@inproceedings{wang-sun-2022-trial2vec,
title = "{T}rial2{V}ec: Zero-Shot Clinical Trial Document Similarity Search using Self-Supervision",
author = "Wang, Zifeng and
Sun, Jimeng",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.476",
doi = "10.18653/v1/2022.findings-emnlp.476",
pages = "6377--6390",
abstract = "Clinical trials are essential for drug development but are extremely expensive and time-consuming to conduct. It is beneficial to study similar historical trials when designing a clinical trial. However, lengthy trial documents and lack of labeled data make trial similarity search difficult. We propose a zero-shotclinical trial retrieval method, called Trial2Vec, which learns through self-supervision without the need for annotating similar clinical trials. Specifically, the meta-structure of trial documents (e.g., title, eligibility criteria, target disease) along with clinical knowledge (e.g., UMLS knowledge base) are leveraged to automatically generate contrastive samples. Besides, encodes trial documents considering meta-structure thus producing compact embeddings aggregating multi-aspect information from the whole document. We show that our method yields medically interpretable embeddings by visualization and it gets 15{\%} average improvement over the best baselines on precision/recall for trial retrieval, which is evaluated on our labeled 1600 trial pairs. In addition, we prove the pretrained embeddings benefit the downstream trial outcome prediction task over 240k trials. Software is available at https://github.com/RyanWangZf/Trial2Vec.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-sun-2022-trial2vec">
<titleInfo>
<title>Trial2Vec: Zero-Shot Clinical Trial Document Similarity Search using Self-Supervision</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zifeng</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jimeng</namePart>
<namePart type="family">Sun</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>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</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</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Clinical trials are essential for drug development but are extremely expensive and time-consuming to conduct. It is beneficial to study similar historical trials when designing a clinical trial. However, lengthy trial documents and lack of labeled data make trial similarity search difficult. We propose a zero-shotclinical trial retrieval method, called Trial2Vec, which learns through self-supervision without the need for annotating similar clinical trials. Specifically, the meta-structure of trial documents (e.g., title, eligibility criteria, target disease) along with clinical knowledge (e.g., UMLS knowledge base) are leveraged to automatically generate contrastive samples. Besides, encodes trial documents considering meta-structure thus producing compact embeddings aggregating multi-aspect information from the whole document. We show that our method yields medically interpretable embeddings by visualization and it gets 15% average improvement over the best baselines on precision/recall for trial retrieval, which is evaluated on our labeled 1600 trial pairs. In addition, we prove the pretrained embeddings benefit the downstream trial outcome prediction task over 240k trials. Software is available at https://github.com/RyanWangZf/Trial2Vec.</abstract>
<identifier type="citekey">wang-sun-2022-trial2vec</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.476</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.476</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>6377</start>
<end>6390</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Trial2Vec: Zero-Shot Clinical Trial Document Similarity Search using Self-Supervision
%A Wang, Zifeng
%A Sun, Jimeng
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F wang-sun-2022-trial2vec
%X Clinical trials are essential for drug development but are extremely expensive and time-consuming to conduct. It is beneficial to study similar historical trials when designing a clinical trial. However, lengthy trial documents and lack of labeled data make trial similarity search difficult. We propose a zero-shotclinical trial retrieval method, called Trial2Vec, which learns through self-supervision without the need for annotating similar clinical trials. Specifically, the meta-structure of trial documents (e.g., title, eligibility criteria, target disease) along with clinical knowledge (e.g., UMLS knowledge base) are leveraged to automatically generate contrastive samples. Besides, encodes trial documents considering meta-structure thus producing compact embeddings aggregating multi-aspect information from the whole document. We show that our method yields medically interpretable embeddings by visualization and it gets 15% average improvement over the best baselines on precision/recall for trial retrieval, which is evaluated on our labeled 1600 trial pairs. In addition, we prove the pretrained embeddings benefit the downstream trial outcome prediction task over 240k trials. Software is available at https://github.com/RyanWangZf/Trial2Vec.
%R 10.18653/v1/2022.findings-emnlp.476
%U https://aclanthology.org/2022.findings-emnlp.476
%U https://doi.org/10.18653/v1/2022.findings-emnlp.476
%P 6377-6390
Markdown (Informal)
[Trial2Vec: Zero-Shot Clinical Trial Document Similarity Search using Self-Supervision](https://aclanthology.org/2022.findings-emnlp.476) (Wang & Sun, Findings 2022)
ACL