pubmed:33737070" \
| HfdSelect -Kh $EXPLOR_AREA/Data/Main/Corpus/biblio.hfd \
| NlmPubMed2Wicri -a CovidChloroV1
| This area was generated with Dilib version V0.6.38. |  |