@inproceedings{alghanmi-etal-2022-self,
title = "Self-Supervised Intermediate Fine-Tuning of Biomedical Language Models for Interpreting Patient Case Descriptions",
author = "Alghanmi, Israa and
Espinosa-Anke, Luis and
Schockaert, Steven",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.123",
pages = "1432--1441",
abstract = "Interpreting patient case descriptions has emerged as a challenging problem for biomedical NLP, where the aim is typically to predict diagnoses, to recommended treatments, or to answer questions about cases more generally. Previous work has found that biomedical language models often lack the knowledge that is needed for such tasks. In this paper, we aim to improve their performance through a self-supervised intermediate fine-tuning strategy based on PubMed abstracts. Our solution builds on the observation that many of these abstracts are case reports, and thus essentially patient case descriptions. As a general strategy, we propose to fine-tune biomedical language models on the task of predicting masked medical concepts from such abstracts. We find that the success of this strategy crucially depends on the selection of the medical concepts to be masked. By ensuring that these concepts are sufficiently salient, we can substantially boost the performance of biomedical language models, achieving state-of-the-art results on two benchmarks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alghanmi-etal-2022-self">
<titleInfo>
<title>Self-Supervised Intermediate Fine-Tuning of Biomedical Language Models for Interpreting Patient Case Descriptions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Israa</namePart>
<namePart type="family">Alghanmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Espinosa-Anke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Interpreting patient case descriptions has emerged as a challenging problem for biomedical NLP, where the aim is typically to predict diagnoses, to recommended treatments, or to answer questions about cases more generally. Previous work has found that biomedical language models often lack the knowledge that is needed for such tasks. In this paper, we aim to improve their performance through a self-supervised intermediate fine-tuning strategy based on PubMed abstracts. Our solution builds on the observation that many of these abstracts are case reports, and thus essentially patient case descriptions. As a general strategy, we propose to fine-tune biomedical language models on the task of predicting masked medical concepts from such abstracts. We find that the success of this strategy crucially depends on the selection of the medical concepts to be masked. By ensuring that these concepts are sufficiently salient, we can substantially boost the performance of biomedical language models, achieving state-of-the-art results on two benchmarks.</abstract>
<identifier type="citekey">alghanmi-etal-2022-self</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.123</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>1432</start>
<end>1441</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Self-Supervised Intermediate Fine-Tuning of Biomedical Language Models for Interpreting Patient Case Descriptions
%A Alghanmi, Israa
%A Espinosa-Anke, Luis
%A Schockaert, Steven
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F alghanmi-etal-2022-self
%X Interpreting patient case descriptions has emerged as a challenging problem for biomedical NLP, where the aim is typically to predict diagnoses, to recommended treatments, or to answer questions about cases more generally. Previous work has found that biomedical language models often lack the knowledge that is needed for such tasks. In this paper, we aim to improve their performance through a self-supervised intermediate fine-tuning strategy based on PubMed abstracts. Our solution builds on the observation that many of these abstracts are case reports, and thus essentially patient case descriptions. As a general strategy, we propose to fine-tune biomedical language models on the task of predicting masked medical concepts from such abstracts. We find that the success of this strategy crucially depends on the selection of the medical concepts to be masked. By ensuring that these concepts are sufficiently salient, we can substantially boost the performance of biomedical language models, achieving state-of-the-art results on two benchmarks.
%U https://aclanthology.org/2022.coling-1.123
%P 1432-1441
Markdown (Informal)
[Self-Supervised Intermediate Fine-Tuning of Biomedical Language Models for Interpreting Patient Case Descriptions](https://aclanthology.org/2022.coling-1.123) (Alghanmi et al., COLING 2022)
ACL