@inproceedings{krishnamoorthy-etal-2024-llm,
title = "{LLM}-Based Section Identifiers Excel on Open Source but Stumble in Real World Applications",
author = "Krishnamoorthy, Saranya and
Singh, Ayush and
Tafreshi, Shabnam",
editor = "Naumann, Tristan and
Ben Abacha, Asma and
Bethard, Steven and
Roberts, Kirk and
Bitterman, Danielle",
booktitle = "Proceedings of the 6th Clinical Natural Language Processing Workshop",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.clinicalnlp-1.22",
doi = "10.18653/v1/2024.clinicalnlp-1.22",
pages = "258--270",
abstract = "Electronic health records (EHR) even though a boon for healthcare practitioners, are grow- ing convoluted and longer every day. Sifting around these lengthy EHRs is taxing and be- comes a cumbersome part of physician-patient interaction. Several approaches have been pro- posed to help alleviate this prevalent issue ei- ther via summarization or sectioning, however, only a few approaches have truly been helpful in the past. With the rise of automated methods, machine learning (ML) has shown promise in solving the task of identifying relevant sections in EHR. However, most ML methods rely on labeled data which is difficult to get in health- care. Large language models (LLMs) on the other hand, have performed impressive feats in natural language processing (NLP), that too in a zero-shot manner, i.e. without any labeled data. To that end, we propose using LLMs to identify relevant section headers. We find that GPT-4 can effectively solve the task on both zero and few-shot settings as well as segment dramatically better than state-of-the-art meth- ods. Additionally, we also annotate a much harder real world dataset and find that GPT-4 struggles to perform well, alluding to further research and harder benchmarks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="krishnamoorthy-etal-2024-llm">
<titleInfo>
<title>LLM-Based Section Identifiers Excel on Open Source but Stumble in Real World Applications</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saranya</namePart>
<namePart type="family">Krishnamoorthy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayush</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shabnam</namePart>
<namePart type="family">Tafreshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 6th Clinical Natural Language Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tristan</namePart>
<namePart type="family">Naumann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asma</namePart>
<namePart type="family">Ben Abacha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kirk</namePart>
<namePart type="family">Roberts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danielle</namePart>
<namePart type="family">Bitterman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Electronic health records (EHR) even though a boon for healthcare practitioners, are grow- ing convoluted and longer every day. Sifting around these lengthy EHRs is taxing and be- comes a cumbersome part of physician-patient interaction. Several approaches have been pro- posed to help alleviate this prevalent issue ei- ther via summarization or sectioning, however, only a few approaches have truly been helpful in the past. With the rise of automated methods, machine learning (ML) has shown promise in solving the task of identifying relevant sections in EHR. However, most ML methods rely on labeled data which is difficult to get in health- care. Large language models (LLMs) on the other hand, have performed impressive feats in natural language processing (NLP), that too in a zero-shot manner, i.e. without any labeled data. To that end, we propose using LLMs to identify relevant section headers. We find that GPT-4 can effectively solve the task on both zero and few-shot settings as well as segment dramatically better than state-of-the-art meth- ods. Additionally, we also annotate a much harder real world dataset and find that GPT-4 struggles to perform well, alluding to further research and harder benchmarks.</abstract>
<identifier type="citekey">krishnamoorthy-etal-2024-llm</identifier>
<identifier type="doi">10.18653/v1/2024.clinicalnlp-1.22</identifier>
<location>
<url>https://aclanthology.org/2024.clinicalnlp-1.22</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>258</start>
<end>270</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LLM-Based Section Identifiers Excel on Open Source but Stumble in Real World Applications
%A Krishnamoorthy, Saranya
%A Singh, Ayush
%A Tafreshi, Shabnam
%Y Naumann, Tristan
%Y Ben Abacha, Asma
%Y Bethard, Steven
%Y Roberts, Kirk
%Y Bitterman, Danielle
%S Proceedings of the 6th Clinical Natural Language Processing Workshop
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F krishnamoorthy-etal-2024-llm
%X Electronic health records (EHR) even though a boon for healthcare practitioners, are grow- ing convoluted and longer every day. Sifting around these lengthy EHRs is taxing and be- comes a cumbersome part of physician-patient interaction. Several approaches have been pro- posed to help alleviate this prevalent issue ei- ther via summarization or sectioning, however, only a few approaches have truly been helpful in the past. With the rise of automated methods, machine learning (ML) has shown promise in solving the task of identifying relevant sections in EHR. However, most ML methods rely on labeled data which is difficult to get in health- care. Large language models (LLMs) on the other hand, have performed impressive feats in natural language processing (NLP), that too in a zero-shot manner, i.e. without any labeled data. To that end, we propose using LLMs to identify relevant section headers. We find that GPT-4 can effectively solve the task on both zero and few-shot settings as well as segment dramatically better than state-of-the-art meth- ods. Additionally, we also annotate a much harder real world dataset and find that GPT-4 struggles to perform well, alluding to further research and harder benchmarks.
%R 10.18653/v1/2024.clinicalnlp-1.22
%U https://aclanthology.org/2024.clinicalnlp-1.22
%U https://doi.org/10.18653/v1/2024.clinicalnlp-1.22
%P 258-270
Markdown (Informal)
[LLM-Based Section Identifiers Excel on Open Source but Stumble in Real World Applications](https://aclanthology.org/2024.clinicalnlp-1.22) (Krishnamoorthy et al., ClinicalNLP-WS 2024)
ACL