@inproceedings{lehman-etal-2022-learning,
title = "Learning to Ask Like a Physician",
author = "Lehman, Eric and
Lialin, Vladislav and
Legaspi, Katelyn Edelwina and
Sy, Anne Janelle and
Pile, Patricia Therese and
Alberto, Nicole Rose and
Ragasa, Richard Raymund and
Puyat, Corinna Victoria and
Tali{\~n}o, Marianne Katharina and
Alberto, Isabelle Rose and
Alfonso, Pia Gabrielle and
Moukheiber, Dana and
Wallace, Byron and
Rumshisky, Anna and
Liang, Jennifer and
Raghavan, Preethi and
Celi, Leo Anthony and
Szolovits, Peter",
editor = "Naumann, Tristan and
Bethard, Steven and
Roberts, Kirk and
Rumshisky, Anna",
booktitle = "Proceedings of the 4th Clinical Natural Language Processing Workshop",
month = jul,
year = "2022",
address = "Seattle, WA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.clinicalnlp-1.8",
doi = "10.18653/v1/2022.clinicalnlp-1.8",
pages = "74--86",
abstract = "Existing question answering (QA) datasets derived from electronic health records (EHR) are artificially generated and consequently fail to capture realistic physician information needs. We present Discharge Summary Clinical Questions (DiSCQ), a newly curated question dataset composed of 2,000+ questions paired with the snippets of text (triggers) that prompted each question. The questions are generated by medical experts from 100+ MIMIC-III discharge summaries. We analyze this dataset to characterize the types of information sought by medical experts. We also train baseline models for trigger detection and question generation (QG), paired with unsupervised answer retrieval over EHRs. Our baseline model is able to generate high quality questions in over 62{\%} of cases when prompted with human selected triggers. We release this dataset (and all code to reproduce baseline model results) to facilitate further research into realistic clinical QA and QG: \url{https://github.com/elehman16/discq}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lehman-etal-2022-learning">
<titleInfo>
<title>Learning to Ask Like a Physician</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Lehman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vladislav</namePart>
<namePart type="family">Lialin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katelyn</namePart>
<namePart type="given">Edelwina</namePart>
<namePart type="family">Legaspi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anne</namePart>
<namePart type="given">Janelle</namePart>
<namePart type="family">Sy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patricia</namePart>
<namePart type="given">Therese</namePart>
<namePart type="family">Pile</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicole</namePart>
<namePart type="given">Rose</namePart>
<namePart type="family">Alberto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="given">Raymund</namePart>
<namePart type="family">Ragasa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Corinna</namePart>
<namePart type="given">Victoria</namePart>
<namePart type="family">Puyat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianne</namePart>
<namePart type="given">Katharina</namePart>
<namePart type="family">Taliño</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="given">Rose</namePart>
<namePart type="family">Alberto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pia</namePart>
<namePart type="given">Gabrielle</namePart>
<namePart type="family">Alfonso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dana</namePart>
<namePart type="family">Moukheiber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Byron</namePart>
<namePart type="family">Wallace</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jennifer</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preethi</namePart>
<namePart type="family">Raghavan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="given">Anthony</namePart>
<namePart type="family">Celi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Szolovits</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 4th Clinical Natural Language Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tristan</namePart>
<namePart type="family">Naumann</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">Kirk</namePart>
<namePart type="family">Roberts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, WA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Existing question answering (QA) datasets derived from electronic health records (EHR) are artificially generated and consequently fail to capture realistic physician information needs. We present Discharge Summary Clinical Questions (DiSCQ), a newly curated question dataset composed of 2,000+ questions paired with the snippets of text (triggers) that prompted each question. The questions are generated by medical experts from 100+ MIMIC-III discharge summaries. We analyze this dataset to characterize the types of information sought by medical experts. We also train baseline models for trigger detection and question generation (QG), paired with unsupervised answer retrieval over EHRs. Our baseline model is able to generate high quality questions in over 62% of cases when prompted with human selected triggers. We release this dataset (and all code to reproduce baseline model results) to facilitate further research into realistic clinical QA and QG: https://github.com/elehman16/discq.</abstract>
<identifier type="citekey">lehman-etal-2022-learning</identifier>
<identifier type="doi">10.18653/v1/2022.clinicalnlp-1.8</identifier>
<location>
<url>https://aclanthology.org/2022.clinicalnlp-1.8</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>74</start>
<end>86</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning to Ask Like a Physician
%A Lehman, Eric
%A Lialin, Vladislav
%A Legaspi, Katelyn Edelwina
%A Sy, Anne Janelle
%A Pile, Patricia Therese
%A Alberto, Nicole Rose
%A Ragasa, Richard Raymund
%A Puyat, Corinna Victoria
%A Taliño, Marianne Katharina
%A Alberto, Isabelle Rose
%A Alfonso, Pia Gabrielle
%A Moukheiber, Dana
%A Wallace, Byron
%A Rumshisky, Anna
%A Liang, Jennifer
%A Raghavan, Preethi
%A Celi, Leo Anthony
%A Szolovits, Peter
%Y Naumann, Tristan
%Y Bethard, Steven
%Y Roberts, Kirk
%Y Rumshisky, Anna
%S Proceedings of the 4th Clinical Natural Language Processing Workshop
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, WA
%F lehman-etal-2022-learning
%X Existing question answering (QA) datasets derived from electronic health records (EHR) are artificially generated and consequently fail to capture realistic physician information needs. We present Discharge Summary Clinical Questions (DiSCQ), a newly curated question dataset composed of 2,000+ questions paired with the snippets of text (triggers) that prompted each question. The questions are generated by medical experts from 100+ MIMIC-III discharge summaries. We analyze this dataset to characterize the types of information sought by medical experts. We also train baseline models for trigger detection and question generation (QG), paired with unsupervised answer retrieval over EHRs. Our baseline model is able to generate high quality questions in over 62% of cases when prompted with human selected triggers. We release this dataset (and all code to reproduce baseline model results) to facilitate further research into realistic clinical QA and QG: https://github.com/elehman16/discq.
%R 10.18653/v1/2022.clinicalnlp-1.8
%U https://aclanthology.org/2022.clinicalnlp-1.8
%U https://doi.org/10.18653/v1/2022.clinicalnlp-1.8
%P 74-86
Markdown (Informal)
[Learning to Ask Like a Physician](https://aclanthology.org/2022.clinicalnlp-1.8) (Lehman et al., ClinicalNLP 2022)
ACL
- Eric Lehman, Vladislav Lialin, Katelyn Edelwina Legaspi, Anne Janelle Sy, Patricia Therese Pile, Nicole Rose Alberto, Richard Raymund Ragasa, Corinna Victoria Puyat, Marianne Katharina Taliño, Isabelle Rose Alberto, Pia Gabrielle Alfonso, Dana Moukheiber, Byron Wallace, Anna Rumshisky, Jennifer Liang, Preethi Raghavan, Leo Anthony Celi, and Peter Szolovits. 2022. Learning to Ask Like a Physician. In Proceedings of the 4th Clinical Natural Language Processing Workshop, pages 74–86, Seattle, WA. Association for Computational Linguistics.