Multimodal Learning on Graphs for Disease Relation Extraction

TL;DR

This paper introduces REMAP, a multimodal neural approach that combines disease knowledge graphs and medical text data to improve disease relation extraction and classification, enabling better AI-driven disease understanding.

Contribution

REMAP is a novel method that jointly embeds incomplete knowledge graphs and text data into a unified space for enhanced disease relation extraction.

Findings

REMAP improves relation extraction accuracy by 10% and F1-score by 17.2%.

REMAP outperforms graph-only methods by 8.4% in accuracy.

The approach effectively recommends new disease relationships from text and graph data.

Abstract

Objective: Disease knowledge graphs are a way to connect, organize, and access disparate information about diseases with numerous benefits for artificial intelligence (AI). To create knowledge graphs, it is necessary to extract knowledge from multimodal datasets in the form of relationships between disease concepts and normalize both concepts and relationship types. Methods: We introduce REMAP, a multimodal approach for disease relation extraction and classification. The REMAP machine learning approach jointly embeds a partial, incomplete knowledge graph and a medical language dataset into a compact latent vector space, followed by aligning the multimodal embeddings for optimal disease relation extraction. Results: We apply REMAP approach to a disease knowledge graph with 96,913 relations and a text dataset of 1.24 million sentences. On a dataset annotated by human experts, REMAP improves text-based disease relation extraction by 10.0% (accuracy) and 17.2% (F1-score) by fusing disease knowledge graphs with text information. Further, REMAP leverages text information to recommend new relationships in the knowledge graph, outperforming graph-based methods by 8.4% (accuracy) and 10.4% (F1-score). Conclusion: REMAP is a multimodal approach for extracting and classifying disease relationships by fusing structured knowledge and text information. REMAP provides a flexible neural architecture to easily find, access, and validate AI-driven relationships between disease concepts.