Disease Normalization with Graph Embeddings

TL;DR

This paper introduces deep learning methods that utilize graph embeddings of MeSH to improve disease recognition and normalization in biomedical texts, demonstrating enhanced performance on the NCBI benchmark corpus.

Contribution

It presents a novel approach combining graph embeddings with neural models for disease recognition and normalization, leveraging MeSH's structure for improved accuracy.

Findings

Graph embeddings improve disease normalization accuracy.

Multitask learning enhances disease recognition performance.

Method achieves state-of-the-art results on NCBI corpus.

Abstract

The detection and normalization of diseases in biomedical texts are key biomedical natural language processing tasks. Disease names need not only be identified, but also normalized or linked to clinical taxonomies describing diseases such as MeSH. In this paper we describe deep learning methods that tackle both tasks. We train and test our methods on the known NCBI disease benchmark corpus. We propose to represent disease names by leveraging MeSH's graphical structure together with the lexical information available in the taxonomy using graph embeddings. We also show that combining neural named entity recognition models with our graph-based entity linking methods via multitask learning leads to improved disease recognition in the NCBI corpus.