<?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-05605622</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="2026-05-19T03:12:15+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Privacy-Preserving Generation of Synthetic Pathology Reports for Information Extraction</title>
            <author role="aut">
              <persName>
                <forename type="first">Alejandra</forename>
                <surname>Lorenzo</surname>
              </persName>
              <email type="md5">95d47ff566d9af945d7d186151ca2804</email>
              <email type="domain">loria.fr</email>
              <idno type="idhal" notation="numeric">1674484</idno>
              <idno type="halauthorid" notation="string">420120-1674484</idno>
              <affiliation ref="#struct-206040"/>
              <affiliation ref="#struct-1825025"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Adrien</forename>
                <surname>Coulet</surname>
              </persName>
              <email type="md5">cbac31e20d8f0cbf0f870c991a79335e</email>
              <email type="domain">inria.fr</email>
              <idno type="idhal" notation="string">coulet</idno>
              <idno type="idhal" notation="numeric">1742</idno>
              <idno type="halauthorid" notation="string">11918-1742</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-1466-062X</idno>
              <idno type="IDREF">https://www.idref.fr/134214099</idno>
              <affiliation ref="#struct-1226657"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Claire</forename>
                <surname>Gardent</surname>
              </persName>
              <email type="md5">2011a70cc805f691b71fc804cd7fac0e</email>
              <email type="domain">loria.fr</email>
              <idno type="idhal" notation="string">claire-gardent</idno>
              <idno type="idhal" notation="numeric">3949</idno>
              <idno type="halauthorid" notation="string">16753-3949</idno>
              <idno type="IDREF">https://www.idref.fr/034104593</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-3805-6662</idno>
              <affiliation ref="#struct-206040"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Adrien</forename>
                <surname>Coulet</surname>
              </persName>
              <email type="md5">cbac31e20d8f0cbf0f870c991a79335e</email>
              <email type="domain">inria.fr</email>
            </editor>
            <funder ref="#projanr-185719"/>
            <funder>HPC resources of IDRIS under the allocation AD011016561 made by GENCI</funder>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2026-04-28 16:47:32</date>
              <date type="whenModified">2026-05-19 03:06:15</date>
              <date type="whenReleased">2026-04-28 17:58:41</date>
              <date type="whenProduced">2026-07-07</date>
              <date type="whenEndEmbargoed">2026-04-28</date>
              <ref type="file" target="https://inria.hal.science/hal-05605622v1/document">
                <date notBefore="2026-04-28"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://inria.hal.science/hal-05605622v1/file/ale_article_2026.pdf" id="file-5605622-4802727">
                <date notBefore="2026-04-28"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="110882">
                <persName>
                  <forename>Adrien</forename>
                  <surname>Coulet</surname>
                </persName>
                <email type="md5">cbac31e20d8f0cbf0f870c991a79335e</email>
                <email type="domain">inria.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-05605622</idno>
            <idno type="halUri">https://inria.hal.science/hal-05605622</idno>
            <idno type="halBibtex">lorenzo:hal-05605622</idno>
            <idno type="halRefHtml">&lt;i&gt;AIME 2026 - International Conference on Artificial Intelligence in Medicine&lt;/i&gt;, Jul 2026, Ottawa, Canada</idno>
            <idno type="halRef">AIME 2026 - International Conference on Artificial Intelligence in Medicine, Jul 2026, Ottawa, Canada</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by-nc-nd/4.0/">CC BY-NC-ND 4.0 - Attribution - Non-commercial use - No Derivative Works<ref corresp="#file-5605622-4802727"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="INSERM">INSERM - Institut national de la santé et de la recherche médicale</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="INRIA">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="INRIA-ROCQ">INRIA Paris - Rocquencourt</idno>
            <idno type="stamp" n="LORIA2">Publications du LORIA</idno>
            <idno type="stamp" n="TESTALAIN1">TESTALAIN1</idno>
            <idno type="stamp" n="CENTRALESUPELEC">Ecole CentraleSupélec</idno>
            <idno type="stamp" n="UNIV-LORRAINE">Université de Lorraine</idno>
            <idno type="stamp" n="INRIA2">INRIA 2</idno>
            <idno type="stamp" n="GENCI">Publications ayant eu recours aux supercalculateurs du GENCI</idno>
            <idno type="stamp" n="LORIA">Laboratoire Lorrain de Recherche en Informatique et ses Applications</idno>
            <idno type="stamp" n="UNIV-PARIS">Université Paris Cité</idno>
            <idno type="stamp" n="UNIVERSITE-PARIS" corresp="UNIV-PARIS">Université Paris Cité</idno>
            <idno type="stamp" n="UP-SANTE">Université Paris Cité - Faculté de Santé</idno>
            <idno type="stamp" n="ANR">ANR</idno>
