@inproceedings{cahyawijaya-etal-2022-long,
title = "How Long Is Enough? Exploring the Optimal Intervals of Long-Range Clinical Note Language Modeling",
author = "Cahyawijaya, Samuel and
Wilie, Bryan and
Lovenia, Holy and
Zhong, Huan and
Zhong, MingQian and
Ip, Yuk-Yu Nancy and
Fung, Pascale",
editor = "Lavelli, Alberto and
Holderness, Eben and
Jimeno Yepes, Antonio and
Minard, Anne-Lyse and
Pustejovsky, James and
Rinaldi, Fabio",
booktitle = "Proceedings of the 13th International Workshop on Health Text Mining and Information Analysis (LOUHI)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.louhi-1.19",
doi = "10.18653/v1/2022.louhi-1.19",
pages = "160--172",
abstract = "Large pre-trained language models (LMs) have been widely adopted in biomedical and clinical domains, introducing many powerful LMs such as bio-lm and BioELECTRA. However, the applicability of these methods to real clinical use cases is hindered, due to the limitation of pre-trained LMs in processing long textual data with thousands of words, which is a common length for a clinical note. In this work, we explore long-range adaptation from such LMs with Longformer, allowing the LMs to capture longer clinical notes context. We conduct experiments on three n2c2 challenges datasets and a longitudinal clinical dataset from Hong Kong Hospital Authority electronic health record (EHR) system to show the effectiveness and generalizability of this concept, achieving {\textasciitilde}10{\%} F1-score improvement. Based on our experiments, we conclude that capturing a longer clinical note interval is beneficial to the model performance, but there are different cut-off intervals to achieve the optimal performance for different target variables.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cahyawijaya-etal-2022-long">
<titleInfo>
<title>How Long Is Enough? Exploring the Optimal Intervals of Long-Range Clinical Note Language Modeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Samuel</namePart>
<namePart type="family">Cahyawijaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bryan</namePart>
<namePart type="family">Wilie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Holy</namePart>
<namePart type="family">Lovenia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huan</namePart>
<namePart type="family">Zhong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">MingQian</namePart>
<namePart type="family">Zhong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuk-Yu</namePart>
<namePart type="given">Nancy</namePart>
<namePart type="family">Ip</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pascale</namePart>
<namePart type="family">Fung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 13th International Workshop on Health Text Mining and Information Analysis (LOUHI)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Lavelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eben</namePart>
<namePart type="family">Holderness</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Jimeno Yepes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anne-Lyse</namePart>
<namePart type="family">Minard</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">Fabio</namePart>
<namePart type="family">Rinaldi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large pre-trained language models (LMs) have been widely adopted in biomedical and clinical domains, introducing many powerful LMs such as bio-lm and BioELECTRA. However, the applicability of these methods to real clinical use cases is hindered, due to the limitation of pre-trained LMs in processing long textual data with thousands of words, which is a common length for a clinical note. In this work, we explore long-range adaptation from such LMs with Longformer, allowing the LMs to capture longer clinical notes context. We conduct experiments on three n2c2 challenges datasets and a longitudinal clinical dataset from Hong Kong Hospital Authority electronic health record (EHR) system to show the effectiveness and generalizability of this concept, achieving ~10% F1-score improvement. Based on our experiments, we conclude that capturing a longer clinical note interval is beneficial to the model performance, but there are different cut-off intervals to achieve the optimal performance for different target variables.</abstract>
<identifier type="citekey">cahyawijaya-etal-2022-long</identifier>
<identifier type="doi">10.18653/v1/2022.louhi-1.19</identifier>
<location>
<url>https://aclanthology.org/2022.louhi-1.19</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>160</start>
<end>172</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How Long Is Enough? Exploring the Optimal Intervals of Long-Range Clinical Note Language Modeling
%A Cahyawijaya, Samuel
%A Wilie, Bryan
%A Lovenia, Holy
%A Zhong, Huan
%A Zhong, MingQian
%A Ip, Yuk-Yu Nancy
%A Fung, Pascale
%Y Lavelli, Alberto
%Y Holderness, Eben
%Y Jimeno Yepes, Antonio
%Y Minard, Anne-Lyse
%Y Pustejovsky, James
%Y Rinaldi, Fabio
%S Proceedings of the 13th International Workshop on Health Text Mining and Information Analysis (LOUHI)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F cahyawijaya-etal-2022-long
%X Large pre-trained language models (LMs) have been widely adopted in biomedical and clinical domains, introducing many powerful LMs such as bio-lm and BioELECTRA. However, the applicability of these methods to real clinical use cases is hindered, due to the limitation of pre-trained LMs in processing long textual data with thousands of words, which is a common length for a clinical note. In this work, we explore long-range adaptation from such LMs with Longformer, allowing the LMs to capture longer clinical notes context. We conduct experiments on three n2c2 challenges datasets and a longitudinal clinical dataset from Hong Kong Hospital Authority electronic health record (EHR) system to show the effectiveness and generalizability of this concept, achieving ~10% F1-score improvement. Based on our experiments, we conclude that capturing a longer clinical note interval is beneficial to the model performance, but there are different cut-off intervals to achieve the optimal performance for different target variables.
%R 10.18653/v1/2022.louhi-1.19
%U https://aclanthology.org/2022.louhi-1.19
%U https://doi.org/10.18653/v1/2022.louhi-1.19
%P 160-172
Markdown (Informal)
[How Long Is Enough? Exploring the Optimal Intervals of Long-Range Clinical Note Language Modeling](https://aclanthology.org/2022.louhi-1.19) (Cahyawijaya et al., Louhi 2022)
ACL