@inproceedings{berg-dalianis-2020-semi,
title = "A Semi-supervised Approach for De-identification of {S}wedish Clinical Text",
author = "Berg, Hanna and
Dalianis, Hercules",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.547",
pages = "4444--4450",
abstract = "An abundance of electronic health records (EHR) is produced every day within healthcare. The records possess valuable information for research and future improvement of healthcare. Multiple efforts have been done to protect the integrity of patients while making electronic health records usable for research by removing personally identifiable information in patient records. Supervised machine learning approaches for de-identification of EHRs need annotated data for training, annotations that are costly in time and human resources. The annotation costs for clinical text is even more costly as the process must be carried out in a protected environment with a limited number of annotators who must have signed confidentiality agreements. In this paper is therefore, a semi-supervised method proposed, for automatically creating high-quality training data. The study shows that the method can be used to improve recall from 84.75{\%} to 89.20{\%} without sacrificing precision to the same extent, dropping from 95.73{\%} to 94.20{\%}. The model{'}s recall is arguably more important for de-identification than precision.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="berg-dalianis-2020-semi">
<titleInfo>
<title>A Semi-supervised Approach for De-identification of Swedish Clinical Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hanna</namePart>
<namePart type="family">Berg</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>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</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">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</namePart>
<namePart type="family">Mazo</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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>An abundance of electronic health records (EHR) is produced every day within healthcare. The records possess valuable information for research and future improvement of healthcare. Multiple efforts have been done to protect the integrity of patients while making electronic health records usable for research by removing personally identifiable information in patient records. Supervised machine learning approaches for de-identification of EHRs need annotated data for training, annotations that are costly in time and human resources. The annotation costs for clinical text is even more costly as the process must be carried out in a protected environment with a limited number of annotators who must have signed confidentiality agreements. In this paper is therefore, a semi-supervised method proposed, for automatically creating high-quality training data. The study shows that the method can be used to improve recall from 84.75% to 89.20% without sacrificing precision to the same extent, dropping from 95.73% to 94.20%. The model’s recall is arguably more important for de-identification than precision.</abstract>
<identifier type="citekey">berg-dalianis-2020-semi</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.547</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>4444</start>
<end>4450</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Semi-supervised Approach for De-identification of Swedish Clinical Text
%A Berg, Hanna
%A Dalianis, Hercules
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F berg-dalianis-2020-semi
%X An abundance of electronic health records (EHR) is produced every day within healthcare. The records possess valuable information for research and future improvement of healthcare. Multiple efforts have been done to protect the integrity of patients while making electronic health records usable for research by removing personally identifiable information in patient records. Supervised machine learning approaches for de-identification of EHRs need annotated data for training, annotations that are costly in time and human resources. The annotation costs for clinical text is even more costly as the process must be carried out in a protected environment with a limited number of annotators who must have signed confidentiality agreements. In this paper is therefore, a semi-supervised method proposed, for automatically creating high-quality training data. The study shows that the method can be used to improve recall from 84.75% to 89.20% without sacrificing precision to the same extent, dropping from 95.73% to 94.20%. The model’s recall is arguably more important for de-identification than precision.
%U https://aclanthology.org/2020.lrec-1.547
%P 4444-4450
Markdown (Informal)
[A Semi-supervised Approach for De-identification of Swedish Clinical Text](https://aclanthology.org/2020.lrec-1.547) (Berg & Dalianis, LREC 2020)
ACL