<?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-02428771</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="2026-05-18T22:22:43+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Terminologies augmented recurrent neural network model for clinical named entity recognition</title>
            <author role="aut">
              <persName>
                <forename type="first">Ivan</forename>
                <surname>Lerner</surname>
              </persName>
              <idno type="idhal" notation="numeric">799102</idno>
              <idno type="halauthorid" notation="string">1745762-799102</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-5466-1707</idno>
              <affiliation ref="#struct-557826"/>
              <affiliation ref="#struct-300068"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Nicolas</forename>
                <surname>Paris</surname>
              </persName>
              <email type="md5">b9d078b625f4d72b605f49dfe6a49f98</email>
              <email type="domain">limsi.fr</email>
              <idno type="idhal" notation="numeric">1152225</idno>
              <idno type="halauthorid" notation="string">248399-1152225</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-1533-5087</idno>
              <affiliation ref="#struct-300068"/>
              <affiliation ref="#struct-1041968"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Xavier</forename>
                <surname>Tannier</surname>
              </persName>
              <email type="md5">2bb58c32aed6ba0e82f442d1853eb8f9</email>
              <email type="domain">sorbonne-universite.fr</email>
              <idno type="idhal" notation="string">xtannier</idno>
              <idno type="idhal" notation="numeric">18076</idno>
              <idno type="halauthorid" notation="string">3654-18076</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-2452-8868</idno>
              <idno type="IDREF">https://www.idref.fr/113391722</idno>
              <idno type="VIAF">https://viaf.org/viaf/159966816</idno>
              <idno type="ISNI">http://isni.org/isni/0000000356945129</idno>
              <affiliation ref="#struct-542073"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Accord Elsevier</forename>
                <surname>CCSD</surname>
              </persName>
              <email type="md5">3cc0cc7b8e3329bfb7423fa2578d788e</email>
              <email type="domain">ccsd.cnrs.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2022-07-21 09:43:58</date>
              <date type="whenModified">2026-04-01 03:13:36</date>
              <date type="whenReleased">2022-07-21 09:44:04</date>
              <date type="whenProduced">2020-02</date>
              <date type="whenEndEmbargoed">2020-12-24</date>
              <ref type="file" target="https://hal.science/hal-02428771v1/document">
                <date notBefore="2020-12-24"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-02428771v1/file/S1532046419302734.pdf" id="file-3732088-3260174">
                <date notBefore="2020-12-24"/>
              </ref>
              <ref type="externalLink" target="http://arxiv.org/pdf/1904.11473"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="1081876">
                <persName>
                  <forename>Accord Elsevier</forename>
                  <surname>CCSD</surname>
                </persName>
                <email type="md5">3cc0cc7b8e3329bfb7423fa2578d788e</email>
                <email type="domain">ccsd.cnrs.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-02428771</idno>
            <idno type="halUri">https://hal.science/hal-02428771</idno>
            <idno type="halBibtex">lerner:hal-02428771</idno>
            <idno type="halRefHtml">&lt;i&gt;Journal of Biomedical Informatics&lt;/i&gt;, 2020, 102, pp.103356. &lt;a target="_blank" href="https://dx.doi.org/10.1016/j.jbi.2019.103356"&gt;&amp;#x27E8;10.1016/j.jbi.2019.103356&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">Journal of Biomedical Informatics, 2020, 102, pp.103356. &amp;#x27E8;10.1016/j.jbi.2019.103356&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by-nc/4.0/">CC BY-NC 4.0 - Attribution - Non-commercial use<ref corresp="#file-3732088-3260174"/></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="UNIV-PARIS13">Université Paris-Nord - Paris XIII </idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="APHP" corresp="INSERM">AP-HP</idno>
            <idno type="stamp" n="LIMSI">Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur</idno>
            <idno type="stamp" n="LIMICS" corresp="SORBONNE-UNIVERSITE">Laboratoire d'Informatique Médicale et Ingénierie des Connaissances en e-Santé</idno>
