@inproceedings{kocaman-etal-2023-automated,
title = "Automated De-Identification of {A}rabic Medical Records",
author = "Kocaman, Veysel and
Mellah, Youssef and
Haq, Hasham and
Talby, David",
editor = "Sawaf, Hassan and
El-Beltagy, Samhaa and
Zaghouani, Wajdi and
Magdy, Walid and
Abdelali, Ahmed and
Tomeh, Nadi and
Abu Farha, Ibrahim and
Habash, Nizar and
Khalifa, Salam and
Keleg, Amr and
Haddad, Hatem and
Zitouni, Imed and
Mrini, Khalil and
Almatham, Rawan",
booktitle = "Proceedings of ArabicNLP 2023",
month = dec,
year = "2023",
address = "Singapore (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.arabicnlp-1.4",
doi = "10.18653/v1/2023.arabicnlp-1.4",
pages = "33--40",
abstract = "As Electronic Health Records (EHR) become ubiquitous in healthcare systems worldwide, including in Arabic-speaking countries, the dual imperative of safeguarding patient privacy and leveraging data for research and quality improvement grows. This paper presents a first-of-its-kind automated de-identification pipeline for medical text specifically tailored for the Arabic language. This includes accurate medical Named Entity Recognition (NER) for identifying personal information; data obfuscation models to replace sensitive entities with fake entities; and an implementation that natively scales to large datasets on commodity clusters. This research makes two contributions. First, we adapt two existing NER architectures{---} BERT For Token Classification (BFTC) and BiLSTM-CNN-Char {--} to accommodate the unique syntactic and morphological characteristics of the Arabic language. Comparative analysis suggests that BFTC models outperform Bi-LSTM models, achieving higher F1 scores for both identifying and redacting personally identifiable information (PII) from Arabic medical texts. Second, we augment the deep learning models with a contextual parser engine to handle commonly missed entities. Experiments show that the combined pipeline demonstrates superior performance with micro F1 scores ranging from 0.94 to 0.98 on the test dataset, which is a translated version of the i2b2 2014 de-identification challenge, across 17 sensitive entities. This level of accuracy is in line with that achieved with manual de-identification by domain experts, suggesting that a fully automated and scalable process is now viable.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kocaman-etal-2023-automated">
<titleInfo>
<title>Automated De-Identification of Arabic Medical Records</title>
</titleInfo>
<name type="personal">
<namePart type="given">Veysel</namePart>
<namePart type="family">Kocaman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Youssef</namePart>
<namePart type="family">Mellah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hasham</namePart>
<namePart type="family">Haq</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Talby</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of ArabicNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hassan</namePart>
<namePart type="family">Sawaf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samhaa</namePart>
<namePart type="family">El-Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Walid</namePart>
<namePart type="family">Magdy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nadi</namePart>
<namePart type="family">Tomeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ibrahim</namePart>
<namePart type="family">Abu Farha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salam</namePart>
<namePart type="family">Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amr</namePart>
<namePart type="family">Keleg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hatem</namePart>
<namePart type="family">Haddad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalil</namePart>
<namePart type="family">Mrini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rawan</namePart>
<namePart type="family">Almatham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>As Electronic Health Records (EHR) become ubiquitous in healthcare systems worldwide, including in Arabic-speaking countries, the dual imperative of safeguarding patient privacy and leveraging data for research and quality improvement grows. This paper presents a first-of-its-kind automated de-identification pipeline for medical text specifically tailored for the Arabic language. This includes accurate medical Named Entity Recognition (NER) for identifying personal information; data obfuscation models to replace sensitive entities with fake entities; and an implementation that natively scales to large datasets on commodity clusters. This research makes two contributions. First, we adapt two existing NER architectures— BERT For Token Classification (BFTC) and BiLSTM-CNN-Char – to accommodate the unique syntactic and morphological characteristics of the Arabic language. Comparative analysis suggests that BFTC models outperform Bi-LSTM models, achieving higher F1 scores for both identifying and redacting personally identifiable information (PII) from Arabic medical texts. Second, we augment the deep learning models with a contextual parser engine to handle commonly missed entities. Experiments show that the combined pipeline demonstrates superior performance with micro F1 scores ranging from 0.94 to 0.98 on the test dataset, which is a translated version of the i2b2 2014 de-identification challenge, across 17 sensitive entities. This level of accuracy is in line with that achieved with manual de-identification by domain experts, suggesting that a fully automated and scalable process is now viable.</abstract>
<identifier type="citekey">kocaman-etal-2023-automated</identifier>
<identifier type="doi">10.18653/v1/2023.arabicnlp-1.4</identifier>
<location>
<url>https://aclanthology.org/2023.arabicnlp-1.4</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>33</start>
<end>40</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automated De-Identification of Arabic Medical Records
%A Kocaman, Veysel
%A Mellah, Youssef
%A Haq, Hasham
%A Talby, David
%Y Sawaf, Hassan
%Y El-Beltagy, Samhaa
%Y Zaghouani, Wajdi
%Y Magdy, Walid
%Y Abdelali, Ahmed
%Y Tomeh, Nadi
%Y Abu Farha, Ibrahim
%Y Habash, Nizar
%Y Khalifa, Salam
%Y Keleg, Amr
%Y Haddad, Hatem
%Y Zitouni, Imed
%Y Mrini, Khalil
%Y Almatham, Rawan
%S Proceedings of ArabicNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore (Hybrid)
%F kocaman-etal-2023-automated
%X As Electronic Health Records (EHR) become ubiquitous in healthcare systems worldwide, including in Arabic-speaking countries, the dual imperative of safeguarding patient privacy and leveraging data for research and quality improvement grows. This paper presents a first-of-its-kind automated de-identification pipeline for medical text specifically tailored for the Arabic language. This includes accurate medical Named Entity Recognition (NER) for identifying personal information; data obfuscation models to replace sensitive entities with fake entities; and an implementation that natively scales to large datasets on commodity clusters. This research makes two contributions. First, we adapt two existing NER architectures— BERT For Token Classification (BFTC) and BiLSTM-CNN-Char – to accommodate the unique syntactic and morphological characteristics of the Arabic language. Comparative analysis suggests that BFTC models outperform Bi-LSTM models, achieving higher F1 scores for both identifying and redacting personally identifiable information (PII) from Arabic medical texts. Second, we augment the deep learning models with a contextual parser engine to handle commonly missed entities. Experiments show that the combined pipeline demonstrates superior performance with micro F1 scores ranging from 0.94 to 0.98 on the test dataset, which is a translated version of the i2b2 2014 de-identification challenge, across 17 sensitive entities. This level of accuracy is in line with that achieved with manual de-identification by domain experts, suggesting that a fully automated and scalable process is now viable.
%R 10.18653/v1/2023.arabicnlp-1.4
%U https://aclanthology.org/2023.arabicnlp-1.4
%U https://doi.org/10.18653/v1/2023.arabicnlp-1.4
%P 33-40
Markdown (Informal)
[Automated De-Identification of Arabic Medical Records](https://aclanthology.org/2023.arabicnlp-1.4) (Kocaman et al., ArabicNLP-WS 2023)
ACL