@inproceedings{weegar-etal-2017-efficient,
title = "Efficient Encoding of Pathology Reports Using Natural Language Processing",
author = "Weegar, Rebecka and
Nyg{\aa}rd, Jan F and
Dalianis, Hercules",
editor = "Mitkov, Ruslan and
Angelova, Galia",
booktitle = "Proceedings of the International Conference Recent Advances in Natural Language Processing, {RANLP} 2017",
month = sep,
year = "2017",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd.",
url = "https://doi.org/10.26615/978-954-452-049-6_100",
doi = "10.26615/978-954-452-049-6_100",
pages = "778--783",
abstract = "In this article we present a system that extracts information from pathology reports. The reports are written in Norwegian and contain free text describing prostate biopsies. Currently, these reports are manually coded for research and statistical purposes by trained experts at the Cancer Registry of Norway where the coders extract values for a set of predefined fields that are specific for prostate cancer. The presented system is rule based and achieves an average F-score of 0.91 for the fields Gleason grade, Gleason score, the number of biopsies that contain tumor tissue, and the orientation of the biopsies. The system also identifies reports that contain ambiguity or other content that should be reviewed by an expert. The system shows potential to encode the reports considerably faster, with less resources, and similar high quality to the manual encoding.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="weegar-etal-2017-efficient">
<titleInfo>
<title>Efficient Encoding of Pathology Reports Using Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rebecka</namePart>
<namePart type="family">Weegar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Nygård</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hercules</namePart>
<namePart type="family">Dalianis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd.</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this article we present a system that extracts information from pathology reports. The reports are written in Norwegian and contain free text describing prostate biopsies. Currently, these reports are manually coded for research and statistical purposes by trained experts at the Cancer Registry of Norway where the coders extract values for a set of predefined fields that are specific for prostate cancer. The presented system is rule based and achieves an average F-score of 0.91 for the fields Gleason grade, Gleason score, the number of biopsies that contain tumor tissue, and the orientation of the biopsies. The system also identifies reports that contain ambiguity or other content that should be reviewed by an expert. The system shows potential to encode the reports considerably faster, with less resources, and similar high quality to the manual encoding.</abstract>
<identifier type="citekey">weegar-etal-2017-efficient</identifier>
<identifier type="doi">10.26615/978-954-452-049-6_100</identifier>
<part>
<date>2017-09</date>
<extent unit="page">
<start>778</start>
<end>783</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Efficient Encoding of Pathology Reports Using Natural Language Processing
%A Weegar, Rebecka
%A Nygård, Jan F.
%A Dalianis, Hercules
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017
%D 2017
%8 September
%I INCOMA Ltd.
%C Varna, Bulgaria
%F weegar-etal-2017-efficient
%X In this article we present a system that extracts information from pathology reports. The reports are written in Norwegian and contain free text describing prostate biopsies. Currently, these reports are manually coded for research and statistical purposes by trained experts at the Cancer Registry of Norway where the coders extract values for a set of predefined fields that are specific for prostate cancer. The presented system is rule based and achieves an average F-score of 0.91 for the fields Gleason grade, Gleason score, the number of biopsies that contain tumor tissue, and the orientation of the biopsies. The system also identifies reports that contain ambiguity or other content that should be reviewed by an expert. The system shows potential to encode the reports considerably faster, with less resources, and similar high quality to the manual encoding.
%R 10.26615/978-954-452-049-6_100
%U https://doi.org/10.26615/978-954-452-049-6_100
%P 778-783
Markdown (Informal)
[Efficient Encoding of Pathology Reports Using Natural Language Processing](https://doi.org/10.26615/978-954-452-049-6_100) (Weegar et al., RANLP 2017)
ACL