Odds per adjusted standard deviation: comparing strengths of associations for risk factors measured on different scales and across diseases and populations.
Identifieur interne : 000076 ( PubMed/Checkpoint ); précédent : 000075; suivant : 000077Odds per adjusted standard deviation: comparing strengths of associations for risk factors measured on different scales and across diseases and populations.
Auteurs : John L. HopperSource :
- American journal of epidemiology ; 2015.
English descriptors
- KwdEn :
- Age Factors, Biomarkers, Tumor, Body Mass Index, Breast Neoplasms (epidemiology), Breast Neoplasms (genetics), Epidemiologic Methods, Female, Genes, BRCA1, Genes, BRCA2, Genetic Predisposition to Disease, Humans, Ovarian Neoplasms (genetics), Probability, Regression Analysis, Research Design, Risk Factors.
- MESH :
- chemical : Biomarkers, Tumor.
- epidemiology : Breast Neoplasms.
- genetics : Breast Neoplasms, Ovarian Neoplasms.
- Age Factors, Body Mass Index, Epidemiologic Methods, Female, Genes, BRCA1, Genes, BRCA2, Genetic Predisposition to Disease, Humans, Probability, Regression Analysis, Research Design, Risk Factors.
Abstract
How can the "strengths" of risk factors, in the sense of how well they discriminate cases from controls, be compared when they are measured on different scales such as continuous, binary, and integer? Given that risk estimates take into account other fitted and design-related factors-and that is how risk gradients are interpreted-so should the presentation of risk gradients. Therefore, for each risk factor X0, I propose using appropriate regression techniques to derive from appropriate population data the best fitting relationship between the mean of X0 and all the other covariates fitted in the model or adjusted for by design (X1, X2, … , Xn). The odds per adjusted standard deviation (OPERA) presents the risk association for X0 in terms of the change in risk per s = standard deviation of X0 adjusted for X1, X2, … , Xn, rather than the unadjusted standard deviation of X0 itself. If the increased risk is relative risk (RR)-fold over A adjusted standard deviations, then OPERA = exp[ln(RR)/A] = RR(s). This unifying approach is illustrated by considering breast cancer and published risk estimates. OPERA estimates are by definition independent and can be used to compare the predictive strengths of risk factors across diseases and populations.
DOI: 10.1093/aje/kwv193
PubMed: 26520360
Affiliations:
Links toward previous steps (curation, corpus...)
Links to Exploration step
pubmed:26520360Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Odds per adjusted standard deviation: comparing strengths of associations for risk factors measured on different scales and across diseases and populations.</title><author><name sortKey="Hopper, John L" sort="Hopper, John L" uniqKey="Hopper J" first="John L" last="Hopper">John L. Hopper</name></author></titleStmt><publicationStmt><idno type="wicri:source">PubMed</idno><date when="2015">2015</date><idno type="RBID">pubmed:26520360</idno><idno type="pmid">26520360</idno><idno type="doi">10.1093/aje/kwv193</idno><idno type="wicri:Area/PubMed/Corpus">000042</idno><idno type="wicri:Area/PubMed/Curation">000042</idno><idno type="wicri:Area/PubMed/Checkpoint">000076</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en">Odds per adjusted standard deviation: comparing strengths of associations for risk factors measured on different scales and across diseases and populations.