Interpretable ICD Code Classification with Faithful Sentence Extraction

Yichen Wang; Lian Hong; Masato Mizogaki; Shunnosuke Umeda; Toshimune Kenmotsu; Akihiro Tamura; Daniel Andrade

Interpretable ICD Code Classification with Faithful Sentence Extraction

Yichen Wang, Lian Hong, Masato Mizogaki, Shunnosuke Umeda, Toshimune Kenmotsu, Akihiro Tamura, Daniel Andrade

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>. You may use <b>...</b> for bold, <i>...</i> for italic, and <url>...</url> for URLs.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

Transformer-based models such as PLM-CA achieve strong performance for automatic ICD coding, but their attention weights do not provide faithful explanations of their predictions. This is a major limitation for electronic medical records, where users often need concise and trustworthy evidence for each assigned code. To address this issue, we jointly train a sentence extractor and an ICD code classifier such that predictions are based only on the extracted sentences. As a result, the extracted sentences serve as faithful rationales for each predicted code and substantially reduce the effort required to inspect long medical records. Experiments on MIMIC-III show that our method approaches the performance of a transformer baseline that processes the full record while using only a small fraction of the document.

Anthology ID:: 2026.bionlp-1.54
Volume:: BioNLP 2026
Month:: July
Year:: 2026
Address:: San Diego, California
Editors:: Dina Demner-Fushman, Sophia Ananiadou, Kirk Roberts, Junichi Tsujii
Venues:: BioNLP | WS
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 679–686
Language:
URL:: https://aclanthology.org/2026.bionlp-1.54/
DOI:
Bibkey:
Cite (ACL):: Yichen Wang, Lian Hong, Masato Mizogaki, Shunnosuke Umeda, Toshimune Kenmotsu, Akihiro Tamura, and Daniel Andrade. 2026. Interpretable ICD Code Classification with Faithful Sentence Extraction. In BioNLP 2026, pages 679–686, San Diego, California. Association for Computational Linguistics.
Cite (Informal):: Interpretable ICD Code Classification with Faithful Sentence Extraction (Wang et al., BioNLP 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.bionlp-1.54.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{wang-etal-2026-interpretable-icd,
    title = "Interpretable {ICD} Code Classification with Faithful Sentence Extraction",
    author = "Wang, Yichen  and
      Hong, Lian  and
      Mizogaki, Masato  and
      Umeda, Shunnosuke  and
      Kenmotsu, Toshimune  and
      Tamura, Akihiro  and
      Andrade, Daniel",
    editor = "Demner-Fushman, Dina  and
      Ananiadou, Sophia  and
      Roberts, Kirk  and
      Tsujii, Junichi",
    booktitle = "{B}io{NLP} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.bionlp-1.54/",
    pages = "679--686",
    ISBN = "979-8-89176-434-7",
    abstract = "Transformer-based models such as PLM-CA achieve strong performance for automatic ICD coding, but their attention weights do not provide faithful explanations of their predictions. This is a major limitation for electronic medical records, where users often need concise and trustworthy evidence for each assigned code. To address this issue, we jointly train a sentence extractor and an ICD code classifier such that predictions are based only on the extracted sentences. As a result, the extracted sentences serve as faithful rationales for each predicted code and substantially reduce the effort required to inspect long medical records. Experiments on MIMIC-III show that our method approaches the performance of a transformer baseline that processes the full record while using only a small fraction of the document."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2026-interpretable-icd">
    <titleInfo>
        <title>Interpretable ICD Code Classification with Faithful Sentence Extraction</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yichen</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lian</namePart>
        <namePart type="family">Hong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Masato</namePart>
        <namePart type="family">Mizogaki</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shunnosuke</namePart>
        <namePart type="family">Umeda</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Toshimune</namePart>
        <namePart type="family">Kenmotsu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Akihiro</namePart>
        <namePart type="family">Tamura</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Daniel</namePart>
        <namePart type="family">Andrade</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>BioNLP 2026</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">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">San Diego, California</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-434-7</identifier>
    </relatedItem>
    <abstract>Transformer-based models such as PLM-CA achieve strong performance for automatic ICD coding, but their attention weights do not provide faithful explanations of their predictions. This is a major limitation for electronic medical records, where users often need concise and trustworthy evidence for each assigned code. To address this issue, we jointly train a sentence extractor and an ICD code classifier such that predictions are based only on the extracted sentences. As a result, the extracted sentences serve as faithful rationales for each predicted code and substantially reduce the effort required to inspect long medical records. Experiments on MIMIC-III show that our method approaches the performance of a transformer baseline that processes the full record while using only a small fraction of the document.</abstract>
    <identifier type="citekey">wang-etal-2026-interpretable-icd</identifier>
    <location>
        <url>https://aclanthology.org/2026.bionlp-1.54/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>679</start>
            <end>686</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Interpretable ICD Code Classification with Faithful Sentence Extraction
%A Wang, Yichen
%A Hong, Lian
%A Mizogaki, Masato
%A Umeda, Shunnosuke
%A Kenmotsu, Toshimune
%A Tamura, Akihiro
%A Andrade, Daniel
%Y Demner-Fushman, Dina
%Y Ananiadou, Sophia
%Y Roberts, Kirk
%Y Tsujii, Junichi
%S BioNLP 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California
%@ 979-8-89176-434-7
%F wang-etal-2026-interpretable-icd
%X Transformer-based models such as PLM-CA achieve strong performance for automatic ICD coding, but their attention weights do not provide faithful explanations of their predictions. This is a major limitation for electronic medical records, where users often need concise and trustworthy evidence for each assigned code. To address this issue, we jointly train a sentence extractor and an ICD code classifier such that predictions are based only on the extracted sentences. As a result, the extracted sentences serve as faithful rationales for each predicted code and substantially reduce the effort required to inspect long medical records. Experiments on MIMIC-III show that our method approaches the performance of a transformer baseline that processes the full record while using only a small fraction of the document.
%U https://aclanthology.org/2026.bionlp-1.54/
%P 679-686

Download as File

Markdown (Informal)

[Interpretable ICD Code Classification with Faithful Sentence Extraction](https://aclanthology.org/2026.bionlp-1.54/) (Wang et al., BioNLP 2026)

Interpretable ICD Code Classification with Faithful Sentence Extraction (Wang et al., BioNLP 2026)

ACL

Yichen Wang, Lian Hong, Masato Mizogaki, Shunnosuke Umeda, Toshimune Kenmotsu, Akihiro Tamura, and Daniel Andrade. 2026. Interpretable ICD Code Classification with Faithful Sentence Extraction. In BioNLP 2026, pages 679–686, San Diego, California. Association for Computational Linguistics.