@inproceedings{obuchowski-etal-2023-information,
title = "Information Extraction from {P}olish Radiology Reports Using Language Models",
author = "Obuchowski, Aleksander and
Klaudel, Barbara and
Jasik, Patryk",
editor = "Piskorski, Jakub and
Marci{\'n}czuk, Micha{\l} and
Nakov, Preslav and
Ogrodniczuk, Maciej and
Pollak, Senja and
P{\v{r}}ib{\'a}{\v{n}}, Pavel and
Rybak, Piotr and
Steinberger, Josef and
Yangarber, Roman",
booktitle = "Proceedings of the 9th Workshop on Slavic Natural Language Processing 2023 (SlavicNLP 2023)",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.bsnlp-1.14",
doi = "10.18653/v1/2023.bsnlp-1.14",
pages = "113--122",
abstract = "Radiology reports are vital elements of directing patient care. They are usually delivered in free text form, which makes them prone to errors, such as omission in reporting radiological findings and using difficult-to-comprehend mental shortcuts. Although structured reporting is the recommended method, its adoption continues to be limited. Radiologists find structured reports too limiting and burdensome. In this paper, we propose the model, which is meant to preserve the benefits of free text, while moving towards a structured report. The model automatically parametrizes Polish radiology reports based on language models. The models were trained on a large dataset of 1200 chest computed tomography (CT) reports annotated by multiple medical experts reports with 44 observation tags. Experimental analysis shows that models based on language models are able to achieve satisfactory results despite being pre-trained on general domain corpora. Overall, the model achieves an F1 score of 81{\%} and is able to successfully parametrize the most common radiological observations, allowing for potential adaptation in clinical practice. Our model is publically available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="obuchowski-etal-2023-information">
<titleInfo>
<title>Information Extraction from Polish Radiology Reports Using Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aleksander</namePart>
<namePart type="family">Obuchowski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Klaudel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patryk</namePart>
<namePart type="family">Jasik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 9th Workshop on Slavic Natural Language Processing 2023 (SlavicNLP 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jakub</namePart>
<namePart type="family">Piskorski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michał</namePart>
<namePart type="family">Marcińczuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maciej</namePart>
<namePart type="family">Ogrodniczuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Senja</namePart>
<namePart type="family">Pollak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pavel</namePart>
<namePart type="family">Přibáň</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piotr</namePart>
<namePart type="family">Rybak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josef</namePart>
<namePart type="family">Steinberger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Yangarber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Radiology reports are vital elements of directing patient care. They are usually delivered in free text form, which makes them prone to errors, such as omission in reporting radiological findings and using difficult-to-comprehend mental shortcuts. Although structured reporting is the recommended method, its adoption continues to be limited. Radiologists find structured reports too limiting and burdensome. In this paper, we propose the model, which is meant to preserve the benefits of free text, while moving towards a structured report. The model automatically parametrizes Polish radiology reports based on language models. The models were trained on a large dataset of 1200 chest computed tomography (CT) reports annotated by multiple medical experts reports with 44 observation tags. Experimental analysis shows that models based on language models are able to achieve satisfactory results despite being pre-trained on general domain corpora. Overall, the model achieves an F1 score of 81% and is able to successfully parametrize the most common radiological observations, allowing for potential adaptation in clinical practice. Our model is publically available.</abstract>
<identifier type="citekey">obuchowski-etal-2023-information</identifier>
<identifier type="doi">10.18653/v1/2023.bsnlp-1.14</identifier>
<location>
<url>https://aclanthology.org/2023.bsnlp-1.14</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>113</start>
<end>122</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Information Extraction from Polish Radiology Reports Using Language Models
%A Obuchowski, Aleksander
%A Klaudel, Barbara
%A Jasik, Patryk
%Y Piskorski, Jakub
%Y Marcińczuk, Michał
%Y Nakov, Preslav
%Y Ogrodniczuk, Maciej
%Y Pollak, Senja
%Y Přibáň, Pavel
%Y Rybak, Piotr
%Y Steinberger, Josef
%Y Yangarber, Roman
%S Proceedings of the 9th Workshop on Slavic Natural Language Processing 2023 (SlavicNLP 2023)
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F obuchowski-etal-2023-information
%X Radiology reports are vital elements of directing patient care. They are usually delivered in free text form, which makes them prone to errors, such as omission in reporting radiological findings and using difficult-to-comprehend mental shortcuts. Although structured reporting is the recommended method, its adoption continues to be limited. Radiologists find structured reports too limiting and burdensome. In this paper, we propose the model, which is meant to preserve the benefits of free text, while moving towards a structured report. The model automatically parametrizes Polish radiology reports based on language models. The models were trained on a large dataset of 1200 chest computed tomography (CT) reports annotated by multiple medical experts reports with 44 observation tags. Experimental analysis shows that models based on language models are able to achieve satisfactory results despite being pre-trained on general domain corpora. Overall, the model achieves an F1 score of 81% and is able to successfully parametrize the most common radiological observations, allowing for potential adaptation in clinical practice. Our model is publically available.
%R 10.18653/v1/2023.bsnlp-1.14
%U https://aclanthology.org/2023.bsnlp-1.14
%U https://doi.org/10.18653/v1/2023.bsnlp-1.14
%P 113-122
Markdown (Informal)
[Information Extraction from Polish Radiology Reports Using Language Models](https://aclanthology.org/2023.bsnlp-1.14) (Obuchowski et al., BSNLP 2023)
ACL