</title><author><name sortKey="Hopper, John L" sort="Hopper, John L" uniqKey="Hopper J" first="John L" last="Hopper">John L. Hopper</name></author></analytic><series><title level="j">American journal of epidemiology</title><idno type="e-ISSN">1476-6256</idno><imprint><date when="2015" type="published">2015</date></imprint></series></biblStruct></sourceDesc></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Age Factors</term><term>Biomarkers, Tumor</term><term>Body Mass Index</term><term>Breast Neoplasms (epidemiology)</term><term>Breast Neoplasms (genetics)</term><term>Epidemiologic Methods</term><term>Female</term><term>Genes, BRCA1</term><term>Genes, BRCA2</term><term>Genetic Predisposition to Disease</term><term>Humans</term><term>Ovarian Neoplasms (genetics)</term><term>Probability</term><term>Regression Analysis</term><term>Research Design</term><term>Risk Factors</term></keywords><keywords scheme="MESH" type="chemical" xml:lang="en"><term>Biomarkers, Tumor</term></keywords><keywords scheme="MESH" qualifier="epidemiology" xml:lang="en"><term>Breast Neoplasms</term></keywords><keywords scheme="MESH" qualifier="genetics" xml:lang="en"><term>Breast Neoplasms</term><term>Ovarian Neoplasms</term></keywords><keywords scheme="MESH" xml:lang="en"><term>Age Factors</term><term>Body Mass Index</term><term>Epidemiologic Methods</term><term>Female</term><term>Genes, BRCA1</term><term>Genes, BRCA2</term><term>Genetic Predisposition to Disease</term><term>Humans</term><term>Probability</term><term>Regression Analysis</term><term>Research Design</term><term>Risk Factors</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">How can the "strengths" of risk factors, in the sense of how well they discriminate cases from controls, be compared when they are measured on different scales such as continuous, binary, and integer? Given that risk estimates take into account other fitted and design-related factors-and that is how risk gradients are interpreted-so should the presentation of risk gradients. Therefore, for each risk factor X0, I propose using appropriate regression techniques to derive from appropriate population data the best fitting relationship between the mean of X0 and all the other covariates fitted in the model or adjusted for by design (X1, X2, … , Xn). The odds per adjusted standard deviation (OPERA) presents the risk association for X0 in terms of the change in risk per s = standard deviation of X0 adjusted for X1, X2, … , Xn, rather than the unadjusted standard deviation of X0 itself. If the increased risk is relative risk (RR)-fold over A adjusted standard deviations, then OPERA = exp[ln(RR)/A] = RR(s). This unifying approach is illustrated by considering breast cancer and published risk estimates. OPERA estimates are by definition independent and can be used to compare the predictive strengths of risk factors across diseases and populations.</div></front></TEI><pubmed><MedlineCitation Owner="NLM" Status="MEDLINE"><PMID Version="1">26520360</PMID><DateCreated><Year>2015</Year><Month>11</Month><Day>06</Day></DateCreated><DateCompleted><Year>2016</Year><Month>02</Month><Day>18</Day></DateCompleted><DateRevised><Year>2016</Year><Month>03</Month><Day>09</Day></DateRevised><Article PubModel="Print-Electronic"><Journal><ISSN IssnType="Electronic">1476-6256</ISSN><JournalIssue CitedMedium="Internet"><Volume>182</Volume><Issue>10</Issue><PubDate><Year>2015</Year><Month>Nov</Month><Day>15</Day></PubDate></JournalIssue><Title>American journal of epidemiology</Title><ISOAbbreviation>Am. J. Epidemiol.</ISOAbbreviation></Journal><ArticleTitle>Odds per adjusted standard deviation: comparing strengths of associations for risk factors measured on different scales and across diseases and populations.</ArticleTitle><Pagination><MedlinePgn>863-7</MedlinePgn></Pagination><ELocationID EIdType="doi" ValidYN="Y">10.1093/aje/kwv193</ELocationID><Abstract><AbstractText>How can the "strengths" of risk factors, in the sense of how well they discriminate cases from controls, be compared when they are measured on different scales such as continuous, binary, and integer? Given that risk estimates take into account other fitted and design-related factors-and that is how risk gradients are interpreted-so should the presentation of risk gradients. Therefore, for each risk factor X0, I propose using appropriate regression techniques to derive from appropriate population data the best fitting relationship between the mean of X0 and all the other covariates fitted in the model or