Modeling Drug-Disease Relations with Linguistic and Knowledge Graph Constraints

TL;DR

This paper enhances drug-disease relation modeling by integrating structured knowledge graphs and clinical narratives with probabilistic logic, outperforming text-only methods and providing a new annotated dataset.

Contribution

It introduces a novel approach combining knowledge graphs and clinical narratives with probabilistic soft logic for improved drug-disease relation extraction.

Findings

Probabilistic Soft Logic models outperform text-only variants.

Clinical narratives graph yields high accuracy with minimal manual effort.

New dataset of drug labels with five drug-disease relation annotations.

Abstract

FDA drug labels are rich sources of information about drugs and drug-disease relations, but their complexity makes them challenging texts to analyze in isolation. To overcome this, we situate these labels in two health knowledge graphs: one built from precise structured information about drugs and diseases, and another built entirely from a database of clinical narrative texts using simple heuristic methods. We show that Probabilistic Soft Logic models defined over these graphs are superior to text-only and relation-only variants, and that the clinical narratives graph delivers exceptional results with little manual effort. Finally, we release a new dataset of drug labels with annotations for five distinct drug-disease relations.