@inproceedings{yadav-etal-2016-deep,
title = "Deep Learning Architecture for Patient Data De-identification in Clinical Records",
author = "Yadav, Shweta and
Ekbal, Asif and
Saha, Sriparna and
Bhattacharyya, Pushpak",
editor = "Rumshisky, Anna and
Roberts, Kirk and
Bethard, Steven and
Naumann, Tristan",
booktitle = "Proceedings of the Clinical Natural Language Processing Workshop ({C}linical{NLP})",
month = dec,
year = "2016",
address = "Osaka, Japan",
publisher = "The COLING 2016 Organizing Committee",
url = "https://aclanthology.org/W16-4206",
pages = "32--41",
abstract = "Rapid growth in Electronic Medical Records (EMR) has emerged to an expansion of data in the clinical domain. The majority of the available health care information is sealed in the form of narrative documents which form the rich source of clinical information. Text mining of such clinical records has gained huge attention in various medical applications like treatment and decision making. However, medical records enclose patient Private Health Information (PHI) which can reveal the identities of the patients. In order to retain the privacy of patients, it is mandatory to remove all the PHI information prior to making it publicly available. The aim is to de-identify or encrypt the PHI from the patient medical records. In this paper, we propose an algorithm based on deep learning architecture to solve this problem. We perform de-identification of seven PHI terms from the clinical records. Experiments on benchmark datasets show that our proposed approach achieves encouraging performance, which is better than the baseline model developed with Conditional Random Field.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yadav-etal-2016-deep">
<titleInfo>
<title>Deep Learning Architecture for Patient Data De-identification in Clinical Records</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shweta</namePart>
<namePart type="family">Yadav</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sriparna</namePart>
<namePart type="family">Saha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Clinical Natural Language Processing Workshop (ClinicalNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kirk</namePart>
<namePart type="family">Roberts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tristan</namePart>
<namePart type="family">Naumann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The COLING 2016 Organizing Committee</publisher>
<place>
<placeTerm type="text">Osaka, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Rapid growth in Electronic Medical Records (EMR) has emerged to an expansion of data in the clinical domain. The majority of the available health care information is sealed in the form of narrative documents which form the rich source of clinical information. Text mining of such clinical records has gained huge attention in various medical applications like treatment and decision making. However, medical records enclose patient Private Health Information (PHI) which can reveal the identities of the patients. In order to retain the privacy of patients, it is mandatory to remove all the PHI information prior to making it publicly available. The aim is to de-identify or encrypt the PHI from the patient medical records. In this paper, we propose an algorithm based on deep learning architecture to solve this problem. We perform de-identification of seven PHI terms from the clinical records. Experiments on benchmark datasets show that our proposed approach achieves encouraging performance, which is better than the baseline model developed with Conditional Random Field.</abstract>
<identifier type="citekey">yadav-etal-2016-deep</identifier>
<location>
<url>https://aclanthology.org/W16-4206</url>
</location>
<part>
<date>2016-12</date>
<extent unit="page">
<start>32</start>
<end>41</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Deep Learning Architecture for Patient Data De-identification in Clinical Records
%A Yadav, Shweta
%A Ekbal, Asif
%A Saha, Sriparna
%A Bhattacharyya, Pushpak
%Y Rumshisky, Anna
%Y Roberts, Kirk
%Y Bethard, Steven
%Y Naumann, Tristan
%S Proceedings of the Clinical Natural Language Processing Workshop (ClinicalNLP)
%D 2016
%8 December
%I The COLING 2016 Organizing Committee
%C Osaka, Japan
%F yadav-etal-2016-deep
%X Rapid growth in Electronic Medical Records (EMR) has emerged to an expansion of data in the clinical domain. The majority of the available health care information is sealed in the form of narrative documents which form the rich source of clinical information. Text mining of such clinical records has gained huge attention in various medical applications like treatment and decision making. However, medical records enclose patient Private Health Information (PHI) which can reveal the identities of the patients. In order to retain the privacy of patients, it is mandatory to remove all the PHI information prior to making it publicly available. The aim is to de-identify or encrypt the PHI from the patient medical records. In this paper, we propose an algorithm based on deep learning architecture to solve this problem. We perform de-identification of seven PHI terms from the clinical records. Experiments on benchmark datasets show that our proposed approach achieves encouraging performance, which is better than the baseline model developed with Conditional Random Field.
%U https://aclanthology.org/W16-4206
%P 32-41
Markdown (Informal)
[Deep Learning Architecture for Patient Data De-identification in Clinical Records](https://aclanthology.org/W16-4206) (Yadav et al., ClinicalNLP 2016)
ACL