The Effect of XML Markup on Retrieval of Clinical Documents
Identifieur interne : 000B04 ( Main/Exploration ); précédent : 000B03; suivant : 000B05The Effect of XML Markup on Retrieval of Clinical Documents
Auteurs : Catherine Arnott SmithSource :
- AMIA Annual Symposium Proceedings [ 1942-597X ] ; 2003.
Abstract
To determine the effect on clinical information retrieval of structuring typical clinical documents in XML, according to the general guidelines of Health Level Seven’s Clinical Document Architecture.
One thousand clinical documents of eight frequently occurring types were deidentified and marked up in XML for access using a Web browser. Fifty information-seeking tasks were posed to subjects. The tasks were comprised of two typical clinical question types —individual patient results reporting and cohort identification. A control group of physician subjects could perform only free-text, keyword searching. The treatment group’s interface permitted field-based searching of particular sections within each document. Differences in precision and other measures of search success across and between question types were investigated for statistical significance.
No statistically significant differences were found between the control and treatment conditions in mean time elapsed or the mean number of records in the final result set. In fact, tasks performed in the treatment condition required a mean number of
These findings are in line with Tange et al.
Url:
PubMed: 14728246
PubMed Central: 1480078
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Pmc, to step Corpus: 000161
- to stream Pmc, to step Curation: 000161
- to stream Pmc, to step Checkpoint: 000058
- to stream Ncbi, to step Merge: 000061
- to stream Ncbi, to step Curation: 000061
- to stream Ncbi, to step Checkpoint: 000061
- to stream Main, to step Merge: 000B21
- to stream Main, to step Curation: 000B04
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">The Effect of XML Markup on Retrieval of Clinical Documents</title>
<author><name sortKey="Smith, Catherine Arnott" sort="Smith, Catherine Arnott" uniqKey="Smith C" first="Catherine Arnott" last="Smith">Catherine Arnott Smith</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">PMC</idno>
<idno type="pmid">14728246</idno>
<idno type="pmc">1480078</idno>
<idno type="url">http://www.ncbi.nlm.nih.gov/pmc/articles/PMC1480078</idno>
<idno type="RBID">PMC:1480078</idno>
<date when="2003">2003</date>
<idno type="wicri:Area/Pmc/Corpus">000161</idno>
<idno type="wicri:explorRef" wicri:stream="Pmc" wicri:step="Corpus" wicri:corpus="PMC">000161</idno>
<idno type="wicri:Area/Pmc/Curation">000161</idno>
<idno type="wicri:explorRef" wicri:stream="Pmc" wicri:step="Curation">000161</idno>
<idno type="wicri:Area/Pmc/Checkpoint">000058</idno>
<idno type="wicri:explorRef" wicri:stream="Pmc" wicri:step="Checkpoint">000058</idno>
<idno type="wicri:Area/Ncbi/Merge">000061</idno>
<idno type="wicri:Area/Ncbi/Curation">000061</idno>
<idno type="wicri:Area/Ncbi/Checkpoint">000061</idno>
<idno type="wicri:Area/Main/Merge">000B21</idno>
<idno type="wicri:Area/Main/Curation">000B04</idno>
<idno type="wicri:Area/Main/Exploration">000B04</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a" type="main">The Effect of XML Markup on Retrieval of Clinical Documents</title>
<author><name sortKey="Smith, Catherine Arnott" sort="Smith, Catherine Arnott" uniqKey="Smith C" first="Catherine Arnott" last="Smith">Catherine Arnott Smith</name>
</author>
</analytic>
<series><title level="j">AMIA Annual Symposium Proceedings</title>
<idno type="eISSN">1942-597X</idno>
<imprint><date when="2003">2003</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass></textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en"><sec><title>Objective</title>
<p>To determine the effect on clinical information retrieval of structuring typical clinical documents in XML, according to the general guidelines of Health Level Seven’s Clinical Document Architecture.</p>
</sec>
<sec><title>Methods</title>
<p>One thousand clinical documents of eight frequently occurring types were deidentified and marked up in XML for access using a Web browser. Fifty information-seeking tasks were posed to subjects. The tasks were comprised of two typical clinical question types —individual patient results reporting and cohort identification. A control group of physician subjects could perform only free-text, keyword searching. The treatment group’s interface permitted field-based searching of particular sections within each document. Differences in precision and other measures of search success across and between question types were investigated for statistical significance.</p>
</sec>
<sec><title>Results</title>
<p>No statistically significant differences were found between the control and treatment conditions in mean time elapsed or the mean number of records in the final result set. In fact, tasks performed in the treatment condition required a mean number of <italic>more</italic>
steps in the search sequence to a degree that was statistically significant. Tasks performed in the treatment condition had a statistically significant lower rate of mean precision. There was no statistically significant difference between the means of relevance of the individual patient and cohort identification tasks.</p>
</sec>
<sec><title>Conclusion</title>
<p>These findings are in line with Tange et al.<xref ref-type="bibr" rid="b1-125">1</xref>
who found that coarser granularity of clinical narrative gave better results. The results of this experiment also have implications for automatic text processing. Complex tag sets cannot ultimately resolve problems of unstandardized structure; the lack of existing structure within clinical documents is itself a significant limitation.</p>
</sec>
</div>
</front>
</TEI>
<affiliations><list></list>
<tree><noCountry><name sortKey="Smith, Catherine Arnott" sort="Smith, Catherine Arnott" uniqKey="Smith C" first="Catherine Arnott" last="Smith">Catherine Arnott Smith</name>
</noCountry>
</tree>
</affiliations>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Informatique/explor/SgmlV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000B04 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000B04 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Wicri/Informatique |area= SgmlV1 |flux= Main |étape= Exploration |type= RBID |clé= PMC:1480078 |texte= The Effect of XML Markup on Retrieval of Clinical Documents }}
Pour générer des pages wiki
HfdIndexSelect -h $EXPLOR_AREA/Data/Main/Exploration/RBID.i -Sk "pubmed:14728246" \ | HfdSelect -Kh $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd \ | NlmPubMed2Wicri -a SgmlV1
This area was generated with Dilib version V0.6.33. |