@inproceedings{gao-etal-2022-hierarchical,
title = "Hierarchical Annotation for Building A Suite of Clinical Natural Language Processing Tasks: Progress Note Understanding",
author = "Gao, Yanjun and
Dligach, Dmitriy and
Miller, Timothy and
Tesch, Samuel and
Laffin, Ryan and
Churpek, Matthew M. and
Afshar, Majid",
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-1.587",
pages = "5484--5493",
abstract = "Applying methods in natural language processing on electronic health records (EHR) data has attracted rising interests. Existing corpus and annotation focus on modeling textual features and relation prediction. However, there are a paucity of annotated corpus built to model clinical diagnostic thinking, a processing involving text understanding, domain knowledge abstraction and reasoning. In this work, we introduce a hierarchical annotation schema with three stages to address clinical text understanding, clinical reasoning and summarization. We create an annotated corpus based on a large collection of publicly available daily progress notes, a type of EHR that is time-sensitive, problem-oriented, and well-documented by the format of Subjective, Objective, Assessment and Plan (SOAP). We also define a new suite of tasks, Progress Note Understanding, with three tasks utilizing the three annotation stages. This new suite aims at training and evaluating future NLP models for clinical text understanding, clinical knowledge representation, inference and summarization.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gao-etal-2022-hierarchical">
<titleInfo>
<title>Hierarchical Annotation for Building A Suite of Clinical Natural Language Processing Tasks: Progress Note Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yanjun</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dmitriy</namePart>
<namePart type="family">Dligach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timothy</namePart>
<namePart type="family">Miller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samuel</namePart>
<namePart type="family">Tesch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Laffin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Churpek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Majid</namePart>
<namePart type="family">Afshar</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>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Applying methods in natural language processing on electronic health records (EHR) data has attracted rising interests. Existing corpus and annotation focus on modeling textual features and relation prediction. However, there are a paucity of annotated corpus built to model clinical diagnostic thinking, a processing involving text understanding, domain knowledge abstraction and reasoning. In this work, we introduce a hierarchical annotation schema with three stages to address clinical text understanding, clinical reasoning and summarization. We create an annotated corpus based on a large collection of publicly available daily progress notes, a type of EHR that is time-sensitive, problem-oriented, and well-documented by the format of Subjective, Objective, Assessment and Plan (SOAP). We also define a new suite of tasks, Progress Note Understanding, with three tasks utilizing the three annotation stages. This new suite aims at training and evaluating future NLP models for clinical text understanding, clinical knowledge representation, inference and summarization.</abstract>
<identifier type="citekey">gao-etal-2022-hierarchical</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.587</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>5484</start>
<end>5493</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hierarchical Annotation for Building A Suite of Clinical Natural Language Processing Tasks: Progress Note Understanding
%A Gao, Yanjun
%A Dligach, Dmitriy
%A Miller, Timothy
%A Tesch, Samuel
%A Laffin, Ryan
%A Churpek, Matthew M.
%A Afshar, Majid
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F gao-etal-2022-hierarchical
%X Applying methods in natural language processing on electronic health records (EHR) data has attracted rising interests. Existing corpus and annotation focus on modeling textual features and relation prediction. However, there are a paucity of annotated corpus built to model clinical diagnostic thinking, a processing involving text understanding, domain knowledge abstraction and reasoning. In this work, we introduce a hierarchical annotation schema with three stages to address clinical text understanding, clinical reasoning and summarization. We create an annotated corpus based on a large collection of publicly available daily progress notes, a type of EHR that is time-sensitive, problem-oriented, and well-documented by the format of Subjective, Objective, Assessment and Plan (SOAP). We also define a new suite of tasks, Progress Note Understanding, with three tasks utilizing the three annotation stages. This new suite aims at training and evaluating future NLP models for clinical text understanding, clinical knowledge representation, inference and summarization.
%U https://aclanthology.org/2022.lrec-1.587
%P 5484-5493
Markdown (Informal)
[Hierarchical Annotation for Building A Suite of Clinical Natural Language Processing Tasks: Progress Note Understanding](https://aclanthology.org/2022.lrec-1.587) (Gao et al., LREC 2022)
ACL