Bidirectional LSTM-CRF for Clinical Concept Extraction

TL;DR

This paper introduces a bidirectional LSTM-CRF model utilizing general-purpose word embeddings for clinical concept extraction, outperforming previous methods and reducing reliance on handcrafted features.

Contribution

It presents a streamlined neural network approach for clinical concept extraction that outperforms existing methods and minimizes domain-specific resource requirements.

Findings

Outperforms recent methods on i2b2/VA datasets

Ranks close to the best challenge submission

Reduces need for handcrafted features

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.