Trial2Vec: Zero-Shot Clinical Trial Document Similarity Search using Self-SupervisionDownload PDF

Anonymous

17 Apr 2022 (modified: 05 May 2023)ACL ARR 2022 April Blind SubmissionReaders: Everyone
Keywords: documeng similarity search, document representation learning, contrastive learning, clinical trials
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-shot clinical trial retrieval method, called Trial2Vec, which learns through self-supervision without the need for annotating similar clinical trials. Specifically, the \textit{meta-structure} of trial documents (e.g., title, eligibility criteria, target disease) along with clinical knowledge (e.g., UMLS knowledge base \footnote{\url{https://www.nlm.nih.gov/research/umls/index.html}}) are leveraged to automatically generate contrastive samples. Besides, Trial2Vec 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.
Paper Type: long
0 Replies

Loading