Sequence Learning with RNNs for Medical Concept Normalization in User-Generated Texts

Abstract

In this work, we consider the medical concept normalization problem, i.e., the problem of mapping a disease mention in free-form text to a concept in a controlled vocabulary, usually to the standard thesaurus in the Unified Medical Language System (UMLS). This task is challenging since medical terminology is very different when coming from health care professionals or from the general public in the form of social media texts. We approach it as a sequence learning problem, with recurrent neural networks trained to obtain semantic representations of one- and multi-word expressions. We develop end-to-end neural architectures tailored specifically to medical concept normalization, including bidirectional LSTM and GRU with an attention mechanism and additional semantic similarity features based on UMLS. Our evaluation over a standard benchmark shows that our model improves over a state of the art baseline for classification based on CNNs.

Machine Learning for Health (ML4H) Workshop at NeurIPS 2018 arXiv:1811.07216

References in corpus (2)

• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Convolutional Neural Networks for Sentence Classification

Cited by in corpus (4)

• SECNLP: A Survey of Embeddings in Clinical Natural Language Processing
• Improving Broad-Coverage Medical Entity Linking with Semantic Type Prediction and Large-Scale Datasets
• RadLex Normalization in Radiology Reports
• An Automated Method to Enrich Consumer Health Vocabularies Using GloVe Word Embeddings and An Auxiliary Lexical Resource