Bidirectional LSTM-CRF for Clinical Concept Extraction
Published in
(2016)External Links:
TL
TL;DR
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 that outperform all recent methods and ranks closely to the best submission from the original 2010 i2b2/VA challenge.
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.
References29 items
1
MIMIC-III, a freely accessible critical care database
2
Neural Architectures for Named Entity Recognition
3
Drug Name Recognition: Approaches and Resources
4
A Study of Neural Word Embeddings for Named Entity Recognition in Clinical Text
5