<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alves-etal-2026-leakage">
    <titleInfo>
        <title>Leakage-Aware Evaluation of Brazilian Clinical Notes for ICU Mortality Prediction: A Study on the BRATECA Dataset</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Felipe</namePart>
        <namePart type="given">André</namePart>
        <namePart type="given">Bach</namePart>
        <namePart type="family">Alves</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Heloísa</namePart>
        <namePart type="given">Oss</namePart>
        <namePart type="family">Boll</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mariana</namePart>
        <namePart type="family">Recamonde-Mendoza</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>Proceedings of the 17th Brazilian Symposium in Information and Human Language Technology</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Bryan</namePart>
            <namePart type="given">Khelven</namePart>
            <namePart type="given">da</namePart>
            <namePart type="given">Silva</namePart>
            <namePart type="family">Barbosa</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Aline</namePart>
            <namePart type="family">Paes</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ariani</namePart>
            <namePart type="given">Di</namePart>
            <namePart type="family">Felippo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Cuiabá, Mato Grosso, Brazil</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Early prediction of ICU mortality can support clinical decisions, but retrospective notes can contain future-event cues that cause leakage in clinical NLP. We evaluate leakage-aware modeling of Brazilian Portuguese ICU notes for mortality prediction using BRATECA. We compare 24-hour restriction, regex and LLM leakage auditing, neural and TF-IDF representations, and unrestricted-note baselines. In the 24-hour setting, models achieved AUROC 0.78-0.83; unrestricted notes reached around 0.95, indicating outcome-related information in late documentation. Regex found leakage signals in 21.13% of the notes, and the LLM audit identified additional semantic cases. Results highlight the need for temporal control and leakage auditing in clinical NLP.</abstract>
    <identifier type="citekey">alves-etal-2026-leakage</identifier>
    <identifier type="doi">10.5753/stil.2026.26535</identifier>
    <location>
        <url>https://aclanthology.org/2026.stil-1.2/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>14</start>
            <end>25</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Leakage-Aware Evaluation of Brazilian Clinical Notes for ICU Mortality Prediction: A Study on the BRATECA Dataset
%A Alves, Felipe André Bach
%A Boll, Heloísa Oss
%A Recamonde-Mendoza, Mariana
%Y Barbosa, Bryan Khelven da Silva
%Y Paes, Aline
%Y Felippo, Ariani Di
%S Proceedings of the 17th Brazilian Symposium in Information and Human Language Technology
%D 2026
%8 October
%I Association for Computational Linguistics
%C Cuiabá, Mato Grosso, Brazil
%F alves-etal-2026-leakage
%X Early prediction of ICU mortality can support clinical decisions, but retrospective notes can contain future-event cues that cause leakage in clinical NLP. We evaluate leakage-aware modeling of Brazilian Portuguese ICU notes for mortality prediction using BRATECA. We compare 24-hour restriction, regex and LLM leakage auditing, neural and TF-IDF representations, and unrestricted-note baselines. In the 24-hour setting, models achieved AUROC 0.78-0.83; unrestricted notes reached around 0.95, indicating outcome-related information in late documentation. Regex found leakage signals in 21.13% of the notes, and the LLM audit identified additional semantic cases. Results highlight the need for temporal control and leakage auditing in clinical NLP.
%R 10.5753/stil.2026.26535
%U https://aclanthology.org/2026.stil-1.2/
%U https://doi.org/10.5753/stil.2026.26535
%P 14-25

Markdown (Informal)

[Leakage-Aware Evaluation of Brazilian Clinical Notes for ICU Mortality Prediction: A Study on the BRATECA Dataset](https://aclanthology.org/2026.stil-1.2/) (Alves et al., STIL 2026)

• Leakage-Aware Evaluation of Brazilian Clinical Notes for ICU Mortality Prediction: A Study on the BRATECA Dataset (Alves et al., STIL 2026)

ACL

• Felipe André Bach Alves, Heloísa Oss Boll, and Mariana Recamonde-Mendoza. 2026. Leakage-Aware Evaluation of Brazilian Clinical Notes for ICU Mortality Prediction: A Study on the BRATECA Dataset. In Proceedings of the 17th Brazilian Symposium in Information and Human Language Technology, pages 14–25, Cuiabá, Mato Grosso, Brazil. Association for Computational Linguistics.