adjusted for by design (X1, X2, … , Xn). The odds per adjusted standard deviation (OPERA) presents the risk association for X0 in terms of the change in risk per s = standard deviation of X0 adjusted for X1, X2, … , Xn, rather than the unadjusted standard deviation of X0 itself. If the increased risk is relative risk (RR)-fold over A adjusted standard deviations, then OPERA = exp[ln(RR)/A] = RR(s). This unifying approach is illustrated by considering breast cancer and published risk estimates. OPERA estimates are by definition independent and can be used to compare the predictive strengths of risk factors across diseases and populations.</AbstractText><CopyrightInformation>© The Author 2015. Published by Oxford University Press on behalf of the Johns Hopkins Bloomberg School of Public Health. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.</CopyrightInformation></Abstract><AuthorList CompleteYN="Y"><Author ValidYN="Y"><LastName>Hopper</LastName><ForeName>John L</ForeName><Initials>JL</Initials></Author></AuthorList><Language>eng</Language><GrantList CompleteYN="Y"><Grant><GrantID>5 R01 CA159868</GrantID><Acronym>CA</Acronym><Agency>NCI NIH HHS</Agency><Country>United States</Country></Grant><Grant><GrantID>R01 CA168893</GrantID><Acronym>CA</Acronym><Agency>NCI NIH HHS</Agency><Country>United States</Country></Grant><Grant><GrantID>UM1 CA164920</GrantID><Acronym>CA</Acronym><Agency>NCI NIH HHS</Agency><Country>United States</Country></Grant><Grant><GrantID>UM1 CA167551-01A1</GrantID><Acronym>CA</Acronym><Agency>NCI NIH HHS</Agency><Country>United States</Country></Grant></GrantList><PublicationTypeList><PublicationType UI="D016428">Journal Article</PublicationType><PublicationType UI="D052061">Research Support, N.I.H., Extramural</PublicationType><PublicationType UI="D013485">Research Support, Non-U.S. Gov't</PublicationType></PublicationTypeList><ArticleDate DateType="Electronic"><Year>2015</Year><Month>10</Month><Day>31</Day></ArticleDate></Article><MedlineJournalInfo><Country>United States</Country><MedlineTA>Am J Epidemiol</MedlineTA><NlmUniqueID>7910653</NlmUniqueID><ISSNLinking>0002-9262</ISSNLinking></MedlineJournalInfo><ChemicalList><Chemical><RegistryNumber>0</RegistryNumber><NameOfSubstance UI="D014408">Biomarkers, Tumor</NameOfSubstance></Chemical></ChemicalList><CitationSubset>IM</CitationSubset><CommentsCorrectionsList><CommentsCorrections RefType="Cites"><RefSource>Lancet. 2002 Jul 20;360(9328):187-95</RefSource><PMID Version="1">12133652</PMID></CommentsCorrections><CommentsCorrections RefType="Cites"><RefSource>Am J Hum Genet. 2003 May;72(5):1117-30</RefSource><PMID Version="1">12677558</PMID></CommentsCorrections><CommentsCorrections RefType="Cites"><RefSource>Biometrics. 1991 Sep;47(3):933-45</RefSource><PMID Version="1">1742447</PMID></CommentsCorrections><CommentsCorrections RefType="Cites"><RefSource>Am J Epidemiol. 1992 Nov 1;136(9):1138-47</RefSource><PMID Version="1">1462973</PMID></CommentsCorrections><CommentsCorrections RefType="Cites"><RefSource>Cancer Epidemiol Biomarkers Prev. 2013 Dec;22(12):2395-403</RefSource><PMID Version="1">24130221</PMID></CommentsCorrections><CommentsCorrections RefType="Cites"><RefSource>Am J Epidemiol. 2014 Feb 15;179(4):475-83</RefSource><PMID Version="1">24169466</PMID></CommentsCorrections><CommentsCorrections RefType="Cites"><RefSource>Ann Epidemiol. 2014 Mar;24(3):222-7</RefSource><PMID Version="1">24360852</PMID></CommentsCorrections><CommentsCorrections RefType="Cites"><RefSource>J Natl Cancer Inst. 2015 May;107(5). pii: djv036. doi: 10.1093/jnci/djv036</RefSource><PMID Version="1">25855707</PMID></CommentsCorrections></CommentsCorrectionsList><MeshHeadingList><MeshHeading><DescriptorName MajorTopicYN="N" UI="D000367">Age Factors</DescriptorName></MeshHeading><MeshHeading><DescriptorName MajorTopicYN="N" UI="D014408">Biomarkers, Tumor</DescriptorName></MeshHeading><MeshHeading><DescriptorName MajorTopicYN="N" UI="D015992">Body Mass Index</DescriptorName></MeshHeading><MeshHeading><DescriptorName