A novel application of the Intent to Attend assessment to reduce bias due to missing data in a randomized controlled clinical trial
Identifieur interne : 001067 ( Pmc/Corpus ); précédent : 001066; suivant : 001068A novel application of the Intent to Attend assessment to reduce bias due to missing data in a randomized controlled clinical trial
Auteurs : Dustin J. Rabideau ; Andrew A. Nierenberg ; Louisa G. Sylvia ; Edward S. Friedman ; Charles L. Bowden ; Michael E. Thase ; Terence Ketter ; Michael J. Ostacher ; Noreen Reilly-Harrington ; Dan V. Iosifescu ; Joseph R. Calabrese ; Andrew C. Leon ; David A. SchoenfeldSource :
- Clinical trials (London, England) [ 1740-7745 ] ; 2014.
Abstract
Missing data are unavoidable in most randomized controlled clinical trials, especially when measurements are taken repeatedly. If strong assumptions about the missing data are not accurate, crude statistical analyses are biased and can lead to false inferences. Furthermore, if we fail to measure all predictors of missing data, we may not be able to model the missing data process sufficiently. In longitudinal randomized trials, measuring a patient's intent to attend future study visits may help to address both of these problems. Leon et al. developed and included the
The purpose of this study is to assess the performance of the
We fit marginal models to assess whether a patient's self-rated intent predicted actual study adherence. We applied inverse probability of attrition weighting (IPAW) coupled with patient intent to assess whether there existed treatment group differences in response over time. We compared the IPAW results to those obtained using other methods.
Patient-rated intent predicted missed study visits, even when adjusting for other predictors of missing data. On average, the hazard of retention increased by 19% for every one-point increase in intent. We also found that more severe mania, male gender, and a previously missed visit predicted subsequent absence. Although we found no difference in response between the randomized treatment groups, IPAW increased the estimated group difference over time.
LiTMUS was designed to limit missed study visits, which may have attenuated the effects of adjusting for missing data. Additionally, IPAW can be less efficient and less powerful than maximum likelihood or Bayesian estimators, given that the parametric model is well-specified.
In LiTMUS, the
Url:
DOI: 10.1177/1740774514531096
PubMed: 24872362
PubMed Central: 4247354
Links to Exploration step
PMC:4247354Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">A novel application of the <italic>Intent to Attend</italic> assessment to reduce bias due to missing data in a randomized controlled clinical trial</title><author><name sortKey="Rabideau, Dustin J" sort="Rabideau, Dustin J" uniqKey="Rabideau D" first="Dustin J" last="Rabideau">Dustin J. Rabideau</name></author><author><name sortKey="Nierenberg, Andrew A" sort="Nierenberg, Andrew A" uniqKey="Nierenberg A" first="Andrew A" last="Nierenberg">Andrew A. Nierenberg</name></author><author><name sortKey="Sylvia, Louisa G" sort="Sylvia, Louisa G" uniqKey="Sylvia L" first="Louisa G" last="Sylvia">Louisa G. Sylvia</name></author><author><name sortKey="Friedman, Edward S" sort="Friedman, Edward S" uniqKey="Friedman E" first="Edward S." last="Friedman">Edward S. Friedman</name></author><author><name sortKey="Bowden, Charles L" sort="Bowden, Charles L" uniqKey="Bowden C" first="Charles L." last="Bowden">Charles L. Bowden</name></author><author><name sortKey="Thase, Michael E" sort="Thase, Michael E" uniqKey="Thase M" first="Michael E." last="Thase">Michael E. Thase</name></author><author><name sortKey="Ketter, Terence" sort="Ketter, Terence" uniqKey="Ketter T" first="Terence" last="Ketter">Terence Ketter</name></author><author><name sortKey="Ostacher, Michael J" sort="Ostacher, Michael J" uniqKey="Ostacher M" first="Michael J." last="Ostacher">Michael J. Ostacher</name></author><author><name sortKey="Reilly Harrington, Noreen" sort="Reilly Harrington, Noreen" uniqKey="Reilly Harrington N" first="Noreen" last="Reilly-Harrington">Noreen Reilly-Harrington</name></author><author><name sortKey="Iosifescu, Dan V" sort="Iosifescu, Dan V" uniqKey="Iosifescu D" first="Dan V." last="Iosifescu">Dan V. Iosifescu</name></author><author><name sortKey="Calabrese, Joseph R" sort="Calabrese, Joseph R" uniqKey="Calabrese J" first="Joseph R." last="Calabrese">Joseph R. Calabrese</name></author><author><name sortKey="Leon, Andrew C" sort="Leon, Andrew C" uniqKey="Leon A" first="Andrew C." last="Leon">Andrew C. Leon</name></author><author><name sortKey="Schoenfeld, David A" sort="Schoenfeld, David A" uniqKey="Schoenfeld D" first="David