@inproceedings{ngo-etal-2024-deidentifying,
title = "Deidentifying a {N}orwegian Clinical Corpus - an Effort to Create a Privacy-preserving {N}orwegian Large Clinical Language Model",
author = "Ngo, Phuong and
Tejedor, Miguel and
Olsen Svenning, Therese and
Chomutare, Taridzo and
Budrionis, Andrius and
Dalianis, Hercules",
editor = {Volodina, Elena and
Alfter, David and
Dobnik, Simon and
Lindstr{\"o}m Tiedemann, Therese and
Mu{\~n}oz S{\'a}nchez, Ricardo and
Szawerna, Maria Irena and
Vu, Xuan-Son},
booktitle = "Proceedings of the Workshop on Computational Approaches to Language Data Pseudonymization (CALD-pseudo 2024)",
month = mar,
year = "2024",
address = "St. Julian{'}s, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.caldpseudo-1.5",
pages = "37--43",
abstract = "The study discusses the methods and challenges of deidentifying and pseudonymizing Norwegian clinical text for research purposes. The results of the NorDeid tool for deidentification and pseudonymization on different types of protected health information were evaluated and discussed, as well as the extension of its functionality with regular expressions to identify specific types of sensitive information. The research used a clinical corpus of adult patients treated in a gastro-surgical department in Norway, which contains approximately nine million clinical notes. The study also highlights the challenges posed by the unique language and clinical terminology of Norway and emphasizes the importance of protecting privacy and the need for customized approaches to meet legal and research requirements.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ngo-etal-2024-deidentifying">
<titleInfo>
<title>Deidentifying a Norwegian Clinical Corpus - an Effort to Create a Privacy-preserving Norwegian Large Clinical Language Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Phuong</namePart>
<namePart type="family">Ngo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miguel</namePart>
<namePart type="family">Tejedor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Therese</namePart>
<namePart type="family">Olsen Svenning</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taridzo</namePart>
<namePart type="family">Chomutare</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrius</namePart>
<namePart type="family">Budrionis</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>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Computational Approaches to Language Data Pseudonymization (CALD-pseudo 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Volodina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Alfter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Dobnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Therese</namePart>
<namePart type="family">Lindström Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ricardo</namePart>
<namePart type="family">Muñoz Sánchez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Irena</namePart>
<namePart type="family">Szawerna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuan-Son</namePart>
<namePart type="family">Vu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The study discusses the methods and challenges of deidentifying and pseudonymizing Norwegian clinical text for research purposes. The results of the NorDeid tool for deidentification and pseudonymization on different types of protected health information were evaluated and discussed, as well as the extension of its functionality with regular expressions to identify specific types of sensitive information. The research used a clinical corpus of adult patients treated in a gastro-surgical department in Norway, which contains approximately nine million clinical notes. The study also highlights the challenges posed by the unique language and clinical terminology of Norway and emphasizes the importance of protecting privacy and the need for customized approaches to meet legal and research requirements.</abstract>
<identifier type="citekey">ngo-etal-2024-deidentifying</identifier>
<location>
<url>https://aclanthology.org/2024.caldpseudo-1.5</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>37</start>
<end>43</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Deidentifying a Norwegian Clinical Corpus - an Effort to Create a Privacy-preserving Norwegian Large Clinical Language Model
%A Ngo, Phuong
%A Tejedor, Miguel
%A Olsen Svenning, Therese
%A Chomutare, Taridzo
%A Budrionis, Andrius
%A Dalianis, Hercules
%Y Volodina, Elena
%Y Alfter, David
%Y Dobnik, Simon
%Y Lindström Tiedemann, Therese
%Y Muñoz Sánchez, Ricardo
%Y Szawerna, Maria Irena
%Y Vu, Xuan-Son
%S Proceedings of the Workshop on Computational Approaches to Language Data Pseudonymization (CALD-pseudo 2024)
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F ngo-etal-2024-deidentifying
%X The study discusses the methods and challenges of deidentifying and pseudonymizing Norwegian clinical text for research purposes. The results of the NorDeid tool for deidentification and pseudonymization on different types of protected health information were evaluated and discussed, as well as the extension of its functionality with regular expressions to identify specific types of sensitive information. The research used a clinical corpus of adult patients treated in a gastro-surgical department in Norway, which contains approximately nine million clinical notes. The study also highlights the challenges posed by the unique language and clinical terminology of Norway and emphasizes the importance of protecting privacy and the need for customized approaches to meet legal and research requirements.
%U https://aclanthology.org/2024.caldpseudo-1.5
%P 37-43
Markdown (Informal)
[Deidentifying a Norwegian Clinical Corpus - an Effort to Create a Privacy-preserving Norwegian Large Clinical Language Model](https://aclanthology.org/2024.caldpseudo-1.5) (Ngo et al., CALD-pseudo-WS 2024)
ACL