MajorTopicYN="N" UI="D001943">Breast Neoplasms</DescriptorName><QualifierName MajorTopicYN="N" UI="Q000453">epidemiology</QualifierName><QualifierName MajorTopicYN="N" UI="Q000235">genetics</QualifierName></MeshHeading><MeshHeading><DescriptorName MajorTopicYN="Y" UI="D004812">Epidemiologic Methods</DescriptorName></MeshHeading><MeshHeading><DescriptorName MajorTopicYN="N" UI="D005260">Female</DescriptorName></MeshHeading><MeshHeading><DescriptorName MajorTopicYN="N" UI="D019398">Genes, BRCA1</DescriptorName></MeshHeading><MeshHeading><DescriptorName MajorTopicYN="N" UI="D024522">Genes, BRCA2</DescriptorName></MeshHeading><MeshHeading><DescriptorName MajorTopicYN="N" UI="D020022">Genetic Predisposition to Disease</DescriptorName></MeshHeading><MeshHeading><DescriptorName MajorTopicYN="N" UI="D006801">Humans</DescriptorName></MeshHeading><MeshHeading><DescriptorName MajorTopicYN="N" UI="D010051">Ovarian Neoplasms</DescriptorName><QualifierName MajorTopicYN="N" UI="Q000235">genetics</QualifierName></MeshHeading><MeshHeading><DescriptorName MajorTopicYN="N" UI="D011336">Probability</DescriptorName></MeshHeading><MeshHeading><DescriptorName MajorTopicYN="N" UI="D012044">Regression Analysis</DescriptorName></MeshHeading><MeshHeading><DescriptorName MajorTopicYN="Y" UI="D012107">Research Design</DescriptorName></MeshHeading><MeshHeading><DescriptorName MajorTopicYN="N" UI="D012307">Risk Factors</DescriptorName></MeshHeading></MeshHeadingList><OtherID Source="NLM">PMC4757943 [Available on 11/15/16]</OtherID><KeywordList Owner="NOTNLM"><Keyword MajorTopicYN="N">breast cancer</Keyword><Keyword MajorTopicYN="N">relative risk</Keyword><Keyword MajorTopicYN="N">risk factor</Keyword><Keyword MajorTopicYN="N">standard deviation</Keyword><Keyword MajorTopicYN="N">strength of association</Keyword></KeywordList></MedlineCitation><PubmedData><History><PubMedPubDate PubStatus="received"><Year>2014</Year><Month>7</Month><Day>11</Day></PubMedPubDate><PubMedPubDate PubStatus="accepted"><Year>2015</Year><Month>7</Month><Day>10</Day></PubMedPubDate><PubMedPubDate PubStatus="aheadofprint"><Year>2015</Year><Month>10</Month><Day>31</Day></PubMedPubDate><PubMedPubDate PubStatus="entrez"><Year>2015</Year><Month>11</Month><Day>2</Day><Hour>6</Hour><Minute>0</Minute></PubMedPubDate><PubMedPubDate PubStatus="pubmed"><Year>2015</Year><Month>11</Month><Day>2</Day><Hour>6</Hour><Minute>0</Minute></PubMedPubDate><PubMedPubDate PubStatus="medline"><Year>2016</Year><Month>2</Month><Day>19</Day><Hour>6</Hour><Minute>0</Minute></PubMedPubDate><PubMedPubDate PubStatus="pmc-release"><Year>2016</Year><Month>11</Month><Day>15</Day><Hour>0</Hour><Minute>0</Minute></PubMedPubDate></History><PublicationStatus>ppublish</PublicationStatus><ArticleIdList><ArticleId IdType="pubmed">26520360</ArticleId><ArticleId IdType="pii">kwv193</ArticleId><ArticleId IdType="doi">10.1093/aje/kwv193</ArticleId><ArticleId IdType="pmc">PMC4757943</ArticleId></ArticleIdList></PubmedData></pubmed><affiliations><list></list><tree><noCountry><name sortKey="Hopper, John L" sort="Hopper, John L" uniqKey="Hopper J" first="John L" last="Hopper">John L. Hopper</name></noCountry></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Musique/explor/OperaV1/Data/PubMed/Checkpoint
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000076 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/PubMed/Checkpoint/biblio.hfd -nk 000076 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Musique
|area= OperaV1
|flux= PubMed
|étape= Checkpoint
|type= RBID
|clé= pubmed:26520360
|texte= Odds per adjusted standard deviation: comparing strengths of associations for risk factors measured on different scales and across diseases and populations.
}}
Pour générer des pages wiki
HfdIndexSelect -h $EXPLOR_AREA/Data/PubMed/Checkpoint/RBID.i -Sk "pubmed:26520360" \
| HfdSelect -Kh $EXPLOR_AREA/Data/PubMed/Checkpoint/biblio.hfd \
| NlmPubMed2Wicri -a OperaV1
| This area was generated with Dilib version V0.6.21. |  |