<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2026-clinical">
    <titleInfo>
        <title>When Clinical Notes Are Incomplete: Fusing Clinical Notes and Time Series Using Diffusion-based Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Feilong</namePart>
        <namePart type="family">Wu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kejing</namePart>
        <namePart type="family">Yin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">William</namePart>
        <namePart type="given">K</namePart>
        <namePart type="family">Cheung</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>Fusing charted times series with clinical notes has been found useful for predictive analytics. However, the incompleteness of clinical notes can undermine prediction quality. We thus propose a novel conditional diffusion-based model called CODE to recover the missing semantics of clinical notes, which integrates EHR time series into diffusion. CODE learns to align a diffusion process with unknown levels of note incompleteness via contrastive learning, by which missing semantics is recovered from the denoising process. We evaluate the effectiveness of CODE by conducting experiments on real-world EHR data for three prediction tasks. Empirical results show that CODE with the capability to recover the missing semantics can outperform state-of-the-art baselines.</abstract>
    <identifier type="citekey">wu-etal-2026-clinical</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.2416/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>51894</start>
            <end>51913</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T When Clinical Notes Are Incomplete: Fusing Clinical Notes and Time Series Using Diffusion-based Models
%A Wu, Feilong
%A Yin, Kejing
%A Cheung, William K.
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F wu-etal-2026-clinical
%X Fusing charted times series with clinical notes has been found useful for predictive analytics. However, the incompleteness of clinical notes can undermine prediction quality. We thus propose a novel conditional diffusion-based model called CODE to recover the missing semantics of clinical notes, which integrates EHR time series into diffusion. CODE learns to align a diffusion process with unknown levels of note incompleteness via contrastive learning, by which missing semantics is recovered from the denoising process. We evaluate the effectiveness of CODE by conducting experiments on real-world EHR data for three prediction tasks. Empirical results show that CODE with the capability to recover the missing semantics can outperform state-of-the-art baselines.
%U https://aclanthology.org/2026.findings-emnlp.2416/
%P 51894-51913

Markdown (Informal)

[When Clinical Notes Are Incomplete: Fusing Clinical Notes and Time Series Using Diffusion-based Models](https://aclanthology.org/2026.findings-emnlp.2416/) (Wu et al., Findings 2026)

• When Clinical Notes Are Incomplete: Fusing Clinical Notes and Time Series Using Diffusion-based Models (Wu et al., Findings 2026)

ACL

• Feilong Wu, Kejing Yin, and William K. Cheung. 2026. When Clinical Notes Are Incomplete: Fusing Clinical Notes and Time Series Using Diffusion-based Models. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 51894–51913, Budapest, Hungary. Association for Computational Linguistics.