@inproceedings{machado-etal-2026-dataset,
title = "A Dataset of {B}razilian {P}ortuguese Clinical Notes for Anaphylaxis Detection",
author = "Machado, Matheus and
Vanzin, Vin{\'i}cius and
Moreira, Dilvan and
Ensina, Luis Felipe and
Lario, F{\'a}bio",
editor = "Souza, Marlo and
de-Dios-Flores, Iria and
Santos, Diana and
Freitas, Larissa and
Souza, Jackson Wilke da Cruz and
Ribeiro, Eug{\'e}nio",
booktitle = "Proceedings of the 17th International Conference on Computational Processing of {P}ortuguese ({PROPOR} 2026) - Vol. 2",
month = apr,
year = "2026",
address = "Salvador, Brazil",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.propor-2.15/",
pages = "78--87",
ISBN = "979-8-89176-387-6",
abstract = "Anaphylaxis is an acute, potentially life-threatening allergic reaction that requires rapid recognition in clinical settings. Natural language processing (NLP) approaches for automatic detection of anaphylaxis in clinical narratives can support large-scale analysis of health records and retrospective clinical research. However, such approaches depend on high-quality labeled corpora, and resources for Portuguese remain scarce. This paper introduces a corpus of Brazilian Portuguese clinical notes annotated by domain specialists for the presence or absence of anaphylaxis. The dataset comprises 969 clinical narratives drawn from three sources: clinician-authored synthetic clinical notes designed to represent realistic scenarios, case reports from the medical literature rewritten into note-like format by specialists, and a subset of de-identified notes from the publicly available SemClinBr corpus. All texts were reviewed and labeled by allergists using established clinical diagnostic criteria, and the corpus reflects realistic prevalence conditions, with approximately 5{\%} positive cases. We describe the corpus design, data sources, annotation methodology, and composition, discuss potential research applications, and address ethical considerations. The corpus is intended as a reusable resource for Portuguese clinical NLP, supporting future work on document classification, information extraction, and language modeling in the medical domain."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="machado-etal-2026-dataset">
<titleInfo>
<title>A Dataset of Brazilian Portuguese Clinical Notes for Anaphylaxis Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Matheus</namePart>
<namePart type="family">Machado</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vinícius</namePart>
<namePart type="family">Vanzin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilvan</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="given">Felipe</namePart>
<namePart type="family">Ensina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fábio</namePart>
<namePart type="family">Lario</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026) - Vol. 2</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marlo</namePart>
<namePart type="family">Souza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iria</namePart>
<namePart type="family">de-Dios-Flores</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diana</namePart>
<namePart type="family">Santos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Larissa</namePart>
<namePart type="family">Freitas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jackson</namePart>
<namePart type="given">Wilke</namePart>
<namePart type="given">da</namePart>
<namePart type="given">Cruz</namePart>
<namePart type="family">Souza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eugénio</namePart>
<namePart type="family">Ribeiro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Salvador, Brazil</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-387-6</identifier>
</relatedItem>
<abstract>Anaphylaxis is an acute, potentially life-threatening allergic reaction that requires rapid recognition in clinical settings. Natural language processing (NLP) approaches for automatic detection of anaphylaxis in clinical narratives can support large-scale analysis of health records and retrospective clinical research. However, such approaches depend on high-quality labeled corpora, and resources for Portuguese remain scarce. This paper introduces a corpus of Brazilian Portuguese clinical notes annotated by domain specialists for the presence or absence of anaphylaxis. The dataset comprises 969 clinical narratives drawn from three sources: clinician-authored synthetic clinical notes designed to represent realistic scenarios, case reports from the medical literature rewritten into note-like format by specialists, and a subset of de-identified notes from the publicly available SemClinBr corpus. All texts were reviewed and labeled by allergists using established clinical diagnostic criteria, and the corpus reflects realistic prevalence conditions, with approximately 5% positive cases. We describe the corpus design, data sources, annotation methodology, and composition, discuss potential research applications, and address ethical considerations. The corpus is intended as a reusable resource for Portuguese clinical NLP, supporting future work on document classification, information extraction, and language modeling in the medical domain.</abstract>
<identifier type="citekey">machado-etal-2026-dataset</identifier>
<location>
<url>https://aclanthology.org/2026.propor-2.15/</url>
</location>
<part>
<date>2026-04</date>
<extent unit="page">
<start>78</start>
<end>87</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Dataset of Brazilian Portuguese Clinical Notes for Anaphylaxis Detection
%A Machado, Matheus
%A Vanzin, Vinícius
%A Moreira, Dilvan
%A Ensina, Luis Felipe
%A Lario, Fábio
%Y Souza, Marlo
%Y de-Dios-Flores, Iria
%Y Santos, Diana
%Y Freitas, Larissa
%Y Souza, Jackson Wilke da Cruz
%Y Ribeiro, Eugénio
%S Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026) - Vol. 2
%D 2026
%8 April
%I Association for Computational Linguistics
%C Salvador, Brazil
%@ 979-8-89176-387-6
%F machado-etal-2026-dataset
%X Anaphylaxis is an acute, potentially life-threatening allergic reaction that requires rapid recognition in clinical settings. Natural language processing (NLP) approaches for automatic detection of anaphylaxis in clinical narratives can support large-scale analysis of health records and retrospective clinical research. However, such approaches depend on high-quality labeled corpora, and resources for Portuguese remain scarce. This paper introduces a corpus of Brazilian Portuguese clinical notes annotated by domain specialists for the presence or absence of anaphylaxis. The dataset comprises 969 clinical narratives drawn from three sources: clinician-authored synthetic clinical notes designed to represent realistic scenarios, case reports from the medical literature rewritten into note-like format by specialists, and a subset of de-identified notes from the publicly available SemClinBr corpus. All texts were reviewed and labeled by allergists using established clinical diagnostic criteria, and the corpus reflects realistic prevalence conditions, with approximately 5% positive cases. We describe the corpus design, data sources, annotation methodology, and composition, discuss potential research applications, and address ethical considerations. The corpus is intended as a reusable resource for Portuguese clinical NLP, supporting future work on document classification, information extraction, and language modeling in the medical domain.
%U https://aclanthology.org/2026.propor-2.15/
%P 78-87
Markdown (Informal)
[A Dataset of Brazilian Portuguese Clinical Notes for Anaphylaxis Detection](https://aclanthology.org/2026.propor-2.15/) (Machado et al., PROPOR 2026)
ACL