Comparison and combination of several MeSH indexing approaches

Comparison and combination of several MeSH indexing approaches

MeSH indexing of MEDLINE is becoming a more difficult task for the group of highly qualified indexing staff at the US National Library of Medicine, due to the large yearly growth of MEDLINE and the increasing size of MeSH. Since 2002, this task has been assisted by the Medical Text Indexer or MTI pr...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:AMIA ... Annual Symposium proceedings 2013, Vol.2013, p.709-718
Hauptverfasser: Yepes, Antonio Jose Jimeno, Mork, James G, Demner-Fushman, Dina, Aronson, Alan R
Format: Artikel
Sprache:eng
Schlagworte:
Abstracting and Indexing as Topic - methods
Algorithms
Artificial Intelligence
Medical Subject Headings
MEDLINE
Natural Language Processing
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 718
container_issue
container_start_page 709
container_title AMIA ... Annual Symposium proceedings
container_volume 2013
creator Yepes, Antonio Jose Jimeno
Mork, James G
Demner-Fushman, Dina
Aronson, Alan R
description MeSH indexing of MEDLINE is becoming a more difficult task for the group of highly qualified indexing staff at the US National Library of Medicine, due to the large yearly growth of MEDLINE and the increasing size of MeSH. Since 2002, this task has been assisted by the Medical Text Indexer or MTI program. We extend previous machine learning analysis by adding a more diverse set of MeSH headings targeting examples where MTI has been shown to perform poorly. Machine learning algorithms exceed MTI's performance on MeSH headings that are used very frequently and headings for which the indexing frequency is very low. We find that when we combine the MTI suggestions and the prediction of the learning algorithms, the performance improves compared to any single method for most of the evaluated MeSH headings.
format Article
fullrecord <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_3900212</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1500691352</sourcerecordid><originalsourceid>FETCH-LOGICAL-p181t-e612b1bb8303716554cd6b720165a986a9310ed23758c7dba19b28d51218ce3c3</originalsourceid><addsrcrecordid>eNpVkE1LAzEQhoMgtlb_guzRy0Im2WR3LwUpagsVD-o55GPaRnaTdbMt-u9dsYqeZoYZnudlTsgUhKjzgpZyQs5TeqW0KEUlz8iEFUIAL2FK5ovYdrr3KYZMB5fZ2Bof9ODHOW6yhAfsdZM94NMy88Hhuw_bTHddH7XdYbogpxvdJLw81hl5ubt9Xizz9eP9anGzzjuoYMhRAjNgTMXpaJVCFNZJUzI69rqupK45UHSMj_ls6YyG2rDKCWBQWeSWz8j8m9vtTYvOYhjGWKrrfav7DxW1V_83we_UNh4UryllwEbA9RHQx7c9pkG1PllsGh0w7pMCQamsgYuv06u_rl_Jz9P4J2kYZ54</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1500691352</pqid></control><display><type>article</type><title>Comparison and combination of several MeSH indexing approaches</title><source>MEDLINE</source><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><source>PubMed Central</source><creator>Yepes, Antonio Jose Jimeno ; Mork, James G ; Demner-Fushman, Dina ; Aronson, Alan R</creator><creatorcontrib>Yepes, Antonio Jose Jimeno ; Mork, James G ; Demner-Fushman, Dina ; Aronson, Alan R</creatorcontrib><description>MeSH indexing of MEDLINE is becoming a more difficult task for the group of highly qualified indexing staff at the US National Library of Medicine, due to the large yearly growth of MEDLINE and the increasing size of MeSH. Since 2002, this task has been assisted by the Medical Text Indexer or MTI program. We extend previous machine learning analysis by adding a more diverse set of MeSH headings targeting examples where MTI has been shown to perform poorly. Machine learning algorithms exceed MTI's performance on MeSH headings that are used very frequently and headings for which the indexing frequency is very low. We find that when we combine the MTI suggestions and the prediction of the learning algorithms, the performance improves compared to any single method for most of the evaluated MeSH headings.</description><identifier>EISSN: 1559-4076</identifier><identifier>PMID: 24551371</identifier><language>eng</language><publisher>United States: American Medical Informatics Association</publisher><subject>Abstracting and Indexing as Topic - methods ; Algorithms ; Artificial Intelligence ; Medical Subject Headings ; MEDLINE ; Natural Language Processing</subject><ispartof>AMIA ... Annual Symposium proceedings, 2013, Vol.2013, p.709-718</ispartof><rights>2013 AMIA - All rights reserved. 2013</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC3900212/pdf/$$EPDF$$P50$$Gpubmedcentral$$H</linktopdf><linktohtml>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC3900212/$$EHTML$$P50$$Gpubmedcentral$$H</linktohtml><link.rule.ids>230,314,723,776,780,881,4010,53769,53771</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/24551371$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Yepes, Antonio Jose Jimeno</creatorcontrib><creatorcontrib>Mork, James G</creatorcontrib><creatorcontrib>Demner-Fushman, Dina</creatorcontrib><creatorcontrib>Aronson, Alan R</creatorcontrib><title>Comparison and combination of several MeSH indexing approaches</title><title>AMIA ... Annual Symposium proceedings</title><addtitle>AMIA Annu Symp Proc</addtitle><description>MeSH indexing of MEDLINE is becoming a more difficult task for the group of highly qualified indexing staff at the US National Library of Medicine, due to the large yearly growth of MEDLINE and the increasing size of MeSH. Since 2002, this task has been assisted by the Medical Text Indexer or MTI program. We extend previous machine learning analysis by adding a more diverse set of MeSH headings targeting examples where MTI has been shown to perform poorly. Machine learning algorithms exceed MTI's performance on MeSH headings that are used very frequently and headings for which the indexing frequency is very low. We find that when we combine the MTI suggestions and the prediction of the learning algorithms, the performance improves compared to any single method for most of the evaluated MeSH headings.