@inproceedings{zheng-etal-2023-making,
title = "Making the Most Out of the Limited Context Length: Predictive Power Varies with Clinical Note Type and Note Section",
author = "Zheng, Hongyi and
Zhu, Yixin and
Jiang, Lavender and
Cho, Kyunghyun and
Oermann, Eric",
editor = "Padmakumar, Vishakh and
Vallejo, Gisela and
Fu, Yao",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-srw.18",
doi = "10.18653/v1/2023.acl-srw.18",
pages = "104--108",
abstract = "Recent advances in large language models have led to renewed interest in natural language processing in healthcare using the free text of clinical notes. One distinguishing characteristic of clinical notes is their long time span over multiple long documents. The unique structure of clinical notes creates a new design choice: when the context length for a language model predictor is limited, which part of clinical notes should we choose as the input? Existing studies either choose the inputs with domain knowledge or simply truncate them. We propose a framework to analyze the sections with high predictive power. Using MIMIC-III, we show that: 1) predictive power distribution is different between nursing notes and discharge notes and 2) combining different types of notes could improve performance when the context length is large. Our findings suggest that a carefully selected sampling function could enable more efficient information extraction from clinical notes.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zheng-etal-2023-making">
<titleInfo>
<title>Making the Most Out of the Limited Context Length: Predictive Power Varies with Clinical Note Type and Note Section</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hongyi</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yixin</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lavender</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyunghyun</namePart>
<namePart type="family">Cho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Oermann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vishakh</namePart>
<namePart type="family">Padmakumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gisela</namePart>
<namePart type="family">Vallejo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yao</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent advances in large language models have led to renewed interest in natural language processing in healthcare using the free text of clinical notes. One distinguishing characteristic of clinical notes is their long time span over multiple long documents. The unique structure of clinical notes creates a new design choice: when the context length for a language model predictor is limited, which part of clinical notes should we choose as the input? Existing studies either choose the inputs with domain knowledge or simply truncate them. We propose a framework to analyze the sections with high predictive power. Using MIMIC-III, we show that: 1) predictive power distribution is different between nursing notes and discharge notes and 2) combining different types of notes could improve performance when the context length is large. Our findings suggest that a carefully selected sampling function could enable more efficient information extraction from clinical notes.</abstract>
<identifier type="citekey">zheng-etal-2023-making</identifier>
<identifier type="doi">10.18653/v1/2023.acl-srw.18</identifier>
<location>
<url>https://aclanthology.org/2023.acl-srw.18</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>104</start>
<end>108</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Making the Most Out of the Limited Context Length: Predictive Power Varies with Clinical Note Type and Note Section
%A Zheng, Hongyi
%A Zhu, Yixin
%A Jiang, Lavender
%A Cho, Kyunghyun
%A Oermann, Eric
%Y Padmakumar, Vishakh
%Y Vallejo, Gisela
%Y Fu, Yao
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F zheng-etal-2023-making
%X Recent advances in large language models have led to renewed interest in natural language processing in healthcare using the free text of clinical notes. One distinguishing characteristic of clinical notes is their long time span over multiple long documents. The unique structure of clinical notes creates a new design choice: when the context length for a language model predictor is limited, which part of clinical notes should we choose as the input? Existing studies either choose the inputs with domain knowledge or simply truncate them. We propose a framework to analyze the sections with high predictive power. Using MIMIC-III, we show that: 1) predictive power distribution is different between nursing notes and discharge notes and 2) combining different types of notes could improve performance when the context length is large. Our findings suggest that a carefully selected sampling function could enable more efficient information extraction from clinical notes.
%R 10.18653/v1/2023.acl-srw.18
%U https://aclanthology.org/2023.acl-srw.18
%U https://doi.org/10.18653/v1/2023.acl-srw.18
%P 104-108
Markdown (Informal)
[Making the Most Out of the Limited Context Length: Predictive Power Varies with Clinical Note Type and Note Section](https://aclanthology.org/2023.acl-srw.18) (Zheng et al., ACL 2023)
ACL