Bidirectional LSTM-CRF for Clinical Concept Extraction

Abstract

Automated extraction of concepts from patient clinical records is an essential facilitator of clinical research. For this reason, the 2010 i2b2/VA Natural Language Processing Challenges for Clinical Records introduced a concept extraction task aimed at identifying and classifying concepts into predefined categories (i.e., treatments, tests and problems). State-of-the-art concept extraction approaches heavily rely on handcrafted features and domain-specific resources which are hard to collect and define. For this reason, this paper proposes an alternative, streamlined approach: a recurrent neural network (the bidirectional LSTM with CRF decoding) initialized with general-purpose, off-the-shelf word embeddings. The experimental results achieved on the 2010 i2b2/VA reference corpora using the proposed framework outperform all recent methods and ranks closely to the best submission from the original 2010 i2b2/VA challenge.

This paper "Bidirectional LSTM-CRF for Clinical Concept Extraction" is accepted for short paper presentation at Clinical Natural Language Processing Workshop at COLING 2016 Osaka, Japan. December 11, 2016

References in corpus (2)

• Distributed Representations of Words and Phrases and their Compositionality
• Natural Language Processing (almost) from Scratch

Cited by in corpus (4)

• Recurrent neural networks with specialized word embeddings for health-domain named-entity recognition
• SECNLP: A Survey of Embeddings in Clinical Natural Language Processing
• Joint Entity Extraction and Assertion Detection for Clinical Text
• Extracting UMLS Concepts from Medical Text Using General and Domain-Specific Deep Learning Models