A" last="Schoenfeld">David A. Schoenfeld</name></author></titleStmt><publicationStmt><idno type="wicri:source">PMC</idno><idno type="pmid">24872362</idno><idno type="pmc">4247354</idno><idno type="url">http://www.ncbi.nlm.nih.gov/pmc/articles/PMC4247354</idno><idno type="RBID">PMC:4247354</idno><idno type="doi">10.1177/1740774514531096</idno><date when="2014">2014</date><idno type="wicri:Area/Pmc/Corpus">001067</idno><idno type="wicri:explorRef" wicri:stream="Pmc" wicri:step="Corpus" wicri:corpus="PMC">001067</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en" level="a" type="main">A novel application of the <italic>Intent to Attend</italic> assessment to reduce bias due to missing data in a randomized controlled clinical trial</title><author><name sortKey="Rabideau, Dustin J" sort="Rabideau, Dustin J" uniqKey="Rabideau D" first="Dustin J" last="Rabideau">Dustin J. Rabideau</name></author><author><name sortKey="Nierenberg, Andrew A" sort="Nierenberg, Andrew A" uniqKey="Nierenberg A" first="Andrew A" last="Nierenberg">Andrew A. Nierenberg</name></author><author><name sortKey="Sylvia, Louisa G" sort="Sylvia, Louisa G" uniqKey="Sylvia L" first="Louisa G" last="Sylvia">Louisa G. Sylvia</name></author><author><name sortKey="Friedman, Edward S" sort="Friedman, Edward S" uniqKey="Friedman E" first="Edward S." last="Friedman">Edward S. Friedman</name></author><author><name sortKey="Bowden, Charles L" sort="Bowden, Charles L" uniqKey="Bowden C" first="Charles L." last="Bowden">Charles L. Bowden</name></author><author><name sortKey="Thase, Michael E" sort="Thase, Michael E" uniqKey="Thase M" first="Michael E." last="Thase">Michael E. Thase</name></author><author><name sortKey="Ketter, Terence" sort="Ketter, Terence" uniqKey="Ketter T" first="Terence" last="Ketter">Terence Ketter</name></author><author><name sortKey="Ostacher, Michael J" sort="Ostacher, Michael J" uniqKey="Ostacher M" first="Michael J." last="Ostacher">Michael J. Ostacher</name></author><author><name sortKey="Reilly Harrington, Noreen" sort="Reilly Harrington, Noreen" uniqKey="Reilly Harrington N" first="Noreen" last="Reilly-Harrington">Noreen Reilly-Harrington</name></author><author><name sortKey="Iosifescu, Dan V" sort="Iosifescu, Dan V" uniqKey="Iosifescu D" first="Dan V." last="Iosifescu">Dan V. Iosifescu</name></author><author><name sortKey="Calabrese, Joseph R" sort="Calabrese, Joseph R" uniqKey="Calabrese J" first="Joseph R." last="Calabrese">Joseph R. Calabrese</name></author><author><name sortKey="Leon, Andrew C" sort="Leon, Andrew C" uniqKey="Leon A" first="Andrew C." last="Leon">Andrew C. Leon</name></author><author><name sortKey="Schoenfeld, David A" sort="Schoenfeld, David A" uniqKey="Schoenfeld D" first="David A" last="Schoenfeld">David A. Schoenfeld</name></author></analytic><series><title level="j">Clinical trials (London, England)</title><idno type="ISSN">1740-7745</idno><idno type="eISSN">1740-7753</idno><imprint><date when="2014">2014</date></imprint></series></biblStruct></sourceDesc></fileDesc><profileDesc><textClass></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en"><sec id="S1"><title>Background</title><p id="P1">Missing data are unavoidable in most randomized controlled clinical trials, especially when measurements are taken repeatedly. If strong assumptions about the missing data are not accurate, crude statistical analyses are biased and can lead to false inferences. Furthermore, if we fail to measure all predictors of missing data, we may not be able to model the missing data process sufficiently. In longitudinal randomized trials, measuring a patient's intent to attend future study visits may help to address both of these problems. Leon et al. developed and included the <italic>Intent to Attend</italic> assessment in the Lithium Treatment—Moderate dose Use Study (LiTMUS), aiming to remove bias due to missing data from the primary study hypothesis [<xref rid="R1" ref-type="bibr">1</xref>].</p></sec><sec id="S2"><title>Purpose</title><p id="P2">The purpose of this study is to assess the performance of the <italic>Intent to Attend</italic> assessment with regard to its use in a sensitivity analysis of missing data.</p></sec><sec id="S3"><title>Methods</title><p id="P3">We fit marginal models to assess whether a patient's self-rated intent predicted actual study adherence. We applied inverse probability of attrition weighting (IPAW) coupled with patient intent to assess whether there existed treatment group differences in response over time. We compared the IPAW results to those obtained using other methods.