@inproceedings{baksi-etal-2025-medcoder,
title = "{M}ed{C}od{ER}: A Generative {AI} Assistant for Medical Coding",
author = "Baksi, Krishanu Das and
Soba, Elijah and
Higgins, John J and
Saini, Ravi and
Wood, Jaden and
Cook, Jane and
Scott, Jack I and
Pudota, Nirmala and
Weninger, Tim and
Bowen, Edward and
Bhattacharya, Sanmitra",
editor = "Chen, Weizhu and
Yang, Yi and
Kachuee, Mohammad and
Fu, Xue-Yong",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: Industry Track)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-industry.37/",
doi = "10.18653/v1/2025.naacl-industry.37",
pages = "449--459",
ISBN = "979-8-89176-194-0",
abstract = "Medical coding standardizes clinical data but is both time-consuming and error-prone. Traditional Natural Language Processing (NLP) methods struggle with automating coding due to the large label space, lengthy text inputs, and the absence of supporting evidence annotations that justify code selection. Recent advancements in Generative Artificial Intelligence (AI) offer promising solutions to these challenges. In this work, we introduce MedCodER, an emerging Generative AI framework for automatic medical coding that leverages extraction, retrieval, and re-ranking techniques as core components. MedCodER achieves a micro-F1 score of 0.62 on International Classification of Diseases (ICD) code prediction, significantly outperforming state-of-the-art methods. Additionally, we present a new dataset containing medical records annotated with disease diagnoses, ICD codes, and supporting evidence texts (https://doi.org/10.5281/zenodo.13308316). Ablation tests confirm that MedCodER{'}s performance depends on the integration of each of its aforementioned components, as performance declines when these components are evaluated in isolation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="baksi-etal-2025-medcoder">
<titleInfo>
<title>MedCodER: A Generative AI Assistant for Medical Coding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Krishanu</namePart>
<namePart type="given">Das</namePart>
<namePart type="family">Baksi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elijah</namePart>
<namePart type="family">Soba</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="given">J</namePart>
<namePart type="family">Higgins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ravi</namePart>
<namePart type="family">Saini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaden</namePart>
<namePart type="family">Wood</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jane</namePart>
<namePart type="family">Cook</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jack</namePart>
<namePart type="given">I</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nirmala</namePart>
<namePart type="family">Pudota</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">Weninger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Edward</namePart>
<namePart type="family">Bowen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanmitra</namePart>
<namePart type="family">Bhattacharya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: Industry Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Weizhu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="family">Kachuee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xue-Yong</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-194-0</identifier>
</relatedItem>
<abstract>Medical coding standardizes clinical data but is both time-consuming and error-prone. Traditional Natural Language Processing (NLP) methods struggle with automating coding due to the large label space, lengthy text inputs, and the absence of supporting evidence annotations that justify code selection. Recent advancements in Generative Artificial Intelligence (AI) offer promising solutions to these challenges. In this work, we introduce MedCodER, an emerging Generative AI framework for automatic medical coding that leverages extraction, retrieval, and re-ranking techniques as core components. MedCodER achieves a micro-F1 score of 0.62 on International Classification of Diseases (ICD) code prediction, significantly outperforming state-of-the-art methods. Additionally, we present a new dataset containing medical records annotated with disease diagnoses, ICD codes, and supporting evidence texts (https://doi.org/10.5281/zenodo.13308316). Ablation tests confirm that MedCodER’s performance depends on the integration of each of its aforementioned components, as performance declines when these components are evaluated in isolation.</abstract>
<identifier type="citekey">baksi-etal-2025-medcoder</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-industry.37</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-industry.37/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>449</start>
<end>459</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MedCodER: A Generative AI Assistant for Medical Coding
%A Baksi, Krishanu Das
%A Soba, Elijah
%A Higgins, John J.
%A Saini, Ravi
%A Wood, Jaden
%A Cook, Jane
%A Scott, Jack I.
%A Pudota, Nirmala
%A Weninger, Tim
%A Bowen, Edward
%A Bhattacharya, Sanmitra
%Y Chen, Weizhu
%Y Yang, Yi
%Y Kachuee, Mohammad
%Y Fu, Xue-Yong
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: Industry Track)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-194-0
%F baksi-etal-2025-medcoder
%X Medical coding standardizes clinical data but is both time-consuming and error-prone. Traditional Natural Language Processing (NLP) methods struggle with automating coding due to the large label space, lengthy text inputs, and the absence of supporting evidence annotations that justify code selection. Recent advancements in Generative Artificial Intelligence (AI) offer promising solutions to these challenges. In this work, we introduce MedCodER, an emerging Generative AI framework for automatic medical coding that leverages extraction, retrieval, and re-ranking techniques as core components. MedCodER achieves a micro-F1 score of 0.62 on International Classification of Diseases (ICD) code prediction, significantly outperforming state-of-the-art methods. Additionally, we present a new dataset containing medical records annotated with disease diagnoses, ICD codes, and supporting evidence texts (https://doi.org/10.5281/zenodo.13308316). Ablation tests confirm that MedCodER’s performance depends on the integration of each of its aforementioned components, as performance declines when these components are evaluated in isolation.
%R 10.18653/v1/2025.naacl-industry.37
%U https://aclanthology.org/2025.naacl-industry.37/
%U https://doi.org/10.18653/v1/2025.naacl-industry.37
%P 449-459
Markdown (Informal)
[MedCodER: A Generative AI Assistant for Medical Coding](https://aclanthology.org/2025.naacl-industry.37/) (Baksi et al., NAACL 2025)
ACL
- Krishanu Das Baksi, Elijah Soba, John J Higgins, Ravi Saini, Jaden Wood, Jane Cook, Jack I Scott, Nirmala Pudota, Tim Weninger, Edward Bowen, and Sanmitra Bhattacharya. 2025. MedCodER: A Generative AI Assistant for Medical Coding. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: Industry Track), pages 449–459, Albuquerque, New Mexico. Association for Computational Linguistics.