@inproceedings{yang-2024-exploring-generalization,
title = "Exploring the Generalization of Cancer Clinical Trial Eligibility Classifiers across Diseases",
author = "Yang, Yumeng",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.609",
pages = "6955--6965",
abstract = "Clinical trials are pivotal in medical research, and NLP can enhance their success, with application in recruitment. This study aims to evaluate the generalizability of eligibility classification across a broad spectrum of clinical trials. Starting with phase 3 cancer trials, annotated with seven eligibility exclusions, then to determine how well models can generalize to non-cancer and non-phase 3 trials. To assess this, we have compiled eligibility criteria data for five types of trials: (1) additional phase 3 cancer trials, (2) phase 1 and 2 cancer trials, (3) heart disease trials, (4) type 2 diabetes trials, and (5) observational trials for any disease, comprising 2,490 annotated eligibility criteria across seven exclusion types. Our results show that models trained on the extensive cancer dataset can effectively handle criteria commonly found in non-cancer trials, such as autoimmune diseases. However, they struggle with criteria disproportionately prevalent in cancer trials, like prior malignancy. We also experiment with few-shot learning, demonstrating that a limited number of disease-specific examples can partially overcome this performance gap. We are releasing this new dataset of annotated eligibility statements to promote the development of cross-disease generalization in clinical trial classification.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-2024-exploring-generalization">
<titleInfo>
<title>Exploring the Generalization of Cancer Clinical Trial Eligibility Classifiers across Diseases</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yumeng</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</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">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</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>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Clinical trials are pivotal in medical research, and NLP can enhance their success, with application in recruitment. This study aims to evaluate the generalizability of eligibility classification across a broad spectrum of clinical trials. Starting with phase 3 cancer trials, annotated with seven eligibility exclusions, then to determine how well models can generalize to non-cancer and non-phase 3 trials. To assess this, we have compiled eligibility criteria data for five types of trials: (1) additional phase 3 cancer trials, (2) phase 1 and 2 cancer trials, (3) heart disease trials, (4) type 2 diabetes trials, and (5) observational trials for any disease, comprising 2,490 annotated eligibility criteria across seven exclusion types. Our results show that models trained on the extensive cancer dataset can effectively handle criteria commonly found in non-cancer trials, such as autoimmune diseases. However, they struggle with criteria disproportionately prevalent in cancer trials, like prior malignancy. We also experiment with few-shot learning, demonstrating that a limited number of disease-specific examples can partially overcome this performance gap. We are releasing this new dataset of annotated eligibility statements to promote the development of cross-disease generalization in clinical trial classification.</abstract>
<identifier type="citekey">yang-2024-exploring-generalization</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.609</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>6955</start>
<end>6965</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring the Generalization of Cancer Clinical Trial Eligibility Classifiers across Diseases
%A Yang, Yumeng
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F yang-2024-exploring-generalization
%X Clinical trials are pivotal in medical research, and NLP can enhance their success, with application in recruitment. This study aims to evaluate the generalizability of eligibility classification across a broad spectrum of clinical trials. Starting with phase 3 cancer trials, annotated with seven eligibility exclusions, then to determine how well models can generalize to non-cancer and non-phase 3 trials. To assess this, we have compiled eligibility criteria data for five types of trials: (1) additional phase 3 cancer trials, (2) phase 1 and 2 cancer trials, (3) heart disease trials, (4) type 2 diabetes trials, and (5) observational trials for any disease, comprising 2,490 annotated eligibility criteria across seven exclusion types. Our results show that models trained on the extensive cancer dataset can effectively handle criteria commonly found in non-cancer trials, such as autoimmune diseases. However, they struggle with criteria disproportionately prevalent in cancer trials, like prior malignancy. We also experiment with few-shot learning, demonstrating that a limited number of disease-specific examples can partially overcome this performance gap. We are releasing this new dataset of annotated eligibility statements to promote the development of cross-disease generalization in clinical trial classification.
%U https://aclanthology.org/2024.lrec-main.609
%P 6955-6965
Markdown (Informal)
[Exploring the Generalization of Cancer Clinical Trial Eligibility Classifiers across Diseases](https://aclanthology.org/2024.lrec-main.609) (Yang, LREC-COLING 2024)
ACL