@inproceedings{kim-etal-2022-anemic,
title = "{A}n{EMIC}: A Framework for Benchmarking {ICD} Coding Models",
author = "Kim, Juyong and
Sharma, Abheesht and
Shanbhogue, Suhas and
Weiss, Jeremy and
Ravikumar, Pradeep",
editor = "Che, Wanxiang and
Shutova, Ekaterina",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = dec,
year = "2022",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-demos.11",
doi = "10.18653/v1/2022.emnlp-demos.11",
pages = "109--120",
abstract = "Diagnostic coding, or ICD coding, is the task of assigning diagnosis codes defined by the ICD (International Classification of Diseases) standard to patient visits based on clinical notes. The current process of manual ICD coding is time-consuming and often error-prone, which suggests the need for automatic ICD coding. However, despite the long history of automatic ICD coding, there have been no standardized frameworks for benchmarking ICD coding models. We open-source an easy-to-use tool named \textit{AnEMIC}, which provides a streamlined pipeline for preprocessing, training, and evaluating for automatic ICD coding. We correct errors in preprocessing by existing works, and provide key models and weights trained on the correctly preprocessed datasets. We also provide an interactive demo performing real-time inference from custom inputs, and visualizations drawn from explainable AI to analyze the models. We hope the framework helps move the research of ICD coding forward and helps professionals explore the potential of ICD coding. The framework and the associated code are available here.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2022-anemic">
<titleInfo>
<title>AnEMIC: A Framework for Benchmarking ICD Coding Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Juyong</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abheesht</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suhas</namePart>
<namePart type="family">Shanbhogue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeremy</namePart>
<namePart type="family">Weiss</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pradeep</namePart>
<namePart type="family">Ravikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Diagnostic coding, or ICD coding, is the task of assigning diagnosis codes defined by the ICD (International Classification of Diseases) standard to patient visits based on clinical notes. The current process of manual ICD coding is time-consuming and often error-prone, which suggests the need for automatic ICD coding. However, despite the long history of automatic ICD coding, there have been no standardized frameworks for benchmarking ICD coding models. We open-source an easy-to-use tool named AnEMIC, which provides a streamlined pipeline for preprocessing, training, and evaluating for automatic ICD coding. We correct errors in preprocessing by existing works, and provide key models and weights trained on the correctly preprocessed datasets. We also provide an interactive demo performing real-time inference from custom inputs, and visualizations drawn from explainable AI to analyze the models. We hope the framework helps move the research of ICD coding forward and helps professionals explore the potential of ICD coding. The framework and the associated code are available here.</abstract>
<identifier type="citekey">kim-etal-2022-anemic</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-demos.11</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-demos.11</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>109</start>
<end>120</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AnEMIC: A Framework for Benchmarking ICD Coding Models
%A Kim, Juyong
%A Sharma, Abheesht
%A Shanbhogue, Suhas
%A Weiss, Jeremy
%A Ravikumar, Pradeep
%Y Che, Wanxiang
%Y Shutova, Ekaterina
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F kim-etal-2022-anemic
%X Diagnostic coding, or ICD coding, is the task of assigning diagnosis codes defined by the ICD (International Classification of Diseases) standard to patient visits based on clinical notes. The current process of manual ICD coding is time-consuming and often error-prone, which suggests the need for automatic ICD coding. However, despite the long history of automatic ICD coding, there have been no standardized frameworks for benchmarking ICD coding models. We open-source an easy-to-use tool named AnEMIC, which provides a streamlined pipeline for preprocessing, training, and evaluating for automatic ICD coding. We correct errors in preprocessing by existing works, and provide key models and weights trained on the correctly preprocessed datasets. We also provide an interactive demo performing real-time inference from custom inputs, and visualizations drawn from explainable AI to analyze the models. We hope the framework helps move the research of ICD coding forward and helps professionals explore the potential of ICD coding. The framework and the associated code are available here.
%R 10.18653/v1/2022.emnlp-demos.11
%U https://aclanthology.org/2022.emnlp-demos.11
%U https://doi.org/10.18653/v1/2022.emnlp-demos.11
%P 109-120
Markdown (Informal)
[AnEMIC: A Framework for Benchmarking ICD Coding Models](https://aclanthology.org/2022.emnlp-demos.11) (Kim et al., EMNLP 2022)
ACL
- Juyong Kim, Abheesht Sharma, Suhas Shanbhogue, Jeremy Weiss, and Pradeep Ravikumar. 2022. AnEMIC: A Framework for Benchmarking ICD Coding Models. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 109–120, Abu Dhabi, UAE. Association for Computational Linguistics.