@inproceedings{pourreza-shahri-etal-2020-ensemble,
title = "An Ensemble Approach for Automatic Structuring of Radiology Reports",
author = "Pourreza Shahri, Morteza and
Tahmasebi, Amir and
Ye, Bingyang and
Zhu, Henghui and
Aslam, Javed and
Ferris, Timothy",
editor = "Rumshisky, Anna and
Roberts, Kirk and
Bethard, Steven and
Naumann, Tristan",
booktitle = "Proceedings of the 3rd Clinical Natural Language Processing Workshop",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.clinicalnlp-1.28",
doi = "10.18653/v1/2020.clinicalnlp-1.28",
pages = "249--258",
abstract = "Automatic structuring of electronic medical records is of high demand for clinical workflow solutions to facilitate extraction, storage, and querying of patient care information. However, developing a scalable solution is extremely challenging, specifically for radiology reports, as most healthcare institutes use either no template or department/institute specific templates. Moreover, radiologists{'} reporting style varies from one to another as sentences are written in a telegraphic format and do not follow general English grammar rules. In this work, we present an ensemble method that consolidates the predictions of three models, capturing various attributes of textual information for automatic labeling of sentences with section labels. These three models are: 1) Focus Sentence model, capturing context of the target sentence; 2) Surrounding Context model, capturing the neighboring context of the target sentence; and finally, 3) Formatting/Layout model, aimed at learning report formatting cues. We utilize Bi-directional LSTMs, followed by sentence encoders, to acquire the context. Furthermore, we define several features that incorporate the structure of reports. We compare our proposed approach against multiple baselines and state-of-the-art approaches on a proprietary dataset as well as 100 manually annotated radiology notes from the MIMIC-III dataset, which we are making publicly available. Our proposed approach significantly outperforms other approaches by achieving 97.1{\%} accuracy.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pourreza-shahri-etal-2020-ensemble">
<titleInfo>
<title>An Ensemble Approach for Automatic Structuring of Radiology Reports</title>
</titleInfo>
<name type="personal">
<namePart type="given">Morteza</namePart>
<namePart type="family">Pourreza Shahri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="family">Tahmasebi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bingyang</namePart>
<namePart type="family">Ye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henghui</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Javed</namePart>
<namePart type="family">Aslam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timothy</namePart>
<namePart type="family">Ferris</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Clinical Natural Language Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kirk</namePart>
<namePart type="family">Roberts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tristan</namePart>
<namePart type="family">Naumann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automatic structuring of electronic medical records is of high demand for clinical workflow solutions to facilitate extraction, storage, and querying of patient care information. However, developing a scalable solution is extremely challenging, specifically for radiology reports, as most healthcare institutes use either no template or department/institute specific templates. Moreover, radiologists’ reporting style varies from one to another as sentences are written in a telegraphic format and do not follow general English grammar rules. In this work, we present an ensemble method that consolidates the predictions of three models, capturing various attributes of textual information for automatic labeling of sentences with section labels. These three models are: 1) Focus Sentence model, capturing context of the target sentence; 2) Surrounding Context model, capturing the neighboring context of the target sentence; and finally, 3) Formatting/Layout model, aimed at learning report formatting cues. We utilize Bi-directional LSTMs, followed by sentence encoders, to acquire the context. Furthermore, we define several features that incorporate the structure of reports. We compare our proposed approach against multiple baselines and state-of-the-art approaches on a proprietary dataset as well as 100 manually annotated radiology notes from the MIMIC-III dataset, which we are making publicly available. Our proposed approach significantly outperforms other approaches by achieving 97.1% accuracy.</abstract>
<identifier type="citekey">pourreza-shahri-etal-2020-ensemble</identifier>
<identifier type="doi">10.18653/v1/2020.clinicalnlp-1.28</identifier>
<location>
<url>https://aclanthology.org/2020.clinicalnlp-1.28</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>249</start>
<end>258</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Ensemble Approach for Automatic Structuring of Radiology Reports
%A Pourreza Shahri, Morteza
%A Tahmasebi, Amir
%A Ye, Bingyang
%A Zhu, Henghui
%A Aslam, Javed
%A Ferris, Timothy
%Y Rumshisky, Anna
%Y Roberts, Kirk
%Y Bethard, Steven
%Y Naumann, Tristan
%S Proceedings of the 3rd Clinical Natural Language Processing Workshop
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F pourreza-shahri-etal-2020-ensemble
%X Automatic structuring of electronic medical records is of high demand for clinical workflow solutions to facilitate extraction, storage, and querying of patient care information. However, developing a scalable solution is extremely challenging, specifically for radiology reports, as most healthcare institutes use either no template or department/institute specific templates. Moreover, radiologists’ reporting style varies from one to another as sentences are written in a telegraphic format and do not follow general English grammar rules. In this work, we present an ensemble method that consolidates the predictions of three models, capturing various attributes of textual information for automatic labeling of sentences with section labels. These three models are: 1) Focus Sentence model, capturing context of the target sentence; 2) Surrounding Context model, capturing the neighboring context of the target sentence; and finally, 3) Formatting/Layout model, aimed at learning report formatting cues. We utilize Bi-directional LSTMs, followed by sentence encoders, to acquire the context. Furthermore, we define several features that incorporate the structure of reports. We compare our proposed approach against multiple baselines and state-of-the-art approaches on a proprietary dataset as well as 100 manually annotated radiology notes from the MIMIC-III dataset, which we are making publicly available. Our proposed approach significantly outperforms other approaches by achieving 97.1% accuracy.
%R 10.18653/v1/2020.clinicalnlp-1.28
%U https://aclanthology.org/2020.clinicalnlp-1.28
%U https://doi.org/10.18653/v1/2020.clinicalnlp-1.28
%P 249-258
Markdown (Informal)
[An Ensemble Approach for Automatic Structuring of Radiology Reports](https://aclanthology.org/2020.clinicalnlp-1.28) (Pourreza Shahri et al., ClinicalNLP 2020)
ACL