@inproceedings{friedrich-etal-2019-adversarial,
title = "Adversarial Learning of Privacy-Preserving Text Representations for De-Identification of Medical Records",
author = {Friedrich, Max and
K{\"o}hn, Arne and
Wiedemann, Gregor and
Biemann, Chris},
editor = "Korhonen, Anna and
Traum, David and
M{\`a}rquez, Llu{\'\i}s",
booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P19-1584",
doi = "10.18653/v1/P19-1584",
pages = "5829--5839",
abstract = "De-identification is the task of detecting protected health information (PHI) in medical text. It is a critical step in sanitizing electronic health records (EHR) to be shared for research. Automatic de-identification classifiers can significantly speed up the sanitization process. However, obtaining a large and diverse dataset to train such a classifier that works well across many types of medical text poses a challenge as privacy laws prohibit the sharing of raw medical records. We introduce a method to create privacy-preserving shareable representations of medical text (i.e. they contain no PHI) that does not require expensive manual pseudonymization. These representations can be shared between organizations to create unified datasets for training de-identification models. Our representation allows training a simple LSTM-CRF de-identification model to an F1 score of 97.4{\%}, which is comparable to a strong baseline that exposes private information in its representation. A robust, widely available de-identification classifier based on our representation could potentially enable studies for which de-identification would otherwise be too costly.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="friedrich-etal-2019-adversarial">
<titleInfo>
<title>Adversarial Learning of Privacy-Preserving Text Representations for De-Identification of Medical Records</title>
</titleInfo>
<name type="personal">
<namePart type="given">Max</namePart>
<namePart type="family">Friedrich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arne</namePart>
<namePart type="family">Köhn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gregor</namePart>
<namePart type="family">Wiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Biemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Korhonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Traum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Màrquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>De-identification is the task of detecting protected health information (PHI) in medical text. It is a critical step in sanitizing electronic health records (EHR) to be shared for research. Automatic de-identification classifiers can significantly speed up the sanitization process. However, obtaining a large and diverse dataset to train such a classifier that works well across many types of medical text poses a challenge as privacy laws prohibit the sharing of raw medical records. We introduce a method to create privacy-preserving shareable representations of medical text (i.e. they contain no PHI) that does not require expensive manual pseudonymization. These representations can be shared between organizations to create unified datasets for training de-identification models. Our representation allows training a simple LSTM-CRF de-identification model to an F1 score of 97.4%, which is comparable to a strong baseline that exposes private information in its representation. A robust, widely available de-identification classifier based on our representation could potentially enable studies for which de-identification would otherwise be too costly.</abstract>
<identifier type="citekey">friedrich-etal-2019-adversarial</identifier>
<identifier type="doi">10.18653/v1/P19-1584</identifier>
<location>
<url>https://aclanthology.org/P19-1584</url>
</location>
<part>
<date>2019-07</date>
<extent unit="page">
<start>5829</start>
<end>5839</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Adversarial Learning of Privacy-Preserving Text Representations for De-Identification of Medical Records
%A Friedrich, Max
%A Köhn, Arne
%A Wiedemann, Gregor
%A Biemann, Chris
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluís
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F friedrich-etal-2019-adversarial
%X De-identification is the task of detecting protected health information (PHI) in medical text. It is a critical step in sanitizing electronic health records (EHR) to be shared for research. Automatic de-identification classifiers can significantly speed up the sanitization process. However, obtaining a large and diverse dataset to train such a classifier that works well across many types of medical text poses a challenge as privacy laws prohibit the sharing of raw medical records. We introduce a method to create privacy-preserving shareable representations of medical text (i.e. they contain no PHI) that does not require expensive manual pseudonymization. These representations can be shared between organizations to create unified datasets for training de-identification models. Our representation allows training a simple LSTM-CRF de-identification model to an F1 score of 97.4%, which is comparable to a strong baseline that exposes private information in its representation. A robust, widely available de-identification classifier based on our representation could potentially enable studies for which de-identification would otherwise be too costly.
%R 10.18653/v1/P19-1584
%U https://aclanthology.org/P19-1584
%U https://doi.org/10.18653/v1/P19-1584
%P 5829-5839
Markdown (Informal)
[Adversarial Learning of Privacy-Preserving Text Representations for De-Identification of Medical Records](https://aclanthology.org/P19-1584) (Friedrich et al., ACL 2019)
ACL