Relation extraction from clinical texts using domain invariant convolutional neural network

TL;DR

This paper proposes a CNN-based model for extracting semantic relations from clinical texts, reducing reliance on manual feature engineering and demonstrating effective performance on a clinical relation dataset.

Contribution

The study introduces a domain-invariant CNN approach for relation extraction in clinical texts, eliminating the need for manual feature engineering.

Findings

CNN outperforms traditional feature-based models

Effective relation extraction on i2b2-2010 dataset

Reduces dependency on expert-designed features

Abstract

In recent years extracting relevant information from biomedical and clinical texts such as research articles, discharge summaries, or electronic health records have been a subject of many research efforts and shared challenges. Relation extraction is the process of detecting and classifying the semantic relation among entities in a given piece of texts. Existing models for this task in biomedical domain use either manually engineered features or kernel methods to create feature vector. These features are then fed to classifier for the prediction of the correct class. It turns out that the results of these methods are highly dependent on quality of user designed features and also suffer from curse of dimensionality. In this work we focus on extracting relations from clinical discharge summaries. Our main objective is to exploit the power of convolution neural network (CNN) to learn features automatically and thus reduce the dependency on manual feature engineering. We evaluate performance of the proposed model on i2b2-2010 clinical relation extraction challenge dataset. Our results indicate that convolution neural network can be a good model for relation exaction in clinical text without being dependent on expert's knowledge on defining quality features.