@inproceedings{chen-etal-2023-rare,
title = "Rare Codes Count: Mining Inter-code Relations for Long-tail Clinical Text Classification",
author = "Chen, Jiamin and
Li, Xuhong and
Xi, Junting and
Yu, Lei and
Xiong, Haoyi",
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-1.43",
doi = "10.18653/v1/2023.clinicalnlp-1.43",
pages = "403--413",
abstract = "Multi-label clinical text classification, such as automatic ICD coding, has always been a challenging subject in Natural Language Processing, due to its long, domain-specific documents and long-tail distribution over a large label set. Existing methods adopt different model architectures to encode the clinical notes. Whereas without digging out the useful connections between labels, the model presents a huge gap in predicting performances between rare and frequent codes. In this work, we propose a novel method for further mining the helpful relations between different codes via a relation-enhanced code encoder to improve the rare code performance. Starting from the simple code descriptions, the model reaches comparable, even better performances than models with heavy external knowledge. Our proposed method is evaluated on MIMIC-III, a common dataset in the medical domain. It outperforms the previous state-of-art models on both overall metrics and rare code performances. Moreover, the interpretation results further prove the effectiveness of our methods. Our code is publicly available at \url{https://github.com/jiaminchen-1031/Rare-ICD}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2023-rare">
<titleInfo>
<title>Rare Codes Count: Mining Inter-code Relations for Long-tail Clinical Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiamin</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuhong</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junting</namePart>
<namePart type="family">Xi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haoyi</namePart>
<namePart type="family">Xiong</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>Multi-label clinical text classification, such as automatic ICD coding, has always been a challenging subject in Natural Language Processing, due to its long, domain-specific documents and long-tail distribution over a large label set. Existing methods adopt different model architectures to encode the clinical notes. Whereas without digging out the useful connections between labels, the model presents a huge gap in predicting performances between rare and frequent codes. In this work, we propose a novel method for further mining the helpful relations between different codes via a relation-enhanced code encoder to improve the rare code performance. Starting from the simple code descriptions, the model reaches comparable, even better performances than models with heavy external knowledge. Our proposed method is evaluated on MIMIC-III, a common dataset in the medical domain. It outperforms the previous state-of-art models on both overall metrics and rare code performances. Moreover, the interpretation results further prove the effectiveness of our methods. Our code is publicly available at https://github.com/jiaminchen-1031/Rare-ICD.</abstract>
<identifier type="citekey">chen-etal-2023-rare</identifier>
<identifier type="doi">10.18653/v1/2023.clinicalnlp-1.43</identifier>
<location>
<url>https://aclanthology.org/2023.clinicalnlp-1.43</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>403</start>
<end>413</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Rare Codes Count: Mining Inter-code Relations for Long-tail Clinical Text Classification
%A Chen, Jiamin
%A Li, Xuhong
%A Xi, Junting
%A Yu, Lei
%A Xiong, Haoyi
%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 chen-etal-2023-rare
%X Multi-label clinical text classification, such as automatic ICD coding, has always been a challenging subject in Natural Language Processing, due to its long, domain-specific documents and long-tail distribution over a large label set. Existing methods adopt different model architectures to encode the clinical notes. Whereas without digging out the useful connections between labels, the model presents a huge gap in predicting performances between rare and frequent codes. In this work, we propose a novel method for further mining the helpful relations between different codes via a relation-enhanced code encoder to improve the rare code performance. Starting from the simple code descriptions, the model reaches comparable, even better performances than models with heavy external knowledge. Our proposed method is evaluated on MIMIC-III, a common dataset in the medical domain. It outperforms the previous state-of-art models on both overall metrics and rare code performances. Moreover, the interpretation results further prove the effectiveness of our methods. Our code is publicly available at https://github.com/jiaminchen-1031/Rare-ICD.
%R 10.18653/v1/2023.clinicalnlp-1.43
%U https://aclanthology.org/2023.clinicalnlp-1.43
%U https://doi.org/10.18653/v1/2023.clinicalnlp-1.43
%P 403-413
Markdown (Informal)
[Rare Codes Count: Mining Inter-code Relations for Long-tail Clinical Text Classification](https://aclanthology.org/2023.clinicalnlp-1.43) (Chen et al., ClinicalNLP 2023)
ACL