2026-09-19T10:34:56Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1446132024-11-14T17:23:50Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Szolovits, Peter
Lehman, Eric(Computer scientist)
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2022-08-29T15:59:38Z
2022-08-29T15:59:38Z
2022-05
2022-06-21T19:25:42.893Z
https://hdl.handle.net/1721.1/144613
0000-0001-9919-2257
Existing question answering (QA) datasets derived from electronic health records (EHR) are artificially generated and, as a result, 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 will release this dataset (and all code to reproduce baseline model results) to facilitate further research into realistic clinical QA and QG.
S.M.
Massachusetts Institute of Technology
In Copyright - Educational Use Permitted
Copyright MIT
http://rightsstatements.org/page/InC-EDU/1.0/
Learning to Ask Like a Physician
Thesis
application/pdf
Master
Master of Science in Electrical Engineering and Computer Science
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="53013968-7670-492d-8bab-d9012e03887f">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Title>Learning to Ask Like a Physician</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2022-05</PublicationDate>
<Authors>
<Author>
<DisplayName>Lehman, Eric(Computer scientist)</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>http://rightsstatements.org/page/InC-EDU/1.0/</License>
<Abstract>Existing question answering (QA) datasets derived from electronic health records (EHR) are artificially generated and, as a result, 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 will release this dataset (and all code to reproduce baseline model results) to facilitate further research into realistic clinical QA and QG.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>