            <idno type="stamp" n="ACADEMIE-SCIENCES">Académie des sciences</idno>
            <idno type="stamp" n="ANR-IA-23" corresp="ANR-IA">ANR-IA-23</idno>
            <idno type="stamp" n="ANR-IA">ANR-IA</idno>
            <idno type="stamp" n="AM2I-UL">Pôle scientifique Automatique, Mathématiques, Informatique et leurs Intéractions de l'Université de Lorraine</idno>
            <idno type="stamp" n="ACADEMIE-SCIENCES-PUBLICATIONS-MEMBRES" corresp="ACADEMIE-SCIENCES">Publications des membres, correspondants et associés étrangers de l'Académie des sciences</idno>
            <idno type="stamp" n="ACADEMIE-SCIENCES-PUBLICATIONS-MEMBRES-3" corresp="ACADEMIE-SCIENCES-PUBLICATIONS-MEMBRES">Publications des membres de l'Académie des sciences (lot 3)</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="invited" n="0">No</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
            <note type="proceedings" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Privacy-Preserving Generation of Synthetic Pathology Reports for Information Extraction</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Alejandra</forename>
                    <surname>Lorenzo</surname>
                  </persName>
                  <email type="md5">95d47ff566d9af945d7d186151ca2804</email>
                  <email type="domain">loria.fr</email>
                  <idno type="idhal" notation="numeric">1674484</idno>
                  <idno type="halauthorid" notation="string">420120-1674484</idno>
                  <affiliation ref="#struct-206040"/>
                  <affiliation ref="#struct-1825025"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Adrien</forename>
                    <surname>Coulet</surname>
                  </persName>
                  <email type="md5">cbac31e20d8f0cbf0f870c991a79335e</email>
                  <email type="domain">inria.fr</email>
                  <idno type="idhal" notation="string">coulet</idno>
                  <idno type="idhal" notation="numeric">1742</idno>
                  <idno type="halauthorid" notation="string">11918-1742</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-1466-062X</idno>
                  <idno type="IDREF">https://www.idref.fr/134214099</idno>
                  <affiliation ref="#struct-1226657"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Claire</forename>
                    <surname>Gardent</surname>
                  </persName>
                  <email type="md5">2011a70cc805f691b71fc804cd7fac0e</email>
                  <email type="domain">loria.fr</email>
                  <idno type="idhal" notation="string">claire-gardent</idno>
                  <idno type="idhal" notation="numeric">3949</idno>
                  <idno type="halauthorid" notation="string">16753-3949</idno>
                  <idno type="IDREF">https://www.idref.fr/034104593</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-3805-6662</idno>
                  <affiliation ref="#struct-206040"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>AIME 2026 - International Conference on Artificial Intelligence in Medicine</title>
                  <date type="start">2026-07-07</date>
                  <date type="end">2026-07-10</date>
                  <settlement>Ottawa</settlement>
                  <country key="CA">Canada</country>
                </meeting>
                <imprint/>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Differential privacy</term>
                <term xml:lang="en">Synthetic data</term>
                <term xml:lang="en">Information Extraction</term>
                <term xml:lang="en">Clinical text</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-ai">Computer Science [cs]/Artificial Intelligence [cs.AI]</classCode>
              <classCode scheme="halDomain" n="sdv.can">Life Sciences [q-bio]/Cancer</classCode>
              <classCode scheme="halTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halOldTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halTreeTypology" n="COMM">Conference papers</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>A long-standing goal in clinical NLP is extracting key variables from clinical text, but progress is hindered by domain shift, limited annotated data, and privacy constraints. In this paper, we propose a novel privacy-preserving method to generate synthetic report/data pairs that support information extraction by associating LLM-generated pathology reports with thirteen variables commonly found in real reports for breast cancer patients. We first generate synthetic tabular data for these variables and their possible values, comparing several tabular synthesizers and selecting PATE-CTGAN for its strong statistical fidelity and differential privacy guarantees. We then generate pathology reports using three LLMs to maximize linguistic diversity and conditioning generation on synthetic variable-value sets. We show that a model fine-tuned on the resulting synthetic data substantially outperforms the same model without fine-tuning and improves performance over a 3-shot baseline using synthetic in-context examples, achieving 0.79 accuracy compared to 0.38 and 0.64, respectively. These results show that high-quality synthetic data can effectively compensate for limited annotated clinical data while enabling accurate and privacy-preserving clinical information extraction. The code is available at https://gitlab.inria.fr/aabdelnu/syntheticpreports.</p>
            </abstract>
