<?xml version="1.0" encoding="utf-8"?>
<TEI xmlns="http://www.tei-c.org/ns/1.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:hal="http://hal.archives-ouvertes.fr/" xmlns:gml="http://www.opengis.net/gml/3.3/" xmlns:gmlce="http://www.opengis.net/gml/3.3/ce" version="1.1" xsi:schemaLocation="http://www.tei-c.org/ns/1.0 http://api.archives-ouvertes.fr/documents/aofr-sword.xsd">
  <teiHeader>
    <fileDesc>
      <titleStmt>
        <title>HAL TEI export of hal-03607651</title>
      </titleStmt>
      <publicationStmt>
        <distributor>CCSD</distributor>
        <availability status="restricted">
          <licence target="https://creativecommons.org/publicdomain/zero/1.0/">CC0 1.0 - Universal</licence>
        </availability>
        <date when="2026-05-16T23:47:54+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">How to remove or control confounds in predictive models, with applications to brain biomarkers</title>
            <author role="aut">
              <persName>
                <forename type="first">Darya</forename>
                <surname>Chyzhyk</surname>
              </persName>
              <email type="md5">1dd2fe72fb1671306f5d1fed981bfa63</email>
              <email type="domain">gmail.com</email>
              <idno type="idhal" notation="numeric">1130222</idno>
              <idno type="halauthorid" notation="string">1387566-1130222</idno>
              <affiliation ref="#struct-56051"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Gaël</forename>
                <surname>Varoquaux</surname>
              </persName>
              <email type="md5">5c9fb379c4e97b58960d74dcbfc5dee5</email>
              <email type="domain">normalesup.org</email>
              <idno type="idhal" notation="string">gael-varoquaux</idno>
              <idno type="idhal" notation="numeric">5878</idno>
              <idno type="halauthorid" notation="string">8362-5878</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-1076-5122</idno>
              <idno type="IDREF">https://www.idref.fr/126239894</idno>
              <affiliation ref="#struct-1093353"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Michael</forename>
                <surname>Milham</surname>
              </persName>
              <idno type="halauthorid">880602-0</idno>
              <affiliation ref="#struct-353393"/>
              <affiliation ref="#struct-87898"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Bertrand</forename>
                <surname>Thirion</surname>
              </persName>
              <idno type="idhal" notation="numeric">760493</idno>
              <idno type="halauthorid" notation="string">142896-760493</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-5018-7895</idno>
              <idno type="IDREF">https://www.idref.fr/080779565</idno>
              <affiliation ref="#struct-1124248"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Bertrand</forename>
                <surname>Thirion</surname>
              </persName>
              <email type="md5">7e13f0e43798e8f4736d80bff2fa694a</email>
              <email type="domain">inria.fr</email>
            </editor>
            <funder ref="#projanr-43299"/>
            <funder ref="#projeurop-712875"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2022-03-14 10:20:45</date>
              <date type="whenModified">2026-02-06 11:36:02</date>
              <date type="whenReleased">2022-03-14 14:03:12</date>
              <date type="whenProduced">2022-03-12</date>
              <date type="whenEndEmbargoed">2022-03-14</date>
              <ref type="file" target="https://inria.hal.science/hal-03607651v1/document">
                <date notBefore="2022-03-14"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://inria.hal.science/hal-03607651v1/file/giac014.pdf" id="file-3607651-3153970">
                <date notBefore="2022-03-14"/>
              </ref>
              <ref type="externalLink" target="https://academic.oup.com/gigascience/article-pdf/doi/10.1093/gigascience/giac014/42869927/giac014.pdf"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="145919">
                <persName>
                  <forename>Bertrand</forename>
                  <surname>Thirion</surname>
                </persName>
                <email type="md5">7e13f0e43798e8f4736d80bff2fa694a</email>
                <email type="domain">inria.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-03607651</idno>
            <idno type="halUri">https://inria.hal.science/hal-03607651</idno>
            <idno type="halBibtex">chyzhyk:hal-03607651</idno>
            <idno type="halRefHtml">&lt;i&gt;GigaScience&lt;/i&gt;, 2022, 11, &lt;a target="_blank" href="https://dx.doi.org/10.1093/gigascience/giac014"&gt;&amp;#x27E8;10.1093/gigascience/giac014&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">GigaScience, 2022, 11, &amp;#x27E8;10.1093/gigascience/giac014&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-3607651-3153970"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CEA">CEA - Commissariat à l'énergie atomique</idno>
