@inproceedings{tepper-etal-2012-statistical,
title = "Statistical Section Segmentation in Free-Text Clinical Records",
author = "Tepper, Michael and
Capurro, Daniel and
Xia, Fei and
Vanderwende, Lucy and
Yetisgen-Yildiz, Meliha",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/1016_Paper.pdf",
pages = "2001--2008",
abstract = "Automatically segmenting and classifying clinical free text into sections is an important first step to automatic information retrieval, information extraction and data mining tasks, as it helps to ground the significance of the text within. In this work we describe our approach to automatic section segmentation of clinical records such as hospital discharge summaries and radiology reports, along with section classification into pre-defined section categories. We apply machine learning to the problems of section segmentation and section classification, comparing a joint (one-step) and a pipeline (two-step) approach. We demonstrate that our systems perform well when tested on three data sets, two for hospital discharge summaries and one for radiology reports. We then show the usefulness of section information by incorporating it in the task of extracting comorbidities from discharge summaries.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tepper-etal-2012-statistical">
<titleInfo>
<title>Statistical Section Segmentation in Free-Text Clinical Records</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Tepper</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Capurro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucy</namePart>
<namePart type="family">Vanderwende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meliha</namePart>
<namePart type="family">Yetisgen-Yildiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Khalid</namePart>
<namePart type="family">Choukri</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Asuncion</namePart>
<namePart type="family">Moreno</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 (ELRA)</publisher>
<place>
<placeTerm type="text">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automatically segmenting and classifying clinical free text into sections is an important first step to automatic information retrieval, information extraction and data mining tasks, as it helps to ground the significance of the text within. In this work we describe our approach to automatic section segmentation of clinical records such as hospital discharge summaries and radiology reports, along with section classification into pre-defined section categories. We apply machine learning to the problems of section segmentation and section classification, comparing a joint (one-step) and a pipeline (two-step) approach. We demonstrate that our systems perform well when tested on three data sets, two for hospital discharge summaries and one for radiology reports. We then show the usefulness of section information by incorporating it in the task of extracting comorbidities from discharge summaries.</abstract>
<identifier type="citekey">tepper-etal-2012-statistical</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/1016_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>2001</start>
<end>2008</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Statistical Section Segmentation in Free-Text Clinical Records
%A Tepper, Michael
%A Capurro, Daniel
%A Xia, Fei
%A Vanderwende, Lucy
%A Yetisgen-Yildiz, Meliha
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F tepper-etal-2012-statistical
%X Automatically segmenting and classifying clinical free text into sections is an important first step to automatic information retrieval, information extraction and data mining tasks, as it helps to ground the significance of the text within. In this work we describe our approach to automatic section segmentation of clinical records such as hospital discharge summaries and radiology reports, along with section classification into pre-defined section categories. We apply machine learning to the problems of section segmentation and section classification, comparing a joint (one-step) and a pipeline (two-step) approach. We demonstrate that our systems perform well when tested on three data sets, two for hospital discharge summaries and one for radiology reports. We then show the usefulness of section information by incorporating it in the task of extracting comorbidities from discharge summaries.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/1016_Paper.pdf
%P 2001-2008
Markdown (Informal)
[Statistical Section Segmentation in Free-Text Clinical Records](http://www.lrec-conf.org/proceedings/lrec2012/pdf/1016_Paper.pdf) (Tepper et al., LREC 2012)
ACL
- Michael Tepper, Daniel Capurro, Fei Xia, Lucy Vanderwende, and Meliha Yetisgen-Yildiz. 2012. Statistical Section Segmentation in Free-Text Clinical Records. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 2001–2008, Istanbul, Turkey. European Language Resources Association (ELRA).