@inproceedings{williamson-etal-2024-low,
title = "Low Resource {ICD} Coding of Hospital Discharge Summaries",
author = "Williamson, Ashton and
de Hilster, David and
Meyers, Amnon and
Hubig, Nina and
Apon, Amy",
editor = "Demner-Fushman, Dina and
Ananiadou, Sophia and
Miwa, Makoto and
Roberts, Kirk and
Tsujii, Junichi",
booktitle = "Proceedings of the 23rd Workshop on Biomedical Natural Language Processing",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.bionlp-1.45",
doi = "10.18653/v1/2024.bionlp-1.45",
pages = "548--558",
abstract = "Medical coding is the process by which standardized medical codes are assigned to patient health records. This is a complex and challenging task that typically requires an expert human coder to review health records and assign codes from a classification system based on a standard set of rules. Since health records typically consist of a large proportion of free-text documents, this problem has traditionally been approached as a natural language processing (NLP) task. While machine learning-based methods have seen recent popularity on this task, they tend to struggle with codes that are assigned less frequently, for which little or no training data exists. In this work we utilize the open-source NLP programming language, NLP++, to design and build an automated system to assign International Classification of Diseases (ICD) codes to discharge summaries that functions in the absence of labeled training data. We evaluate our system using the MIMIC-III dataset and find that for codes with little training data, our approach achieves competitive performance compared to state-of-the-art machine learning approaches.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="williamson-etal-2024-low">
<titleInfo>
<title>Low Resource ICD Coding of Hospital Discharge Summaries</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ashton</namePart>
<namePart type="family">Williamson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">de Hilster</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amnon</namePart>
<namePart type="family">Meyers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nina</namePart>
<namePart type="family">Hubig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amy</namePart>
<namePart type="family">Apon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd Workshop on Biomedical Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Makoto</namePart>
<namePart type="family">Miwa</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">Junichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Medical coding is the process by which standardized medical codes are assigned to patient health records. This is a complex and challenging task that typically requires an expert human coder to review health records and assign codes from a classification system based on a standard set of rules. Since health records typically consist of a large proportion of free-text documents, this problem has traditionally been approached as a natural language processing (NLP) task. While machine learning-based methods have seen recent popularity on this task, they tend to struggle with codes that are assigned less frequently, for which little or no training data exists. In this work we utilize the open-source NLP programming language, NLP++, to design and build an automated system to assign International Classification of Diseases (ICD) codes to discharge summaries that functions in the absence of labeled training data. We evaluate our system using the MIMIC-III dataset and find that for codes with little training data, our approach achieves competitive performance compared to state-of-the-art machine learning approaches.</abstract>
<identifier type="citekey">williamson-etal-2024-low</identifier>
<identifier type="doi">10.18653/v1/2024.bionlp-1.45</identifier>
<location>
<url>https://aclanthology.org/2024.bionlp-1.45</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>548</start>
<end>558</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Low Resource ICD Coding of Hospital Discharge Summaries
%A Williamson, Ashton
%A de Hilster, David
%A Meyers, Amnon
%A Hubig, Nina
%A Apon, Amy
%Y Demner-Fushman, Dina
%Y Ananiadou, Sophia
%Y Miwa, Makoto
%Y Roberts, Kirk
%Y Tsujii, Junichi
%S Proceedings of the 23rd Workshop on Biomedical Natural Language Processing
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F williamson-etal-2024-low
%X Medical coding is the process by which standardized medical codes are assigned to patient health records. This is a complex and challenging task that typically requires an expert human coder to review health records and assign codes from a classification system based on a standard set of rules. Since health records typically consist of a large proportion of free-text documents, this problem has traditionally been approached as a natural language processing (NLP) task. While machine learning-based methods have seen recent popularity on this task, they tend to struggle with codes that are assigned less frequently, for which little or no training data exists. In this work we utilize the open-source NLP programming language, NLP++, to design and build an automated system to assign International Classification of Diseases (ICD) codes to discharge summaries that functions in the absence of labeled training data. We evaluate our system using the MIMIC-III dataset and find that for codes with little training data, our approach achieves competitive performance compared to state-of-the-art machine learning approaches.
%R 10.18653/v1/2024.bionlp-1.45
%U https://aclanthology.org/2024.bionlp-1.45
%U https://doi.org/10.18653/v1/2024.bionlp-1.45
%P 548-558
Markdown (Informal)
[Low Resource ICD Coding of Hospital Discharge Summaries](https://aclanthology.org/2024.bionlp-1.45) (Williamson et al., BioNLP-WS 2024)
ACL
- Ashton Williamson, David de Hilster, Amnon Meyers, Nina Hubig, and Amy Apon. 2024. Low Resource ICD Coding of Hospital Discharge Summaries. In Proceedings of the 23rd Workshop on Biomedical Natural Language Processing, pages 548–558, Bangkok, Thailand. Association for Computational Linguistics.