            <idno type="stamp" n="INRIA">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="INRIA-SACLAY" corresp="INRIA">INRIA Saclay - Ile de France</idno>
            <idno type="stamp" n="OPENAIRE">OpenAIRE</idno>
            <idno type="stamp" n="INRIA_TEST">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="TESTALAIN1">TESTALAIN1</idno>
            <idno type="stamp" n="INRIA2">INRIA 2</idno>
            <idno type="stamp" n="CEA-UPSAY" corresp="CEA">CEA - Université Paris-Saclay</idno>
            <idno type="stamp" n="UNIV-PARIS-SACLAY">Université Paris-Saclay</idno>
            <idno type="stamp" n="JOLIOT" corresp="CEA">Institut des Sciences du Vivant Frédéric JOLIOT</idno>
            <idno type="stamp" n="CEA-DRF" corresp="CEA">Direction de Recherche Fondamentale</idno>
            <idno type="stamp" n="NEUROSPIN" corresp="JOLIOT">Département NEUROSPIN</idno>
            <idno type="stamp" n="UNIVERSITE-PARIS-SACLAY" corresp="UNIV-PARIS-SACLAY">Université Paris-Saclay</idno>
            <idno type="stamp" n="ANR">ANR</idno>
            <idno type="stamp" n="GS-ENGINEERING">Graduate School Sciences de l'Ingénierie et des Systèmes</idno>
            <idno type="stamp" n="GS-COMPUTER-SCIENCE">Graduate School Computer Science</idno>
            <idno type="stamp" n="GS-LIFE-SCIENCES-HEALTH" corresp="UNIVERSITE-PARIS-SACLAY">Graduate School Life Sciences and Health</idno>
            <idno type="stamp" n="INRIA-ETATSUNIS">Copublications Inria-Etats-Unis</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">How to remove or control confounds in predictive models, with applications to brain biomarkers</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Darya</forename>
                    <surname>Chyzhyk</surname>
                  </persName>
                  <email type="md5">1dd2fe72fb1671306f5d1fed981bfa63</email>
                  <email type="domain">gmail.com</email>
                  <idno type="idhal" notation="numeric">1130222</idno>
                  <idno type="halauthorid" notation="string">1387566-1130222</idno>
                  <affiliation ref="#struct-56051"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Gaël</forename>
                    <surname>Varoquaux</surname>
                  </persName>
                  <email type="md5">5c9fb379c4e97b58960d74dcbfc5dee5</email>
                  <email type="domain">normalesup.org</email>
                  <idno type="idhal" notation="string">gael-varoquaux</idno>
                  <idno type="idhal" notation="numeric">5878</idno>
                  <idno type="halauthorid" notation="string">8362-5878</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-1076-5122</idno>
                  <idno type="IDREF">https://www.idref.fr/126239894</idno>
                  <affiliation ref="#struct-1093353"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Michael</forename>
                    <surname>Milham</surname>
                  </persName>
                  <idno type="halauthorid">880602-0</idno>
                  <affiliation ref="#struct-353393"/>
                  <affiliation ref="#struct-87898"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Bertrand</forename>
                    <surname>Thirion</surname>
                  </persName>
                  <idno type="idhal" notation="numeric">760493</idno>
                  <idno type="halauthorid" notation="string">142896-760493</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-5018-7895</idno>
                  <idno type="IDREF">https://www.idref.fr/080779565</idno>
                  <affiliation ref="#struct-1124248"/>
                </author>
              </analytic>
              <monogr>
                <idno type="localRef">MIND</idno>
                <idno type="halJournalId" status="VALID">69034</idno>
                <idno type="eissn">2047-217X</idno>
                <title level="j">GigaScience</title>
                <imprint>
                  <publisher>Oxford Univ Press</publisher>
                  <biblScope unit="volume">11</biblScope>
                  <date type="datePub">2022-03-12</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1093/gigascience/giac014</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">deconfounding</term>
                <term xml:lang="en">statistical testing</term>
                <term xml:lang="en">biomarkers</term>
                <term xml:lang="en">predictive models</term>
                <term xml:lang="en">phenotype</term>
                <term xml:lang="en">subsampling</term>
                <term xml:lang="en">confound</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-im">Computer Science [cs]/Medical Imaging</classCode>
