Modelling Radiological Language with Bidirectional Long Short-Term Memory Networks

TL;DR

This paper introduces a BiLSTM neural network approach for extracting medical information from radiological reports, specifically focusing on named-entity recognition and negation detection, demonstrating advantages over traditional rule-based systems.

Contribution

The paper presents a novel BiLSTM-based model for radiological language modeling, improving NLP tasks in medical report analysis compared to rule-based methods.

Findings

BiLSTM outperforms dictionary-based NER systems.

BiLSTM achieves better negation detection than NegEx.

Learning multiple word embeddings enhances model performance.

Abstract

Motivated by the need to automate medical information extraction from free-text radiological reports, we present a bi-directional long short-term memory (BiLSTM) neural network architecture for modelling radiological language. The model has been used to address two NLP tasks: medical named-entity recognition (NER) and negation detection. We investigate whether learning several types of word embeddings improves BiLSTM's performance on those tasks. Using a large dataset of chest x-ray reports, we compare the proposed model to a baseline dictionary-based NER system and a negation detection system that leverages the hand-crafted rules of the NegEx algorithm and the grammatical relations obtained from the Stanford Dependency Parser. Compared to these more traditional rule-based systems, we argue that BiLSTM offers a strong alternative for both our tasks.