@inproceedings{berg-etal-2019-building,
title = "Building a De-identification System for Real {S}wedish Clinical Text Using Pseudonymised Clinical Text",
author = "Berg, Hanna and
Chomutare, Taridzo and
Dalianis, Hercules",
editor = "Holderness, Eben and
Jimeno Yepes, Antonio and
Lavelli, Alberto and
Minard, Anne-Lyse and
Pustejovsky, James and
Rinaldi, Fabio",
booktitle = "Proceedings of the Tenth International Workshop on Health Text Mining and Information Analysis (LOUHI 2019)",
month = nov,
year = "2019",
address = "Hong Kong",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-6215",
doi = "10.18653/v1/D19-6215",
pages = "118--125",
abstract = "This article presents experiments with pseudonymised Swedish clinical text used as training data to de-identify real clinical text with the future aim to transfer non-sensitive training data to other hospitals. Conditional Random Fields (CFR) and Long Short-Term Memory (LSTM) machine learning algorithms were used to train de-identification models. The two models were trained on pseudonymised data and evaluated on real data. For benchmarking, models were also trained on real data, and evaluated on real data as well as trained on pseudonymised data and evaluated on pseudonymised data. CRF showed better performance for some PHI information like Date Part, First Name and Last Name; consistent with some reports in the literature. In contrast, poor performances on Location and Health Care Unit information were noted, partially due to the constrained vocabulary in the pseudonymised training data. It is concluded that it is possible to train transferable models based on pseudonymised Swedish clinical data, but even small narrative and distributional variation could negatively impact performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="berg-etal-2019-building">
<titleInfo>
<title>Building a De-identification System for Real Swedish Clinical Text Using Pseudonymised 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">Taridzo</namePart>
<namePart type="family">Chomutare</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>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Workshop on Health Text Mining and Information Analysis (LOUHI 2019)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eben</namePart>
<namePart type="family">Holderness</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Jimeno Yepes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Lavelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anne-Lyse</namePart>
<namePart type="family">Minard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabio</namePart>
<namePart type="family">Rinaldi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This article presents experiments with pseudonymised Swedish clinical text used as training data to de-identify real clinical text with the future aim to transfer non-sensitive training data to other hospitals. Conditional Random Fields (CFR) and Long Short-Term Memory (LSTM) machine learning algorithms were used to train de-identification models. The two models were trained on pseudonymised data and evaluated on real data. For benchmarking, models were also trained on real data, and evaluated on real data as well as trained on pseudonymised data and evaluated on pseudonymised data. CRF showed better performance for some PHI information like Date Part, First Name and Last Name; consistent with some reports in the literature. In contrast, poor performances on Location and Health Care Unit information were noted, partially due to the constrained vocabulary in the pseudonymised training data. It is concluded that it is possible to train transferable models based on pseudonymised Swedish clinical data, but even small narrative and distributional variation could negatively impact performance.</abstract>
<identifier type="citekey">berg-etal-2019-building</identifier>
<identifier type="doi">10.18653/v1/D19-6215</identifier>
<location>
<url>https://aclanthology.org/D19-6215</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>118</start>
<end>125</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Building a De-identification System for Real Swedish Clinical Text Using Pseudonymised Clinical Text
%A Berg, Hanna
%A Chomutare, Taridzo
%A Dalianis, Hercules
%Y Holderness, Eben
%Y Jimeno Yepes, Antonio
%Y Lavelli, Alberto
%Y Minard, Anne-Lyse
%Y Pustejovsky, James
%Y Rinaldi, Fabio
%S Proceedings of the Tenth International Workshop on Health Text Mining and Information Analysis (LOUHI 2019)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong
%F berg-etal-2019-building
%X This article presents experiments with pseudonymised Swedish clinical text used as training data to de-identify real clinical text with the future aim to transfer non-sensitive training data to other hospitals. Conditional Random Fields (CFR) and Long Short-Term Memory (LSTM) machine learning algorithms were used to train de-identification models. The two models were trained on pseudonymised data and evaluated on real data. For benchmarking, models were also trained on real data, and evaluated on real data as well as trained on pseudonymised data and evaluated on pseudonymised data. CRF showed better performance for some PHI information like Date Part, First Name and Last Name; consistent with some reports in the literature. In contrast, poor performances on Location and Health Care Unit information were noted, partially due to the constrained vocabulary in the pseudonymised training data. It is concluded that it is possible to train transferable models based on pseudonymised Swedish clinical data, but even small narrative and distributional variation could negatively impact performance.
%R 10.18653/v1/D19-6215
%U https://aclanthology.org/D19-6215
%U https://doi.org/10.18653/v1/D19-6215
%P 118-125
Markdown (Informal)
[Building a De-identification System for Real Swedish Clinical Text Using Pseudonymised Clinical Text](https://aclanthology.org/D19-6215) (Berg et al., Louhi 2019)
ACL