@inproceedings{carlsson-dalianis-2010-influence,
title = "Influence of Module Order on Rule-Based De-identification of Personal Names in Electronic Patient Records Written in {S}wedish",
author = "Carlsson, Elin and
Dalianis, Hercules",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/46_Paper.pdf",
abstract = "Electronic patient records (EPRs) are a valuable resource for research but for confidentiality reasons they cannot be used freely. In order to make EPRs available to a wider group of researchers, sensitive information such as personal names has to be removed. De-identification is a process that makes this possible. Both rule-based as well as statistical and machine learning based methods exist to perform de-identification, but the second method requires annotated training material which exists only very sparsely for patient names. It is therefore necessary to use rule-based methods for de-identification of EPRs. Not much is known, however, about the order in which the various rules should be applied and how the different rules influence precision and recall. This paper aims to answer this research question by implementing and evaluating four common rules for de-identification of personal names in EPRs written in Swedish: (1) dictionary name matching, (2) title matching, (3) common words filtering and (4) learning from previous modules. The results show that to obtain the highest recall and precision, the rules should be applied in the following order: title matching, common words filtering and dictionary name matching.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="carlsson-dalianis-2010-influence">
<titleInfo>
<title>Influence of Module Order on Rule-Based De-identification of Personal Names in Electronic Patient Records Written in Swedish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elin</namePart>
<namePart type="family">Carlsson</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>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">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">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>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Rosner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Electronic patient records (EPRs) are a valuable resource for research but for confidentiality reasons they cannot be used freely. In order to make EPRs available to a wider group of researchers, sensitive information such as personal names has to be removed. De-identification is a process that makes this possible. Both rule-based as well as statistical and machine learning based methods exist to perform de-identification, but the second method requires annotated training material which exists only very sparsely for patient names. It is therefore necessary to use rule-based methods for de-identification of EPRs. Not much is known, however, about the order in which the various rules should be applied and how the different rules influence precision and recall. This paper aims to answer this research question by implementing and evaluating four common rules for de-identification of personal names in EPRs written in Swedish: (1) dictionary name matching, (2) title matching, (3) common words filtering and (4) learning from previous modules. The results show that to obtain the highest recall and precision, the rules should be applied in the following order: title matching, common words filtering and dictionary name matching.</abstract>
<identifier type="citekey">carlsson-dalianis-2010-influence</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/46_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Influence of Module Order on Rule-Based De-identification of Personal Names in Electronic Patient Records Written in Swedish
%A Carlsson, Elin
%A Dalianis, Hercules
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F carlsson-dalianis-2010-influence
%X Electronic patient records (EPRs) are a valuable resource for research but for confidentiality reasons they cannot be used freely. In order to make EPRs available to a wider group of researchers, sensitive information such as personal names has to be removed. De-identification is a process that makes this possible. Both rule-based as well as statistical and machine learning based methods exist to perform de-identification, but the second method requires annotated training material which exists only very sparsely for patient names. It is therefore necessary to use rule-based methods for de-identification of EPRs. Not much is known, however, about the order in which the various rules should be applied and how the different rules influence precision and recall. This paper aims to answer this research question by implementing and evaluating four common rules for de-identification of personal names in EPRs written in Swedish: (1) dictionary name matching, (2) title matching, (3) common words filtering and (4) learning from previous modules. The results show that to obtain the highest recall and precision, the rules should be applied in the following order: title matching, common words filtering and dictionary name matching.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/46_Paper.pdf
Markdown (Informal)
[Influence of Module Order on Rule-Based De-identification of Personal Names in Electronic Patient Records Written in Swedish](http://www.lrec-conf.org/proceedings/lrec2010/pdf/46_Paper.pdf) (Carlsson & Dalianis, LREC 2010)
ACL