@inproceedings{jeong-etal-2023-improving,
title = "Improving Automatic {KCD} Coding: Introducing the {K}o{DAK} and an Optimized Tokenization Method for {K}orean Clinical Documents",
author = "Jeong, Geunyeong and
Sun, Juoh and
Jeong, Seokwon and
Shin, Hyunjin and
Kim, Harksoo",
editor = "Naumann, Tristan and
Ben Abacha, Asma and
Bethard, Steven and
Roberts, Kirk and
Rumshisky, Anna",
booktitle = "Proceedings of the 5th Clinical Natural Language Processing Workshop",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.clinicalnlp-1.12",
doi = "10.18653/v1/2023.clinicalnlp-1.12",
pages = "96--101",
abstract = "International Classification of Diseases (ICD) coding is the task of assigning a patient{'}s electronic health records into standardized codes, which is crucial for enhancing medical services and reducing healthcare costs. In Korea, automatic Korean Standard Classification of Diseases (KCD) coding has been hindered by limited resources, differences in ICD systems, and language-specific characteristics. Therefore, we construct the Korean Dataset for Automatic KCD coding (KoDAK) by collecting and preprocessing Korean clinical documents. In addition, we propose a tokenization method optimized for Korean clinical documents. Our experiments show that our proposed method outperforms Korean Medical BERT (KM-BERT) in Macro-F1 performance by 0.14{\%}p while using fewer model parameters, demonstrating its effectiveness in Korean clinical documents.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jeong-etal-2023-improving">
<titleInfo>
<title>Improving Automatic KCD Coding: Introducing the KoDAK and an Optimized Tokenization Method for Korean Clinical Documents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Geunyeong</namePart>
<namePart type="family">Jeong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juoh</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokwon</namePart>
<namePart type="family">Jeong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyunjin</namePart>
<namePart type="family">Shin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harksoo</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th Clinical Natural Language Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tristan</namePart>
<namePart type="family">Naumann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asma</namePart>
<namePart type="family">Ben Abacha</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">Kirk</namePart>
<namePart type="family">Roberts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>International Classification of Diseases (ICD) coding is the task of assigning a patient’s electronic health records into standardized codes, which is crucial for enhancing medical services and reducing healthcare costs. In Korea, automatic Korean Standard Classification of Diseases (KCD) coding has been hindered by limited resources, differences in ICD systems, and language-specific characteristics. Therefore, we construct the Korean Dataset for Automatic KCD coding (KoDAK) by collecting and preprocessing Korean clinical documents. In addition, we propose a tokenization method optimized for Korean clinical documents. Our experiments show that our proposed method outperforms Korean Medical BERT (KM-BERT) in Macro-F1 performance by 0.14%p while using fewer model parameters, demonstrating its effectiveness in Korean clinical documents.</abstract>
<identifier type="citekey">jeong-etal-2023-improving</identifier>
<identifier type="doi">10.18653/v1/2023.clinicalnlp-1.12</identifier>
<location>
<url>https://aclanthology.org/2023.clinicalnlp-1.12</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>96</start>
<end>101</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Automatic KCD Coding: Introducing the KoDAK and an Optimized Tokenization Method for Korean Clinical Documents
%A Jeong, Geunyeong
%A Sun, Juoh
%A Jeong, Seokwon
%A Shin, Hyunjin
%A Kim, Harksoo
%Y Naumann, Tristan
%Y Ben Abacha, Asma
%Y Bethard, Steven
%Y Roberts, Kirk
%Y Rumshisky, Anna
%S Proceedings of the 5th Clinical Natural Language Processing Workshop
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F jeong-etal-2023-improving
%X International Classification of Diseases (ICD) coding is the task of assigning a patient’s electronic health records into standardized codes, which is crucial for enhancing medical services and reducing healthcare costs. In Korea, automatic Korean Standard Classification of Diseases (KCD) coding has been hindered by limited resources, differences in ICD systems, and language-specific characteristics. Therefore, we construct the Korean Dataset for Automatic KCD coding (KoDAK) by collecting and preprocessing Korean clinical documents. In addition, we propose a tokenization method optimized for Korean clinical documents. Our experiments show that our proposed method outperforms Korean Medical BERT (KM-BERT) in Macro-F1 performance by 0.14%p while using fewer model parameters, demonstrating its effectiveness in Korean clinical documents.
%R 10.18653/v1/2023.clinicalnlp-1.12
%U https://aclanthology.org/2023.clinicalnlp-1.12
%U https://doi.org/10.18653/v1/2023.clinicalnlp-1.12
%P 96-101
Markdown (Informal)
[Improving Automatic KCD Coding: Introducing the KoDAK and an Optimized Tokenization Method for Korean Clinical Documents](https://aclanthology.org/2023.clinicalnlp-1.12) (Jeong et al., ClinicalNLP 2023)
ACL