Medical Entity Linking using Triplet Network

TL;DR

This paper introduces a novel disease entity linking method using a Triplet Network that improves candidate ranking accuracy without relying on handcrafted rules, demonstrating superior performance on standard benchmarks.

Contribution

The paper proposes a robust, portable candidate generation scheme and applies a Triplet Network for disease normalization, outperforming prior methods on benchmark datasets.

Findings

Outperforms previous methods on NCBI disease dataset

Uses a Triplet Network for improved candidate ranking

Eliminates need for handcrafted rules in candidate generation

Abstract

Entity linking (or Normalization) is an essential task in text mining that maps the entity mentions in the medical text to standard entities in a given Knowledge Base (KB). This task is of great importance in the medical domain. It can also be used for merging different medical and clinical ontologies. In this paper, we center around the problem of disease linking or normalization. This task is executed in two phases: candidate generation and candidate scoring. In this paper, we present an approach to rank the candidate Knowledge Base entries based on their similarity with disease mention. We make use of the Triplet Network for candidate ranking. While the existing methods have used carefully generated sieves and external resources for candidate generation, we introduce a robust and portable candidate generation scheme that does not make use of the hand-crafted rules. Experimental results on the standard benchmark NCBI disease dataset demonstrate that our system outperforms the prior methods by a significant margin.