@inproceedings{gomes-etal-2024-accurate,
title = "Accurate and Well-Calibrated {ICD} Code Assignment Through Attention Over Diverse Label Embeddings",
author = "Gomes, Goncalo and
Coutinho, Isabel and
Martins, Bruno",
editor = "Graham, Yvette and
Purver, Matthew",
booktitle = "Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = mar,
year = "2024",
address = "St. Julian{'}s, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.eacl-long.141",
pages = "2302--2315",
abstract = "Although the International Classification of Diseases (ICD) has been adopted worldwide, manually assigning ICD codes to clinical text is time-consuming, error-prone, and expensive, motivating the development of automated approaches. This paper describes a novel approach for automated ICD coding, combining several ideas from previous related work. We specifically employ a strong Transformer-based model as a text encoder and, to handle lengthy clinical narratives, we explored either (a) adapting the base encoder model into a Longformer, or (b) dividing the text into chunks and processing each chunk independently. The representations produced by the encoder are combined with a label embedding mechanism that explores diverse ICD code synonyms. Experiments with different splits of the MIMIC-III dataset show that the proposed approach outperforms the current state-of-the-art models in ICD coding, with the label embeddings significantly contributing to the good performance. Our approach also leads to properly calibrated classification results, which can effectively inform downstream tasks such as quantification.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gomes-etal-2024-accurate">
<titleInfo>
<title>Accurate and Well-Calibrated ICD Code Assignment Through Attention Over Diverse Label Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Goncalo</namePart>
<namePart type="family">Gomes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabel</namePart>
<namePart type="family">Coutinho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bruno</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Purver</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Although the International Classification of Diseases (ICD) has been adopted worldwide, manually assigning ICD codes to clinical text is time-consuming, error-prone, and expensive, motivating the development of automated approaches. This paper describes a novel approach for automated ICD coding, combining several ideas from previous related work. We specifically employ a strong Transformer-based model as a text encoder and, to handle lengthy clinical narratives, we explored either (a) adapting the base encoder model into a Longformer, or (b) dividing the text into chunks and processing each chunk independently. The representations produced by the encoder are combined with a label embedding mechanism that explores diverse ICD code synonyms. Experiments with different splits of the MIMIC-III dataset show that the proposed approach outperforms the current state-of-the-art models in ICD coding, with the label embeddings significantly contributing to the good performance. Our approach also leads to properly calibrated classification results, which can effectively inform downstream tasks such as quantification.</abstract>
<identifier type="citekey">gomes-etal-2024-accurate</identifier>
<location>
<url>https://aclanthology.org/2024.eacl-long.141</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>2302</start>
<end>2315</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Accurate and Well-Calibrated ICD Code Assignment Through Attention Over Diverse Label Embeddings
%A Gomes, Goncalo
%A Coutinho, Isabel
%A Martins, Bruno
%Y Graham, Yvette
%Y Purver, Matthew
%S Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F gomes-etal-2024-accurate
%X Although the International Classification of Diseases (ICD) has been adopted worldwide, manually assigning ICD codes to clinical text is time-consuming, error-prone, and expensive, motivating the development of automated approaches. This paper describes a novel approach for automated ICD coding, combining several ideas from previous related work. We specifically employ a strong Transformer-based model as a text encoder and, to handle lengthy clinical narratives, we explored either (a) adapting the base encoder model into a Longformer, or (b) dividing the text into chunks and processing each chunk independently. The representations produced by the encoder are combined with a label embedding mechanism that explores diverse ICD code synonyms. Experiments with different splits of the MIMIC-III dataset show that the proposed approach outperforms the current state-of-the-art models in ICD coding, with the label embeddings significantly contributing to the good performance. Our approach also leads to properly calibrated classification results, which can effectively inform downstream tasks such as quantification.
%U https://aclanthology.org/2024.eacl-long.141
%P 2302-2315
Markdown (Informal)
[Accurate and Well-Calibrated ICD Code Assignment Through Attention Over Diverse Label Embeddings](https://aclanthology.org/2024.eacl-long.141) (Gomes et al., EACL 2024)
ACL