@inproceedings{yaneva-etal-2022-usmle,
title = "The {USMLE}® Step 2 Clinical Skills Patient Note Corpus",
author = "Yaneva, Victoria and
Mee, Janet and
Ha, Le and
Harik, Polina and
Jodoin, Michael and
Mechaber, Alex",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.208",
doi = "10.18653/v1/2022.naacl-main.208",
pages = "2880--2886",
abstract = "This paper presents a corpus of 43,985 clinical patient notes (PNs) written by 35,156 examinees during the high-stakes USMLE® Step 2 Clinical Skills examination. In this exam, examinees interact with standardized patients - people trained to portray simulated scenarios called clinical cases. For each encounter, an examinee writes a PN, which is then scored by physician raters using a rubric of clinical concepts, expressions of which should be present in the PN. The corpus features PNs from 10 clinical cases, as well as the clinical concepts from the case rubrics. A subset of 2,840 PNs were annotated by 10 physician experts such that all 143 concepts from the case rubrics (e.g., shortness of breath) were mapped to 34,660 PN phrases (e.g., dyspnea, difficulty breathing). The corpus is available via a data sharing agreement with NBME and can be requested at https://www.nbme.org/services/data-sharing.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yaneva-etal-2022-usmle">
<titleInfo>
<title>The USMLE® Step 2 Clinical Skills Patient Note Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Victoria</namePart>
<namePart type="family">Yaneva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Janet</namePart>
<namePart type="family">Mee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Le</namePart>
<namePart type="family">Ha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Polina</namePart>
<namePart type="family">Harik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Jodoin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Mechaber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents a corpus of 43,985 clinical patient notes (PNs) written by 35,156 examinees during the high-stakes USMLE® Step 2 Clinical Skills examination. In this exam, examinees interact with standardized patients - people trained to portray simulated scenarios called clinical cases. For each encounter, an examinee writes a PN, which is then scored by physician raters using a rubric of clinical concepts, expressions of which should be present in the PN. The corpus features PNs from 10 clinical cases, as well as the clinical concepts from the case rubrics. A subset of 2,840 PNs were annotated by 10 physician experts such that all 143 concepts from the case rubrics (e.g., shortness of breath) were mapped to 34,660 PN phrases (e.g., dyspnea, difficulty breathing). The corpus is available via a data sharing agreement with NBME and can be requested at https://www.nbme.org/services/data-sharing.</abstract>
<identifier type="citekey">yaneva-etal-2022-usmle</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-main.208</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-main.208</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>2880</start>
<end>2886</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The USMLE® Step 2 Clinical Skills Patient Note Corpus
%A Yaneva, Victoria
%A Mee, Janet
%A Ha, Le
%A Harik, Polina
%A Jodoin, Michael
%A Mechaber, Alex
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F yaneva-etal-2022-usmle
%X This paper presents a corpus of 43,985 clinical patient notes (PNs) written by 35,156 examinees during the high-stakes USMLE® Step 2 Clinical Skills examination. In this exam, examinees interact with standardized patients - people trained to portray simulated scenarios called clinical cases. For each encounter, an examinee writes a PN, which is then scored by physician raters using a rubric of clinical concepts, expressions of which should be present in the PN. The corpus features PNs from 10 clinical cases, as well as the clinical concepts from the case rubrics. A subset of 2,840 PNs were annotated by 10 physician experts such that all 143 concepts from the case rubrics (e.g., shortness of breath) were mapped to 34,660 PN phrases (e.g., dyspnea, difficulty breathing). The corpus is available via a data sharing agreement with NBME and can be requested at https://www.nbme.org/services/data-sharing.
%R 10.18653/v1/2022.naacl-main.208
%U https://aclanthology.org/2022.naacl-main.208
%U https://doi.org/10.18653/v1/2022.naacl-main.208
%P 2880-2886
Markdown (Informal)
[The USMLE® Step 2 Clinical Skills Patient Note Corpus](https://aclanthology.org/2022.naacl-main.208) (Yaneva et al., NAACL 2022)
ACL
- Victoria Yaneva, Janet Mee, Le Ha, Polina Harik, Michael Jodoin, and Alex Mechaber. 2022. The USMLE® Step 2 Clinical Skills Patient Note Corpus. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2880–2886, Seattle, United States. Association for Computational Linguistics.