            <idno type="stamp" n="USPC">Université Sorbonne Paris Cité</idno>
            <idno type="stamp" n="UNIV-PARIS-SACLAY">Université Paris-Saclay</idno>
            <idno type="stamp" n="SORBONNE-UNIVERSITE">Sorbonne Université</idno>
            <idno type="stamp" n="SORBONNE-UNIV" corresp="SORBONNE-UNIVERSITE">Sorbonne Université 01/01/2018</idno>
            <idno type="stamp" n="SU-SCIENCES" corresp="SORBONNE-UNIVERSITE">Faculté des Sciences de Sorbonne Université</idno>
            <idno type="stamp" n="IBHGC" corresp="UNIV-PARIS13">Institut de Biomécanique Humaine Georges Charpak</idno>
            <idno type="stamp" n="SORBONNE-PARIS-NORD">Université Sorbonne Paris Nord</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="TEST-HALCNRS">Collection test HAL CNRS</idno>
            <idno type="stamp" n="UNIVERSITE-PARIS-SACLAY" corresp="UNIV-PARIS-SACLAY">Université Paris-Saclay</idno>
            <idno type="stamp" n="SU-TI">Sorbonne Université - Texte Intégral</idno>
            <idno type="stamp" n="LISN">Laboratoire Interdisciplinaire des Sciences du Numérique</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="ELSEVIER">Import Elsevier</idno>
            <idno type="stamp" n="ALLIANCE-SU"> Alliance Sorbonne Université</idno>
            <idno type="stamp" n="ACT-R" corresp="UNIV-PARIS13">Act'R </idno>
            <idno type="stamp" n="SUPRA_INGENIERIE">Ingénierie</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">Terminologies augmented recurrent neural network model for clinical named entity recognition</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Ivan</forename>
                    <surname>Lerner</surname>
                  </persName>
                  <idno type="idhal" notation="numeric">799102</idno>
                  <idno type="halauthorid" notation="string">1745762-799102</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-5466-1707</idno>
                  <affiliation ref="#struct-557826"/>
                  <affiliation ref="#struct-300068"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Nicolas</forename>
                    <surname>Paris</surname>
                  </persName>
                  <email type="md5">b9d078b625f4d72b605f49dfe6a49f98</email>
                  <email type="domain">limsi.fr</email>
                  <idno type="idhal" notation="numeric">1152225</idno>
                  <idno type="halauthorid" notation="string">248399-1152225</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-1533-5087</idno>
                  <affiliation ref="#struct-300068"/>
                  <affiliation ref="#struct-1041968"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Xavier</forename>
                    <surname>Tannier</surname>
                  </persName>
                  <email type="md5">2bb58c32aed6ba0e82f442d1853eb8f9</email>
                  <email type="domain">sorbonne-universite.fr</email>
                  <idno type="idhal" notation="string">xtannier</idno>
                  <idno type="idhal" notation="numeric">18076</idno>
                  <idno type="halauthorid" notation="string">3654-18076</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-2452-8868</idno>
                  <idno type="IDREF">https://www.idref.fr/113391722</idno>
                  <idno type="VIAF">https://viaf.org/viaf/159966816</idno>
                  <idno type="ISNI">http://isni.org/isni/0000000356945129</idno>
                  <affiliation ref="#struct-542073"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">11440</idno>
                <idno type="issn">1532-0464</idno>
                <idno type="eissn">1532-0480</idno>
                <title level="j">Journal of Biomedical Informatics</title>
                <imprint>
                  <publisher>Elsevier</publisher>
                  <biblScope unit="volume">102</biblScope>
                  <biblScope unit="pp">103356</biblScope>
                  <date type="datePub">2020-02</date>
                </imprint>
              </monogr>
              <idno type="arxiv">1904.11473</idno>
              <idno type="doi">10.1016/j.jbi.2019.103356</idno>
              <idno type="pii">S1532-0464(19)30273-4</idno>
              <idno type="pubmed">31837473</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Named entity recognition</term>
                <term xml:lang="en">Machine learning</term>
                <term xml:lang="en">Information extraction</term>
                <term xml:lang="en">Clinical natural language processing</term>
