Bidirectional LSTM-CRF for Clinical Concept Extraction
This addresses the problem of automating concept extraction for clinical research, reducing reliance on handcrafted features, but it is incremental as it builds on existing LSTM-CRF methods.
The paper tackled clinical concept extraction from patient records by using a bidirectional LSTM-CRF model with general word embeddings, achieving results close to top-ranked systems on the 2010 i2b2/VA dataset.
Extraction of concepts present in patient clinical records is an essential step in clinical research. The 2010 i2b2/VA Workshop on Natural Language Processing Challenges for clinical records presented concept extraction (CE) task, with aim to identify concepts (such as treatments, tests, problems) and classify them into predefined categories. State-of-the-art CE approaches heavily rely on hand crafted features and domain specific resources which are hard to collect and tune. For this reason, this paper employs bidirectional LSTM with CRF decoding initialized with general purpose off-the-shelf word embeddings for CE. The experimental results achieved on 2010 i2b2/VA reference standard corpora using bidirectional LSTM CRF ranks closely with top ranked systems.