@inproceedings{kweon-etal-2024-publicly,
title = "Publicly Shareable Clinical Large Language Model Built on Synthetic Clinical Notes",
author = "Kweon, Sunjun and
Kim, Junu and
Kim, Jiyoun and
Im, Sujeong and
Cho, Eunbyeol and
Bae, Seongsu and
Oh, Jungwoo and
Lee, Gyubok and
Moon, Jong Hak and
You, Seng Chan and
Baek, Seungjin and
Han, Chang Hoon and
Jung, Yoon Bin and
Jo, Yohan and
Choi, Edward",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.305",
doi = "10.18653/v1/2024.findings-acl.305",
pages = "5148--5168",
abstract = "The development of large language models tailored for handling patients{'} clinical notes is often hindered by the limited accessibility and usability of these notes due to strict privacy regulations.To address these challenges, we first create synthetic large-scale clinical notes using publicly available case reports extracted from biomedical literature.We then use these synthetic notes to train our specialized clinical large language model, Asclepius.While Asclepius is trained on synthetic data, we assess its potential performance in real-world applications by evaluating it using real clinical notes.We benchmark Asclepius against several other large language models, including GPT-3.5-turbo and other open-source alternatives. To further validate our approach using synthetic notes, we also compare Asclepius with its variants trained on real clinical notes. Our findings convincingly demonstrate that synthetic clinical notes can serve as viable substitutes for real ones when constructing high-performing clinical language models. This conclusion is supported by detailed evaluations conducted by both GPT-4 and medical professionals. All resources{---}including weights, codes, and data{---}used in the development of Asclepius will be made publicly accessible for future research.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kweon-etal-2024-publicly">
<titleInfo>
<title>Publicly Shareable Clinical Large Language Model Built on Synthetic Clinical Notes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sunjun</namePart>
<namePart type="family">Kweon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junu</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiyoun</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujeong</namePart>
<namePart type="family">Im</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eunbyeol</namePart>
<namePart type="family">Cho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seongsu</namePart>
<namePart type="family">Bae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jungwoo</namePart>
<namePart type="family">Oh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gyubok</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jong</namePart>
<namePart type="given">Hak</namePart>
<namePart type="family">Moon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seng</namePart>
<namePart type="given">Chan</namePart>
<namePart type="family">You</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seungjin</namePart>
<namePart type="family">Baek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chang</namePart>
<namePart type="given">Hoon</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoon</namePart>
<namePart type="given">Bin</namePart>
<namePart type="family">Jung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yohan</namePart>
<namePart type="family">Jo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Edward</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The development of large language models tailored for handling patients’ clinical notes is often hindered by the limited accessibility and usability of these notes due to strict privacy regulations.To address these challenges, we first create synthetic large-scale clinical notes using publicly available case reports extracted from biomedical literature.We then use these synthetic notes to train our specialized clinical large language model, Asclepius.While Asclepius is trained on synthetic data, we assess its potential performance in real-world applications by evaluating it using real clinical notes.We benchmark Asclepius against several other large language models, including GPT-3.5-turbo and other open-source alternatives. To further validate our approach using synthetic notes, we also compare Asclepius with its variants trained on real clinical notes. Our findings convincingly demonstrate that synthetic clinical notes can serve as viable substitutes for real ones when constructing high-performing clinical language models. This conclusion is supported by detailed evaluations conducted by both GPT-4 and medical professionals. All resources—including weights, codes, and data—used in the development of Asclepius will be made publicly accessible for future research.</abstract>
<identifier type="citekey">kweon-etal-2024-publicly</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.305</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.305</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>5148</start>
<end>5168</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Publicly Shareable Clinical Large Language Model Built on Synthetic Clinical Notes
%A Kweon, Sunjun
%A Kim, Junu
%A Kim, Jiyoun
%A Im, Sujeong
%A Cho, Eunbyeol
%A Bae, Seongsu
%A Oh, Jungwoo
%A Lee, Gyubok
%A Moon, Jong Hak
%A You, Seng Chan
%A Baek, Seungjin
%A Han, Chang Hoon
%A Jung, Yoon Bin
%A Jo, Yohan
%A Choi, Edward
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics: ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F kweon-etal-2024-publicly
%X The development of large language models tailored for handling patients’ clinical notes is often hindered by the limited accessibility and usability of these notes due to strict privacy regulations.To address these challenges, we first create synthetic large-scale clinical notes using publicly available case reports extracted from biomedical literature.We then use these synthetic notes to train our specialized clinical large language model, Asclepius.While Asclepius is trained on synthetic data, we assess its potential performance in real-world applications by evaluating it using real clinical notes.We benchmark Asclepius against several other large language models, including GPT-3.5-turbo and other open-source alternatives. To further validate our approach using synthetic notes, we also compare Asclepius with its variants trained on real clinical notes. Our findings convincingly demonstrate that synthetic clinical notes can serve as viable substitutes for real ones when constructing high-performing clinical language models. This conclusion is supported by detailed evaluations conducted by both GPT-4 and medical professionals. All resources—including weights, codes, and data—used in the development of Asclepius will be made publicly accessible for future research.
%R 10.18653/v1/2024.findings-acl.305
%U https://aclanthology.org/2024.findings-acl.305
%U https://doi.org/10.18653/v1/2024.findings-acl.305
%P 5148-5168
Markdown (Informal)
[Publicly Shareable Clinical Large Language Model Built on Synthetic Clinical Notes](https://aclanthology.org/2024.findings-acl.305) (Kweon et al., Findings 2024)
ACL
- Sunjun Kweon, Junu Kim, Jiyoun Kim, Sujeong Im, Eunbyeol Cho, Seongsu Bae, Jungwoo Oh, Gyubok Lee, Jong Hak Moon, Seng Chan You, Seungjin Baek, Chang Hoon Han, Yoon Bin Jung, Yohan Jo, and Edward Choi. 2024. Publicly Shareable Clinical Large Language Model Built on Synthetic Clinical Notes. In Findings of the Association for Computational Linguistics: ACL 2024, pages 5148–5168, Bangkok, Thailand. Association for Computational Linguistics.