                <term xml:lang="en">APcNER</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-cl">Computer Science [cs]/Computation and Language [cs.CL]</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>OBJECTIVE:We aimed to enhance the performance of a supervised model for clinical named-entity recognition (NER) using medical terminologies. In order to evaluate our system in French, we built a corpus for 5 types of clinical entities.METHODS:We used a terminology-based system as baseline, built upon UMLS and SNOMED. Then, we evaluated a biGRU-CRF, and a hybrid system using the prediction of the terminology-based system as feature for the biGRU-CRF. In French, we built APcNER, a corpus of 147 documents annotated for 5 entities (Drug names, Signs or symptoms, Diseases or disorders, Diagnostic procedures or lab tests and Therapeutic procedures). We evaluated each NER systems using exact and partial match definition of F-measure for NER. The APcNER contains 4,837 entities, which took 28 h to annotate. The inter-annotator agreement as measured by Cohen's Kappa was substantial for non-exact match (Κ = 0.61) and moderate considering exact match (Κ = 0.42). In English, we evaluated the NER systems on the i2b2-2009 Medication Challenge for Drug name recognition, which contained 8,573 entities for 268 documents, and i2b2-small a version reduced to match APcNER number of entities.RESULTS:For drug name recognition on both i2b2-2009 and APcNER, the biGRU-CRF performed better that the terminology-based system, with an exact-match F-measure of 91.1% versus 73% and 81.9% versus 75% respectively. For i2b2-small and APcNER, the hybrid system outperformed the biGRU-CRF, with an exact-match F-measure of 87.8% versus 85.6% and 86.4% versus 81.9% respectively. On APcNER corpus, the micro-average F-measure of the hybrid system on the 5 entities was 69.5% in exact match and 84.1% in non-exact match.CONCLUSION:APcNER is a French corpus for clinical-NER of five types of entities which covers a large variety of document types. The extension of the supervised model with terminology has allowed an easy increase in performance, especially for rare entities, and established near state of the art results on the i2b2-2009 corpus.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <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>
        <org type="regroupinstitution" xml:id="struct-300068" status="VALID">
          <idno type="ROR">https://ror.org/00pg5jh14</idno>
          <orgName>Assistance publique - Hôpitaux de Paris (AP-HP)</orgName>
          <orgName type="acronym">AP-HP</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-1041968" status="OLD">
          <orgName>Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur</orgName>
          <orgName type="acronym">LIMSI</orgName>
          <date type="start">2020-01-01</date>
          <date type="end">2020-12-31</date>
          <desc>
            <address>
              <addrLine>Bâtiment 507, rue du Belvédère,91405, Orsay cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.limsi.fr/fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-419361" type="direct"/>
            <relation name="UPR3251" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-542073" status="OLD">
          <idno type="RNSR">201420870D</idno>
          <orgName>Laboratoire d'Informatique Médicale et Ingénierie des Connaissances en e-Santé</orgName>
          <orgName type="acronym">LIMICS</orgName>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>Campus des Cordeliers/Escalier D - 15 rue de l'Ecole de Médecine 75006 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://ics.upmc.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-15786" type="direct"/>
            <relation name="U1142" active="#struct-303623" type="direct"/>
            <relation active="#struct-413221" type="direct"/>
          </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="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-15786" status="VALID">
          <idno type="ROR">https://ror.org/05f82e368</idno>
          <orgName>Université Paris 13</orgName>
          <orgName type="acronym">UP13</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-paris13.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="regroupinstitution" xml:id="struct-413221" status="VALID">
          <idno type="IdRef">221333754</idno>
          <idno type="ROR">https://ror.org/02en5vm52</idno>
          <orgName>Sorbonne Université</orgName>
          <orgName type="acronym">SU</orgName>
          <date type="start">2018-01-01</date>
          <desc>
            <address>
              <addrLine>21 rue de l’École de médecine - 75006 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.sorbonne-universite.fr/</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>