Performance evaluation of unified medical language system<sup>®</sup>'s synonyms expansion to query PubMed

<p>Abstract</p> <p>Background</p> <p>PubMed is the main access to medical literature on the Internet. In order to enhance the performance of its information retrieval tools, primarily non-indexed citations, the authors propose a method: expanding users' queries usi...

Full description

Bibliographic Details
Main Authors: Griffon Nicolas, Chebil Wiem, Rollin Laetitia, Kerdelhue Gaetan, Thirion Benoit, Gehanno Jean-François, Darmoni Stéfan
Format: Article
Language:English
Published: BMC 2012-02-01
Series:BMC Medical Informatics and Decision Making
Online Access:http://www.biomedcentral.com/1472-6947/12/12
_version_ 1818528749454360576
author Griffon Nicolas
Chebil Wiem
Rollin Laetitia
Kerdelhue Gaetan
Thirion Benoit
Gehanno Jean-François
Darmoni Stéfan
author_facet Griffon Nicolas
Chebil Wiem
Rollin Laetitia
Kerdelhue Gaetan
Thirion Benoit
Gehanno Jean-François
Darmoni Stéfan
author_sort Griffon Nicolas
collection DOAJ
description <p>Abstract</p> <p>Background</p> <p>PubMed is the main access to medical literature on the Internet. In order to enhance the performance of its information retrieval tools, primarily non-indexed citations, the authors propose a method: expanding users' queries using Unified Medical Language System' (UMLS) synonyms i.e. all the terms gathered under one unique Concept Unique Identifier.</p> <p>Methods</p> <p>This method was evaluated using queries constructed to emphasize the differences between this new method and the current PubMed automatic term mapping. Four experts assessed citation relevance.</p> <p>Results</p> <p>Using UMLS, we were able to retrieve new citations in 45.5% of queries, which implies a small increase in recall. The new strategy led to a heterogeneous 23.7% mean increase in non-indexed citation retrieved. Of these, 82% have been published less than 4 months earlier. The overall mean precision was 48.4% but differed according to the evaluators, ranging from 36.7% to 88.1% (Inter rater agreement was poor: kappa = 0.34).</p> <p>Conclusions</p> <p>This study highlights the need for specific search tools for each type of user and use-cases. The proposed strategy may be useful to retrieve recent scientific advancement.</p>
first_indexed 2024-12-11T06:54:03Z
format Article
id doaj.art-0e595c24979a4eaa9b036c9cabfe3245
institution Directory Open Access Journal
issn 1472-6947
language English
last_indexed 2024-12-11T06:54:03Z
publishDate 2012-02-01
publisher BMC
record_format Article
series BMC Medical Informatics and Decision Making
spelling doaj.art-0e595c24979a4eaa9b036c9cabfe32452022-12-22T01:16:48ZengBMCBMC Medical Informatics and Decision Making1472-69472012-02-011211210.1186/1472-6947-12-12Performance evaluation of unified medical language system<sup>®</sup>'s synonyms expansion to query PubMedGriffon NicolasChebil WiemRollin LaetitiaKerdelhue GaetanThirion BenoitGehanno Jean-FrançoisDarmoni Stéfan<p>Abstract</p> <p>Background</p> <p>PubMed is the main access to medical literature on the Internet. In order to enhance the performance of its information retrieval tools, primarily non-indexed citations, the authors propose a method: expanding users' queries using Unified Medical Language System' (UMLS) synonyms i.e. all the terms gathered under one unique Concept Unique Identifier.</p> <p>Methods</p> <p>This method was evaluated using queries constructed to emphasize the differences between this new method and the current PubMed automatic term mapping. Four experts assessed citation relevance.</p> <p>Results</p> <p>Using UMLS, we were able to retrieve new citations in 45.5% of queries, which implies a small increase in recall. The new strategy led to a heterogeneous 23.7% mean increase in non-indexed citation retrieved. Of these, 82% have been published less than 4 months earlier. The overall mean precision was 48.4% but differed according to the evaluators, ranging from 36.7% to 88.1% (Inter rater agreement was poor: kappa = 0.34).</p> <p>Conclusions</p> <p>This study highlights the need for specific search tools for each type of user and use-cases. The proposed strategy may be useful to retrieve recent scientific advancement.</p>http://www.biomedcentral.com/1472-6947/12/12
spellingShingle Griffon Nicolas
Chebil Wiem
Rollin Laetitia
Kerdelhue Gaetan
Thirion Benoit
Gehanno Jean-François
Darmoni Stéfan
Performance evaluation of unified medical language system<sup>®</sup>'s synonyms expansion to query PubMed
BMC Medical Informatics and Decision Making
title Performance evaluation of unified medical language system<sup>®</sup>'s synonyms expansion to query PubMed
title_full Performance evaluation of unified medical language system<sup>®</sup>'s synonyms expansion to query PubMed
title_fullStr Performance evaluation of unified medical language system<sup>®</sup>'s synonyms expansion to query PubMed
title_full_unstemmed Performance evaluation of unified medical language system<sup>®</sup>'s synonyms expansion to query PubMed
title_short Performance evaluation of unified medical language system<sup>®</sup>'s synonyms expansion to query PubMed
title_sort performance evaluation of unified medical language system sup r sup s synonyms expansion to query pubmed
url http://www.biomedcentral.com/1472-6947/12/12
work_keys_str_mv AT griffonnicolas performanceevaluationofunifiedmedicallanguagesystemsupsupssynonymsexpansiontoquerypubmed
AT chebilwiem performanceevaluationofunifiedmedicallanguagesystemsupsupssynonymsexpansiontoquerypubmed
AT rollinlaetitia performanceevaluationofunifiedmedicallanguagesystemsupsupssynonymsexpansiontoquerypubmed
AT kerdelhuegaetan performanceevaluationofunifiedmedicallanguagesystemsupsupssynonymsexpansiontoquerypubmed
AT thirionbenoit performanceevaluationofunifiedmedicallanguagesystemsupsupssynonymsexpansiontoquerypubmed
AT gehannojeanfrancois performanceevaluationofunifiedmedicallanguagesystemsupsupssynonymsexpansiontoquerypubmed
AT darmonistefan performanceevaluationofunifiedmedicallanguagesystemsupsupssynonymsexpansiontoquerypubmed