              <classCode scheme="halTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halOldTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halTreeTypology" n="ART">Journal articles</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>Background : With increasing data sizes and more easily available computational methods, neurosciences rely more and more on predictive modeling with machine learning, e.g., to extract disease biomarkers. Yet, a successful prediction may capture a confounding effect correlated with the outcome instead of brain features specific to the outcome of interest. For instance, because patients tend to move more in the scanner than controls, imaging biomarkers of a disease condition may mostly reflect head motion, leading to inefficient use of resources and wrong interpretation of the biomarkers. Results : Here we study how to adapt statistical methods that control for confounds to predictive modeling settings. We review how to train predictors that are not driven by such spurious effects. We also show how to measure the unbiased predictive accuracy of these biomarkers, based on a confounded dataset. For this purpose, cross-validation must be modified to account for the nuisance effect. To guide understanding and practical recommendations, we apply various strategies to assess predictive models in the presence of confounds on simulated data and population brain imaging settings. Theoretical and empirical studies show that deconfounding should not be applied to the train and test data jointly: modeling the effect of confounds, on the training data only, should instead be decoupled from removing confounds. Conclusions : Cross-validation that isolates nuisance effects gives an additional piece of information: confound-free prediction accuracy.</p>
            </abstract>
            <particDesc>
              <org type="consortium">MIND</org>
            </particDesc>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-56051" status="OLD">
          <idno type="RNSR">200919007A</idno>
          <orgName>Modelling brain structure, function and variability based on high-field MRI data</orgName>
          <orgName type="acronym">PARIETAL</orgName>
          <date type="start">2009-07-01</date>
          <date type="end">2022-03-31</date>
          <desc>
            <address>
              <addrLine>Neurospin, CEA Saclay, Bâtiment 145, 91191 Gif-sur-Yvette Cedex</addrLine>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-40417" type="direct"/>
            <relation active="#struct-419361" type="indirect"/>
            <relation active="#struct-487603" type="indirect"/>
            <relation name="DRF" active="#struct-300016" type="indirect"/>
            <relation active="#struct-118511" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-1093353" status="VALID">
          <idno type="RNSR">202224249S</idno>
          <idno type="ROR">https://ror.org/030zn8d06</idno>
          <orgName>Méthodes computationnelles et mathématiques pour comprendre la société et la santé à partir de données</orgName>
          <orgName type="acronym">SODA</orgName>
          <date type="start">2022-03-01</date>
          <date type="end">2026-02-28</date>
          <desc>
            <address>
              <addrLine>Inria Saclay – SODABâtiment Alan TuringCampus de l’École polytechnique1 rue Honoré d’Estienne d’Orves91120 Palaiseau</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://team.inria.fr/soda/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-118511" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-353393" status="VALID">
          <idno type="ROR">https://ror.org/01bfgxw09</idno>
          <orgName>Child Mind Institute</orgName>
          <desc>
            <address>
              <addrLine>101 East 56th Street, New York, NY 10022</addrLine>
              <country key="US"/>
            </address>
            <ref type="url">https://childmind.org/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-87898" status="VALID">
          <orgName>Nathan S. Kline Institute for Psychiatric Research</orgName>
          <orgName type="acronym">NKI</orgName>
          <desc>
            <address>
              <addrLine>Nathan S. Kline Institute for Psychiatric Research, 140 Old Orangeburg Road, Orangeburg, NY 10962</addrLine>
              <country key="US"/>
            </address>
            <ref type="url">http://www.rfmh.org/nki/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301650" type="direct"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-1124248" status="VALID">
          <idno type="RNSR">202224253W</idno>
          <idno type="ROR">https://ror.org/00dfknt61</idno>
          <orgName>Modèles et inférence pour les données de Neuroimagerie</orgName>
          <orgName type="acronym">MIND</orgName>
          <date type="start">2022-04-01</date>
          <date type="end">2026-03-31</date>
          <desc>
            <address>
              <addrLine>1 rue Honoré d'Estienne d'Orves Campus de l'École Polytechnique 91120 Palaiseau</addrLine>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-118170" type="direct"/>
            <relation active="#struct-300016" type="indirect"/>
            <relation active="#struct-1225627" type="direct"/>
            <relation active="#struct-118511" type="indirect"/>
            <relation active="#struct-300009" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-40417" status="VALID">