</p></sec><sec id="S4"><title>Results</title><p id="P4">Patient-rated intent predicted missed study visits, even when adjusting for other predictors of missing data. On average, the hazard of retention increased by 19% for every one-point increase in intent. We also found that more severe mania, male gender, and a previously missed visit predicted subsequent absence. Although we found no difference in response between the randomized treatment groups, IPAW increased the estimated group difference over time.</p></sec><sec id="S5"><title>Limitations</title><p id="P5">LiTMUS was designed to limit missed study visits, which may have attenuated the effects of adjusting for missing data. Additionally, IPAW can be less efficient and less powerful than maximum likelihood or Bayesian estimators, given that the parametric model is well-specified.</p></sec><sec id="S6"><title>Conclusions</title><p id="P6">In LiTMUS, the <italic>Intent to Attend</italic> assessment predicted missed study visits. This item was incorporated into our IPAW models and helped reduce bias due to informative missing data. This analysis should both encourage and facilitate future use of the <italic>Intent to Attend</italic> assessment along with IPAW to address missing data in a randomized trial.</p></sec></div></front></TEI><pmc article-type="research-article"><pmc-comment>The publisher of this article does not allow downloading of the full text in XML form.</pmc-comment>
<pmc-dir>properties manuscript</pmc-dir>
<front><journal-meta><journal-id journal-id-type="nlm-journal-id">101197451</journal-id><journal-id journal-id-type="pubmed-jr-id">32521</journal-id><journal-id journal-id-type="nlm-ta">Clin Trials</journal-id><journal-id journal-id-type="iso-abbrev">Clin Trials</journal-id><journal-title-group><journal-title>Clinical trials (London, England)</journal-title></journal-title-group><issn pub-type="ppub">1740-7745</issn><issn pub-type="epub">1740-7753</issn></journal-meta><article-meta><article-id pub-id-type="pmid">24872362</article-id><article-id pub-id-type="pmc">4247354</article-id><article-id pub-id-type="doi">10.1177/1740774514531096</article-id><article-id pub-id-type="manuscript">NIHMS577757</article-id><article-categories><subj-group subj-group-type="heading"><subject>Article</subject></subj-group></article-categories><title-group><article-title>A novel application of the <italic>Intent to Attend</italic> assessment to reduce bias due to missing data in a randomized controlled clinical trial</article-title></title-group><contrib-group><contrib contrib-type="author"><name><surname>Rabideau</surname><given-names>Dustin J</given-names></name><degrees>M.S.</degrees><aff id="A1">Massachusetts General Hospital</aff></contrib><contrib contrib-type="author"><name><surname>Nierenberg</surname><given-names>Andrew A</given-names></name><degrees>M.D.</degrees><aff id="A2">Massachusetts General Hospital</aff></contrib><contrib contrib-type="author"><name><surname>Sylvia</surname><given-names>Louisa G</given-names></name><degrees>Ph.D.</degrees><aff id="A3">Massachusetts General Hospital</aff></contrib><contrib contrib-type="author"><name><surname>Friedman</surname><given-names>Edward S.</given-names></name><degrees>M.D.</degrees><aff id="A4">University of Pittsburgh School of Medicine</aff></contrib><contrib contrib-type="author"><name><surname>Bowden</surname><given-names>Charles L.</given-names></name><degrees>M.D.</degrees><aff id="A5">University of Texas Health Science Center, San Antonio</aff></contrib><contrib contrib-type="author"><name><surname>Thase</surname><given-names>Michael E.</given-names></name><degrees>M.D.</degrees><aff id="A6">University of Pennsylvania School of Medicine</aff></contrib><contrib contrib-type="author"><name><surname>Ketter</surname><given-names>Terence</given-names></name><degrees>M.D.</degrees><aff id="A7">Stanford University</aff></contrib><contrib contrib-type="author"><name><surname>Ostacher</surname><given-names>Michael J.</given-names></name><degrees>M.D., M.P.H., M.S.C.</degrees><aff id="A8">Stanford University</aff></contrib><contrib contrib-type="author"><name><surname>Reilly-Harrington</surname><given-names>Noreen</given-names></name><degrees>Ph.D.</degrees><aff id="A9">Massachusetts General Hospital</aff></contrib><contrib contrib-type="author"><name><surname>Iosifescu</surname><given-names>Dan V.</given-names></name><degrees>M.D.</degrees><aff id="A10">Mount Sinai School of Medicine</aff></contrib><contrib contrib-type="author"><name><surname>Calabrese</surname><given-names>Joseph R.</given-names></name><degrees>M.D.</degrees><aff id="A11">Case Western Reserve Univ. School of Medicine</aff></contrib><contrib contrib-type="author"><name><surname>Leon</surname><given-names>Andrew C.</given-names></name><degrees>Ph.D.