@inproceedings{skeppstedt-etal-2012-rule,
title = "Rule-based Entity Recognition and Coverage of {SNOMED} {CT} in {S}wedish Clinical Text",
author = "Skeppstedt, Maria and
Kvist, Maria and
Dalianis, Hercules",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/521_Paper.pdf",
pages = "1250--1257",
abstract = "Named entity recognition of the clinical entities disorders, findings and body structures is needed for information extraction from unstructured text in health records. Clinical notes from a Swedish emergency unit were annotated and used for evaluating a rule- and terminology-based entity recognition system. This system used different preprocessing techniques for matching terms to SNOMED CT, and, one by one, four other terminologies were added. For the class body structure, the results improved with preprocessing, whereas only small improvements were shown for the classes disorder and finding. The best average results were achieved when all terminologies were used together. The entity body structure was recognised with a precision of 0.74 and a recall of 0.80, whereas lower results were achieved for disorder (precision: 0.75, recall: 0.55) and for finding (precision: 0.57, recall: 0.30). The proportion of entities containing abbreviations were higher for false negatives than for correctly recognised entities, and no entities containing more than two tokens were recognised by the system. Low recall for disorders and findings shows both that additional methods are needed for entity recognition and that there are many expressions in clinical text that are not included in SNOMED CT.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="skeppstedt-etal-2012-rule">
<titleInfo>
<title>Rule-based Entity Recognition and Coverage of SNOMED CT in Swedish Clinical Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Skeppstedt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Kvist</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hercules</namePart>
<namePart type="family">Dalianis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Named entity recognition of the clinical entities disorders, findings and body structures is needed for information extraction from unstructured text in health records. Clinical notes from a Swedish emergency unit were annotated and used for evaluating a rule- and terminology-based entity recognition system. This system used different preprocessing techniques for matching terms to SNOMED CT, and, one by one, four other terminologies were added. For the class body structure, the results improved with preprocessing, whereas only small improvements were shown for the classes disorder and finding. The best average results were achieved when all terminologies were used together. The entity body structure was recognised with a precision of 0.74 and a recall of 0.80, whereas lower results were achieved for disorder (precision: 0.75, recall: 0.55) and for finding (precision: 0.57, recall: 0.30). The proportion of entities containing abbreviations were higher for false negatives than for correctly recognised entities, and no entities containing more than two tokens were recognised by the system. Low recall for disorders and findings shows both that additional methods are needed for entity recognition and that there are many expressions in clinical text that are not included in SNOMED CT.</abstract>
<identifier type="citekey">skeppstedt-etal-2012-rule</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/521_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>1250</start>
<end>1257</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Rule-based Entity Recognition and Coverage of SNOMED CT in Swedish Clinical Text
%A Skeppstedt, Maria
%A Kvist, Maria
%A Dalianis, Hercules
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F skeppstedt-etal-2012-rule
%X Named entity recognition of the clinical entities disorders, findings and body structures is needed for information extraction from unstructured text in health records. Clinical notes from a Swedish emergency unit were annotated and used for evaluating a rule- and terminology-based entity recognition system. This system used different preprocessing techniques for matching terms to SNOMED CT, and, one by one, four other terminologies were added. For the class body structure, the results improved with preprocessing, whereas only small improvements were shown for the classes disorder and finding. The best average results were achieved when all terminologies were used together. The entity body structure was recognised with a precision of 0.74 and a recall of 0.80, whereas lower results were achieved for disorder (precision: 0.75, recall: 0.55) and for finding (precision: 0.57, recall: 0.30). The proportion of entities containing abbreviations were higher for false negatives than for correctly recognised entities, and no entities containing more than two tokens were recognised by the system. Low recall for disorders and findings shows both that additional methods are needed for entity recognition and that there are many expressions in clinical text that are not included in SNOMED CT.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/521_Paper.pdf
%P 1250-1257
Markdown (Informal)
[Rule-based Entity Recognition and Coverage of SNOMED CT in Swedish Clinical Text](http://www.lrec-conf.org/proceedings/lrec2012/pdf/521_Paper.pdf) (Skeppstedt et al., LREC 2012)
ACL