          <idno type="RNSR">201722552U</idno>
          <orgName>Service NEUROSPIN</orgName>
          <orgName type="acronym">NEUROSPIN</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://joliot.cea.fr/drf/joliot/recherche/neurospin</ref>
          </desc>
          <listRelation>
            <relation active="#struct-419361" type="direct"/>
            <relation active="#struct-487603" type="direct"/>
            <relation name="DRF" active="#struct-300016" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-419361" status="VALID">
          <idno type="IdRef">241345251</idno>
          <idno type="ROR">https://ror.org/03xjwb503</idno>
          <orgName>Université Paris-Saclay</orgName>
          <desc>
            <address>
              <addrLine>Bâtiment Bréguet, 3 Rue Joliot Curie 2e ét, 91190 Gif-sur-Yvette</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.universite-paris-saclay.fr/fr</ref>
          </desc>
        </org>
        <org type="regrouplaboratory" xml:id="struct-487603" status="VALID">
          <idno type="IdRef">262253712</idno>
          <idno type="RNSR">201722498K</idno>
          <idno type="ROR">https://ror.org/016pnwd02</idno>
          <idno type="Wikidata">Q61933008</idno>
          <orgName>Institut des Sciences du Vivant Frédéric JOLIOT</orgName>
          <orgName type="acronym">JOLIOT</orgName>
          <date type="start">2017-01-01</date>
          <desc>
            <address>
              <addrLine>DRFCEAGif-sur-Yvette</addrLine>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation name="DRF" active="#struct-300016" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-300016" status="VALID">
          <idno type="IdRef">026372061</idno>
          <idno type="ISNI">0000000122998025</idno>
          <idno type="ROR">https://ror.org/00jjx8s55</idno>
          <idno type="Wikidata">Q868550</idno>
          <orgName>Commissariat à l'énergie atomique et aux énergies alternatives</orgName>
          <orgName type="acronym">CEA</orgName>
          <desc>
            <address>
              <addrLine>Centre de SaclayCentre de GrenobleCentre de Cadaracheetc</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.cea.fr/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-118511" status="VALID">
          <idno type="RNSR">200818248E</idno>
          <idno type="ROR">https://ror.org/0315e5x55</idno>
          <orgName>Centre Inria de Saclay</orgName>
          <desc>
            <address>
              <addrLine>1 rue Honoré d'Estienne d'OrvesBâtiment Alan TuringCampus de l'École Polytechnique91120 Palaiseau</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/centre/saclay</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-300009" status="VALID">
          <idno type="ROR">https://ror.org/02kvxyf05</idno>
          <orgName>Institut National de Recherche en Informatique et en Automatique</orgName>
          <orgName type="acronym">Inria</orgName>
          <desc>
            <address>
              <addrLine>Domaine de VoluceauRocquencourt - BP 10578153 Le Chesnay Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/en/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-301650" status="VALID">
          <orgName>New York State Office of Mental Health</orgName>
          <desc>
            <address>
              <country key="US"/>
            </address>
            <ref type="url">https://omh.ny.gov/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-118170" status="VALID">
          <orgName>IFR49 - Neurospin - CEA</orgName>
          <desc>
            <address>
              <addrLine>Gif sur Yvette</addrLine>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-300016" type="direct"/>
          </listRelation>
        </org>
        <org type="department" xml:id="struct-1225627" status="VALID">
          <idno type="ROR">https://ror.org/040753f36</idno>
          <orgName>Centre Inria de l'Université Paris-Saclay</orgName>
          <date type="start">2022-11-01</date>
          <desc>
            <address>
              <addrLine>9 Rue Joliot Curie, 91190 Gif-sur-Yvette</addrLine>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-118511" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
          </listRelation>
        </org>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-43299" status="VALID">
          <idno type="anr">ANR-17-CE23-0018</idno>
          <orgName>DirtyData</orgName>
          <desc>Intégration et nettoyage de données pour l'analyse statistique</desc>
          <date type="start">2017</date>
        </org>
        <org type="europeanProject" xml:id="projeurop-712875" status="VALID">
          <idno type="number">826421</idno>
          <idno type="program">H2020-SC1-DTH-2018-2020</idno>
          <idno type="call">H2020-SC1-DTH-2018-1</idno>
          <orgName>VirtualBrainCloud</orgName>
          <desc>Personalized Recommendations for Neurodegenerative Disease</desc>
          <date type="start">2018-12-01</date>
          <date type="end">2023-05-31</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>