</degrees><aff id="A12">Weill Cornell Medical College</aff></contrib><contrib contrib-type="author"><name><surname>Schoenfeld</surname><given-names>David A</given-names></name><degrees>Ph.D.</degrees><aff id="A13">Massachusetts General Hospital</aff></contrib></contrib-group><author-notes><corresp id="CR1"><bold>Corresponding author:</bold> Dustin J Rabideau, Biostatistics Center, Massachusetts General Hospital, 50 Staniford St, Suite 560, Boston, MA, USA, <email>drabideau@partners.edu</email></corresp></author-notes><pub-date pub-type="nihms-submitted"><day>8</day><month>5</month><year>2014</year></pub-date><pub-date pub-type="epub"><day>28</day><month>5</month><year>2014</year></pub-date><pub-date pub-type="ppub"><month>8</month><year>2014</year></pub-date><pub-date pub-type="pmc-release"><day>28</day><month>11</month><year>2015</year></pub-date><volume>11</volume><issue>4</issue><fpage>494</fpage><lpage>502</lpage><pmc-comment>elocation-id from pubmed: 10.1177/1740774514531096</pmc-comment>
<abstract><sec id="S1"><title>Background</title><p id="P1">Missing data are unavoidable in most randomized controlled clinical trials, especially when measurements are taken repeatedly. If strong assumptions about the missing data are not accurate, crude statistical analyses are biased and can lead to false inferences. Furthermore, if we fail to measure all predictors of missing data, we may not be able to model the missing data process sufficiently. In longitudinal randomized trials, measuring a patient's intent to attend future study visits may help to address both of these problems. Leon et al. developed and included the <italic>Intent to Attend</italic> assessment in the Lithium Treatment—Moderate dose Use Study (LiTMUS), aiming to remove bias due to missing data from the primary study hypothesis [<xref rid="R1" ref-type="bibr">1</xref>].</p></sec><sec id="S2"><title>Purpose</title><p id="P2">The purpose of this study is to assess the performance of the <italic>Intent to Attend</italic> assessment with regard to its use in a sensitivity analysis of missing data.</p></sec><sec id="S3"><title>Methods</title><p id="P3">We fit marginal models to assess whether a patient's self-rated intent predicted actual study adherence. We applied inverse probability of attrition weighting (IPAW) coupled with patient intent to assess whether there existed treatment group differences in response over time. We compared the IPAW results to those obtained using other methods.</p></sec><sec id="S4"><title>Results</title><p id="P4">Patient-rated intent predicted missed study visits, even when adjusting for other predictors of missing data. On average, the hazard of retention increased by 19% for every one-point increase in intent. We also found that more severe mania, male gender, and a previously missed visit predicted subsequent absence. Although we found no difference in response between the randomized treatment groups, IPAW increased the estimated group difference over time.</p></sec><sec id="S5"><title>Limitations</title><p id="P5">LiTMUS was designed to limit missed study visits, which may have attenuated the effects of adjusting for missing data. Additionally, IPAW can be less efficient and less powerful than maximum likelihood or Bayesian estimators, given that the parametric model is well-specified.</p></sec><sec id="S6"><title>Conclusions</title><p id="P6">In LiTMUS, the <italic>Intent to Attend</italic> assessment predicted missed study visits. This item was incorporated into our IPAW models and helped reduce bias due to informative missing data. This analysis should both encourage and facilitate future use of the <italic>Intent to Attend</italic> assessment along with IPAW to address missing data in a randomized trial.</p></sec></abstract><kwd-group><kwd>intent to attend</kwd><kwd>inverse probability weighting</kwd><kwd>attrition</kwd><kwd>intermittent missing data</kwd><kwd>bipolar disorder</kwd><kwd>LiTMUS</kwd></kwd-group></article-meta></front></pmc></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Amérique/explor/PittsburghV1/Data/Pmc/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 001067 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Pmc/Corpus/biblio.hfd -nk 001067 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Amérique
|area= PittsburghV1
|flux= Pmc
|étape= Corpus
|type= RBID
|clé= PMC:4247354
|texte= A novel application of the Intent to Attend assessment to reduce bias due to missing data in a randomized controlled clinical trial
}}
Pour générer des pages wiki
HfdIndexSelect -h $EXPLOR_AREA/Data/Pmc/Corpus/RBID.i -Sk "pubmed:24872362" \
| HfdSelect -Kh $EXPLOR_AREA/Data/Pmc/Corpus/biblio.hfd \
| NlmPubMed2Wicri -a PittsburghV1
| This area was generated with Dilib version V0.6.38. |  |