</description><subject>Abstracting and Indexing as Topic - methods</subject><subject>Algorithms</subject><subject>Artificial Intelligence</subject><subject>Medical Subject Headings</subject><subject>MEDLINE</subject><subject>Natural Language Processing</subject><issn>1559-4076</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2013</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><recordid>eNpVkE1LAzEQhoMgtlb_guzRy0Im2WR3LwUpagsVD-o55GPaRnaTdbMt-u9dsYqeZoYZnudlTsgUhKjzgpZyQs5TeqW0KEUlz8iEFUIAL2FK5ovYdrr3KYZMB5fZ2Bof9ODHOW6yhAfsdZM94NMy88Hhuw_bTHddH7XdYbogpxvdJLw81hl5ubt9Xizz9eP9anGzzjuoYMhRAjNgTMXpaJVCFNZJUzI69rqupK45UHSMj_ls6YyG2rDKCWBQWeSWz8j8m9vtTYvOYhjGWKrrfav7DxW1V_83we_UNh4UryllwEbA9RHQx7c9pkG1PllsGh0w7pMCQamsgYuv06u_rl_Jz9P4J2kYZ54</recordid><startdate>2013</startdate><enddate>2013</enddate><creator>Yepes, Antonio Jose Jimeno</creator><creator>Mork, James G</creator><creator>Demner-Fushman, Dina</creator><creator>Aronson, Alan R</creator><general>American Medical Informatics Association</general><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>7X8</scope><scope>5PM</scope></search><sort><creationdate>2013</creationdate><title>Comparison and combination of several MeSH indexing approaches</title><author>Yepes, Antonio Jose Jimeno ; Mork, James G ; Demner-Fushman, Dina ; Aronson, Alan R</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-p181t-e612b1bb8303716554cd6b720165a986a9310ed23758c7dba19b28d51218ce3c3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2013</creationdate><topic>Abstracting and Indexing as Topic - methods</topic><topic>Algorithms</topic><topic>Artificial Intelligence</topic><topic>Medical Subject Headings</topic><topic>MEDLINE</topic><topic>Natural Language Processing</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Yepes, Antonio Jose Jimeno</creatorcontrib><creatorcontrib>Mork, James G</creatorcontrib><creatorcontrib>Demner-Fushman, Dina</creatorcontrib><creatorcontrib>Aronson, Alan R</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>AMIA ... Annual Symposium proceedings</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Yepes, Antonio Jose Jimeno</au><au>Mork, James G</au><au>Demner-Fushman, Dina</au><au>Aronson, Alan R</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Comparison and combination of several MeSH indexing approaches</atitle><jtitle>AMIA ... Annual Symposium proceedings</jtitle><addtitle>AMIA Annu Symp Proc</addtitle><date>2013</date><risdate>2013</risdate><volume>2013</volume><spage>709</spage><epage>718</epage><pages>709-718</pages><eissn>1559-4076</eissn><abstract>MeSH indexing of MEDLINE is becoming a more difficult task for the group of highly qualified indexing staff at the US National Library of Medicine, due to the large yearly growth of MEDLINE and the increasing size of MeSH. Since 2002, this task has been assisted by the Medical Text Indexer or MTI program. We extend previous machine learning analysis by adding a more diverse set of MeSH headings targeting examples where MTI has been shown to perform poorly. Machine learning algorithms exceed MTI's performance on MeSH headings that are used very frequently and headings for which the indexing frequency is very low. We find that when we combine the MTI suggestions and the prediction of the learning algorithms, the performance improves compared to any single method for most of the evaluated MeSH headings.</abstract><cop>United States</cop><pub>American Medical Informatics Association</pub><pmid>24551371</pmid><tpages>10</tpages></addata></record>
fulltext fulltext
identifier EISSN: 1559-4076
ispartof AMIA ... Annual Symposium proceedings, 2013, Vol.2013, p.709-718
issn 1559-4076
language eng
recordid cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_3900212
source MEDLINE; Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals; PubMed Central
subjects Abstracting and Indexing as Topic - methods
Algorithms
Artificial Intelligence
Medical Subject Headings
MEDLINE
Natural Language Processing
title Comparison and combination of several MeSH indexing approaches
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-28T02%3A27%3A38IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Comparison%20and%20combination%20of%20several%20MeSH%20indexing%20approaches&rft.jtitle=AMIA%20...%20Annual%20Symposium%20proceedings&rft.au=Yepes,%20Antonio%20Jose%20Jimeno&rft.date=2013&rft.volume=2013&rft.spage=709&rft.epage=718&rft.pages=709-718&rft.eissn=1559-4076&rft_id=info:doi/&rft_dat=%3Cproquest_pubme%3E1500691352%3C/proquest_pubme%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=1500691352&rft_id=info:pmid/24551371&rfr_iscdi=true