@inproceedings{nguyen-etal-2023-two,
title = "A Two-Stage Decoder for Efficient {ICD} Coding",
author = "Nguyen, Thanh-Tung and
Schlegel, Viktor and
Ramesh Kashyap, Abhinav and
Winkler, Stefan",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.285/",
doi = "10.18653/v1/2023.findings-acl.285",
pages = "4658--4665",
abstract = "Clinical notes in healthcare facilities are tagged with the International Classification of Diseases (ICD) code; a list of classification codes for medical diagnoses and procedures. ICD coding is a challenging multilabel text classification problem due to noisy clinical document inputs and long-tailed label distribution. Recent automated ICD coding efforts improve performance by encoding medical notes and codes with additional data and knowledge bases. However, most of them do not reflect how human coders generate the code: first, the coders select general code categories and then look for specific subcategories that are relevant to a patient`s condition. Inspired by this, we propose a two-stage decoding mechanism to predict ICD codes. Our model uses the hierarchical properties of the codes to split the prediction into two steps: At first, we predict the parent code and then predict the child code based on the previous prediction. Experiments on the public MIMIC-III data set have shown that our model performs well in single-model settings without external data or knowledge."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nguyen-etal-2023-two">
<titleInfo>
<title>A Two-Stage Decoder for Efficient ICD Coding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thanh-Tung</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viktor</namePart>
<namePart type="family">Schlegel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhinav</namePart>
<namePart type="family">Ramesh Kashyap</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Winkler</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>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</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>Clinical notes in healthcare facilities are tagged with the International Classification of Diseases (ICD) code; a list of classification codes for medical diagnoses and procedures. ICD coding is a challenging multilabel text classification problem due to noisy clinical document inputs and long-tailed label distribution. Recent automated ICD coding efforts improve performance by encoding medical notes and codes with additional data and knowledge bases. However, most of them do not reflect how human coders generate the code: first, the coders select general code categories and then look for specific subcategories that are relevant to a patient‘s condition. Inspired by this, we propose a two-stage decoding mechanism to predict ICD codes. Our model uses the hierarchical properties of the codes to split the prediction into two steps: At first, we predict the parent code and then predict the child code based on the previous prediction. Experiments on the public MIMIC-III data set have shown that our model performs well in single-model settings without external data or knowledge.</abstract>
<identifier type="citekey">nguyen-etal-2023-two</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.285</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.285/</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>4658</start>
<end>4665</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Two-Stage Decoder for Efficient ICD Coding
%A Nguyen, Thanh-Tung
%A Schlegel, Viktor
%A Ramesh Kashyap, Abhinav
%A Winkler, Stefan
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F nguyen-etal-2023-two
%X Clinical notes in healthcare facilities are tagged with the International Classification of Diseases (ICD) code; a list of classification codes for medical diagnoses and procedures. ICD coding is a challenging multilabel text classification problem due to noisy clinical document inputs and long-tailed label distribution. Recent automated ICD coding efforts improve performance by encoding medical notes and codes with additional data and knowledge bases. However, most of them do not reflect how human coders generate the code: first, the coders select general code categories and then look for specific subcategories that are relevant to a patient‘s condition. Inspired by this, we propose a two-stage decoding mechanism to predict ICD codes. Our model uses the hierarchical properties of the codes to split the prediction into two steps: At first, we predict the parent code and then predict the child code based on the previous prediction. Experiments on the public MIMIC-III data set have shown that our model performs well in single-model settings without external data or knowledge.
%R 10.18653/v1/2023.findings-acl.285
%U https://aclanthology.org/2023.findings-acl.285/
%U https://doi.org/10.18653/v1/2023.findings-acl.285
%P 4658-4665
Markdown (Informal)
[A Two-Stage Decoder for Efficient ICD Coding](https://aclanthology.org/2023.findings-acl.285/) (Nguyen et al., Findings 2023)
ACL
- Thanh-Tung Nguyen, Viktor Schlegel, Abhinav Ramesh Kashyap, and Stefan Winkler. 2023. A Two-Stage Decoder for Efficient ICD Coding. In Findings of the Association for Computational Linguistics: ACL 2023, pages 4658–4665, Toronto, Canada. Association for Computational Linguistics.