@inproceedings{hazan-etal-2024-leveraging,
title = "Leveraging Prompt-Learning for Structured Information Extraction from Crohn{'}s Disease Radiology Reports in a Low-Resource Language",
author = "Hazan, Liam and
Gavrielov, Naama and
Reichart, Roi and
Hagopian, Talar and
Greer, Mary-Louise and
Cytter-Kuint, Ruth and
Focht, Gili and
Turner, Dan and
Freiman, Moti",
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-1.26",
doi = "10.18653/v1/2024.clinicalnlp-1.26",
pages = "301--309",
abstract = "Automatic conversion of free-text radiology reports into structured data using Natural Language Processing (NLP) techniques is crucial for analyzing diseases on a large scale. While effective for tasks in widely spoken languages like English, generative large language models (LLMs) typically underperform with less common languages and can pose potential risks to patient privacy. Fine-tuning local NLP models is hindered by the skewed nature of real-world medical datasets, where rare findings represent a significant data imbalance. We introduce SMP-BERT, a novel prompt learning method that leverages the structured nature of reports to overcome these challenges. In our studies involving a substantial collection of Crohn{'}s disease radiology reports in Hebrew (over 8,000 patients and 10,000 reports), SMP-BERT greatly surpassed traditional fine-tuning methods in performance, notably in detecting infrequent conditions (AUC: 0.99 vs 0.94, F1: 0.84 vs 0.34). SMP-BERT empowers more accurate AI diagnostics available for low-resource languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hazan-etal-2024-leveraging">
<titleInfo>
<title>Leveraging Prompt-Learning for Structured Information Extraction from Crohn’s Disease Radiology Reports in a Low-Resource Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Liam</namePart>
<namePart type="family">Hazan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naama</namePart>
<namePart type="family">Gavrielov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roi</namePart>
<namePart type="family">Reichart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Talar</namePart>
<namePart type="family">Hagopian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mary-Louise</namePart>
<namePart type="family">Greer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruth</namePart>
<namePart type="family">Cytter-Kuint</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gili</namePart>
<namePart type="family">Focht</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Turner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Moti</namePart>
<namePart type="family">Freiman</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>Automatic conversion of free-text radiology reports into structured data using Natural Language Processing (NLP) techniques is crucial for analyzing diseases on a large scale. While effective for tasks in widely spoken languages like English, generative large language models (LLMs) typically underperform with less common languages and can pose potential risks to patient privacy. Fine-tuning local NLP models is hindered by the skewed nature of real-world medical datasets, where rare findings represent a significant data imbalance. We introduce SMP-BERT, a novel prompt learning method that leverages the structured nature of reports to overcome these challenges. In our studies involving a substantial collection of Crohn’s disease radiology reports in Hebrew (over 8,000 patients and 10,000 reports), SMP-BERT greatly surpassed traditional fine-tuning methods in performance, notably in detecting infrequent conditions (AUC: 0.99 vs 0.94, F1: 0.84 vs 0.34). SMP-BERT empowers more accurate AI diagnostics available for low-resource languages.</abstract>
<identifier type="citekey">hazan-etal-2024-leveraging</identifier>
<identifier type="doi">10.18653/v1/2024.clinicalnlp-1.26</identifier>
<location>
<url>https://aclanthology.org/2024.clinicalnlp-1.26</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>301</start>
<end>309</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Leveraging Prompt-Learning for Structured Information Extraction from Crohn’s Disease Radiology Reports in a Low-Resource Language
%A Hazan, Liam
%A Gavrielov, Naama
%A Reichart, Roi
%A Hagopian, Talar
%A Greer, Mary-Louise
%A Cytter-Kuint, Ruth
%A Focht, Gili
%A Turner, Dan
%A Freiman, Moti
%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 hazan-etal-2024-leveraging
%X Automatic conversion of free-text radiology reports into structured data using Natural Language Processing (NLP) techniques is crucial for analyzing diseases on a large scale. While effective for tasks in widely spoken languages like English, generative large language models (LLMs) typically underperform with less common languages and can pose potential risks to patient privacy. Fine-tuning local NLP models is hindered by the skewed nature of real-world medical datasets, where rare findings represent a significant data imbalance. We introduce SMP-BERT, a novel prompt learning method that leverages the structured nature of reports to overcome these challenges. In our studies involving a substantial collection of Crohn’s disease radiology reports in Hebrew (over 8,000 patients and 10,000 reports), SMP-BERT greatly surpassed traditional fine-tuning methods in performance, notably in detecting infrequent conditions (AUC: 0.99 vs 0.94, F1: 0.84 vs 0.34). SMP-BERT empowers more accurate AI diagnostics available for low-resource languages.
%R 10.18653/v1/2024.clinicalnlp-1.26
%U https://aclanthology.org/2024.clinicalnlp-1.26
%U https://doi.org/10.18653/v1/2024.clinicalnlp-1.26
%P 301-309
Markdown (Informal)
[Leveraging Prompt-Learning for Structured Information Extraction from Crohn’s Disease Radiology Reports in a Low-Resource Language](https://aclanthology.org/2024.clinicalnlp-1.26) (Hazan et al., ClinicalNLP-WS 2024)
ACL
- Liam Hazan, Naama Gavrielov, Roi Reichart, Talar Hagopian, Mary-Louise Greer, Ruth Cytter-Kuint, Gili Focht, Dan Turner, and Moti Freiman. 2024. Leveraging Prompt-Learning for Structured Information Extraction from Crohn’s Disease Radiology Reports in a Low-Resource Language. In Proceedings of the 6th Clinical Natural Language Processing Workshop, pages 301–309, Mexico City, Mexico. Association for Computational Linguistics.