@inproceedings{consoli-etal-2022-brateca,
title = "{BRATECA} ({B}razilian Tertiary Care Dataset): a Clinical Information Dataset for the {P}ortuguese Language",
author = "Consoli, Bernardo and
dos Santos, Henrique D. P. and
Ulbrich, Ana Helena D. P. S. and
Vieira, Renata and
Bordini, Rafael H.",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.602",
pages = "5609--5616",
abstract = "Computational medicine research requires clinical data for training and testing purposes, so the development of datasets composed of real hospital data is of utmost importance in this field. Most such data collections are in the English language, were collected in anglophone countries, and do not reflect other clinical realities, which increases the importance of national datasets for projects that hope to positively impact public health. This paper presents a new Brazilian Clinical Dataset containing over 70,000 admissions from 10 hospitals in two Brazilian states, composed of a sum total of over 2.5 million free-text clinical notes alongside data pertaining to patient information, prescription information, and exam results. This data was collected, organized, deidentified, and is being distributed via credentialed access for the use of the research community. In the course of presenting the new dataset, this paper will explore the new dataset{'}s structure, population, and potential benefits of using this dataset in clinical AI tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="consoli-etal-2022-brateca">
<titleInfo>
<title>BRATECA (Brazilian Tertiary Care Dataset): a Clinical Information Dataset for the Portuguese Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bernardo</namePart>
<namePart type="family">Consoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henrique</namePart>
<namePart type="given">D</namePart>
<namePart type="given">P</namePart>
<namePart type="family">dos Santos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ana</namePart>
<namePart type="given">Helena</namePart>
<namePart type="given">D</namePart>
<namePart type="given">P</namePart>
<namePart type="given">S</namePart>
<namePart type="family">Ulbrich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Renata</namePart>
<namePart type="family">Vieira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rafael</namePart>
<namePart type="given">H</namePart>
<namePart type="family">Bordini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Computational medicine research requires clinical data for training and testing purposes, so the development of datasets composed of real hospital data is of utmost importance in this field. Most such data collections are in the English language, were collected in anglophone countries, and do not reflect other clinical realities, which increases the importance of national datasets for projects that hope to positively impact public health. This paper presents a new Brazilian Clinical Dataset containing over 70,000 admissions from 10 hospitals in two Brazilian states, composed of a sum total of over 2.5 million free-text clinical notes alongside data pertaining to patient information, prescription information, and exam results. This data was collected, organized, deidentified, and is being distributed via credentialed access for the use of the research community. In the course of presenting the new dataset, this paper will explore the new dataset’s structure, population, and potential benefits of using this dataset in clinical AI tasks.</abstract>
<identifier type="citekey">consoli-etal-2022-brateca</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.602</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>5609</start>
<end>5616</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BRATECA (Brazilian Tertiary Care Dataset): a Clinical Information Dataset for the Portuguese Language
%A Consoli, Bernardo
%A dos Santos, Henrique D. P.
%A Ulbrich, Ana Helena D. P. S.
%A Vieira, Renata
%A Bordini, Rafael H.
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F consoli-etal-2022-brateca
%X Computational medicine research requires clinical data for training and testing purposes, so the development of datasets composed of real hospital data is of utmost importance in this field. Most such data collections are in the English language, were collected in anglophone countries, and do not reflect other clinical realities, which increases the importance of national datasets for projects that hope to positively impact public health. This paper presents a new Brazilian Clinical Dataset containing over 70,000 admissions from 10 hospitals in two Brazilian states, composed of a sum total of over 2.5 million free-text clinical notes alongside data pertaining to patient information, prescription information, and exam results. This data was collected, organized, deidentified, and is being distributed via credentialed access for the use of the research community. In the course of presenting the new dataset, this paper will explore the new dataset’s structure, population, and potential benefits of using this dataset in clinical AI tasks.
%U https://aclanthology.org/2022.lrec-1.602
%P 5609-5616
Markdown (Informal)
[BRATECA (Brazilian Tertiary Care Dataset): a Clinical Information Dataset for the Portuguese Language](https://aclanthology.org/2022.lrec-1.602) (Consoli et al., LREC 2022)
ACL