            <particDesc>
              <org type="ir" xml:id="fr-esr-fdr-ir-064">
                <orgName type="acronym">GENCI</orgName>
                <idno type="wikidata">Q3093180</idno>
              </org>
            </particDesc>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-206040" status="VALID">
          <idno type="IdRef">067077927</idno>
          <idno type="ISNI">0000000121795429</idno>
          <idno type="RNSR">198912571S</idno>
          <idno type="IdUnivLorraine">[UL]RSI--</idno>
          <idno type="ROR">https://ror.org/02vnf0c38</idno>
          <orgName>Laboratoire Lorrain de Recherche en Informatique et ses Applications</orgName>
          <orgName type="acronym">LORIA</orgName>
          <date type="start">2012-01-01</date>
          <desc>
            <address>
              <addrLine>Campus Scientifique BP 239 54506 Vandoeuvre-lès-Nancy Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.loria.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
            <relation active="#struct-411575" type="direct"/>
            <relation active="#struct-413289" type="direct"/>
            <relation name="UMR7503" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-1825025" status="VALID">
          <orgName>Unité de Radiothérapie République</orgName>
          <orgName type="acronym">U2R</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <org type="researchteam" xml:id="struct-1226657" status="VALID">
          <idno type="RNSR">202124127N</idno>
          <idno type="ROR">https://ror.org/00my0j309</idno>
          <orgName>Health data-and model-driven approaches for Knowledge Acquisition</orgName>
          <orgName type="acronym">HeKA | U1346</orgName>
          <date type="start">2025-01-01</date>
          <date type="end">2026-10-31</date>
          <desc>
            <address>
              <addrLine>Paris Santé Campus : 2 - 10 Rue d'Oradour-sur-Glane 75015 PARIS</addrLine>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation name="U1346" active="#struct-303623" type="direct"/>
            <relation active="#struct-454310" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation name="UMR_S 1346" active="#struct-557826" 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-411575" status="VALID">
          <idno type="IdRef">184443237</idno>
          <idno type="ROR">https://ror.org/019tcpt25</idno>
          <orgName>CentraleSupélec</orgName>
          <desc>
            <address>
              <addrLine>3, rue Joliot Curie,Plateau de Moulon,91192 GIF-SUR-YVETTE Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.centralesupelec.fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-413289" status="VALID">
          <idno type="IdRef">157040569</idno>
          <idno type="IdUnivLorraine">[UL]100--</idno>
          <idno type="ROR">https://ror.org/04vfs2w97</idno>
          <orgName>Université de Lorraine</orgName>
          <orgName type="acronym">UL</orgName>
          <date type="start">2012-01-01</date>
          <desc>
            <address>
              <addrLine>34 cours Léopold - CS 25233 - 54052 Nancy cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-lorraine.fr/</ref>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-441569" status="VALID">
          <idno type="IdRef">02636817X</idno>
          <idno type="ISNI">0000000122597504</idno>
          <idno type="ROR">https://ror.org/02feahw73</idno>
          <orgName>Centre National de la Recherche Scientifique</orgName>
          <orgName type="acronym">CNRS</orgName>
          <date type="start">1939-10-19</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.cnrs.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-303623" status="VALID">
          <idno type="IdRef">026388278</idno>
          <idno type="ROR">https://ror.org/02vjkv261</idno>
          <orgName>Institut National de la Santé et de la Recherche Médicale</orgName>
          <orgName type="acronym">INSERM</orgName>
          <desc>
            <address>
              <addrLine>101, rue de Tolbiac, 75013 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inserm.fr</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-454310" status="VALID">
          <idno type="IdRef">241614864</idno>
          <idno type="RNSR">196718247G</idno>
          <idno type="ROR">https://ror.org/05eyd5d35</idno>
          <orgName>Centre Inria de Paris</orgName>
          <date type="start">2016-03-10</date>
          <desc>
            <address>
              <addrLine>48 Rue Barrault, 75013 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/centre/paris</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-557826" status="VALID">
          <idno type="IdRef">236453505</idno>
          <idno type="ISNI">0000 0004 7885 7602</idno>
          <idno type="ROR">https://ror.org/05f82e368</idno>
          <orgName>Université Paris Cité</orgName>
          <orgName type="acronym">UPCité</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>85 boulevard Saint-Germain75006 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://u-paris.fr/</ref>
          </desc>
        </org>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-185719" status="VALID">
          <idno type="anr">ANR-23-IACL-0004</idno>
          <orgName>ENACT</orgName>
          <desc>European Center on Artificial Intelligence Through Innovation</desc>
          <date type="start">2023</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>