English

Clinical Trial Information Extraction with BERT

Quantitative Methods 2021-10-20 v1 Computation and Language Machine Learning

Abstract

Natural language processing (NLP) of clinical trial documents can be useful in new trial design. Here we identify entity types relevant to clinical trial design and propose a framework called CT-BERT for information extraction from clinical trial text. We trained named entity recognition (NER) models to extract eligibility criteria entities by fine-tuning a set of pre-trained BERT models. We then compared the performance of CT-BERT with recent baseline methods including attention-based BiLSTM and Criteria2Query. The results demonstrate the superiority of CT-BERT in clinical trial NLP.

Cite

@article{arxiv.2110.10027,
  title  = {Clinical Trial Information Extraction with BERT},
  author = {Xiong Liu and Greg L. Hersch and Iya Khalil and Murthy Devarakonda},
  journal= {arXiv preprint arXiv:2110.10027},
  year   = {2021}
}

Comments

HealthNLP 2021, IEEE International Conference on Healthcare Informatics (ICHI 2021)

R2 v1 2026-06-24T07:00:52.062Z