Attention-Gated Graph Convolutions for Extracting Drug Interaction Information from Drug Labels

TL;DR

This paper introduces a novel attention-gated graph convolutional neural network for extracting drug-drug interactions from labels, leveraging transfer learning to improve performance on limited data, achieving state-of-the-art results.

Contribution

It proposes a new attention-based gating mechanism in graph convolutions and combines it with transfer learning for improved DDI extraction from drug labels.

Findings

Achieved up to 6 F1 point improvement over previous best results.

State-of-the-art performance on the 2018 TAC DDI corpus.

Effective joint extraction of drugs and interactions with novel GCA model.

Abstract

Preventable adverse events as a result of medical errors present a growing concern in the healthcare system. As drug-drug interactions (DDIs) may lead to preventable adverse events, being able to extract DDIs from drug labels into a machine-processable form is an important step toward effective dissemination of drug safety information. In this study, we tackle the problem of jointly extracting drugs and their interactions, including interaction outcome, from drug labels. Our deep learning approach entails composing various intermediate representations including sequence and graph based context, where the latter is derived using graph convolutions (GC) with a novel attention-based gating mechanism (holistically called GCA). These representations are then composed in meaningful ways to handle all subtasks jointly. To overcome scarcity in training data, we additionally propose transfer learning by pre-training on related DDI data. Our model is trained and evaluated on the 2018 TAC DDI corpus. Our GCA model in conjunction with transfer learning performs at 39.20% F1 and 26.09% F1 on entity recognition (ER) and relation extraction (RE) respectively on the first official test set and at 45.30% F1 and 27.87% F1 on ER and RE respectively on the second official test set corresponding to an improvement over our prior best results by up to 6 absolute F1 points. After controlling for available training data, our model exhibits state-of-the-art performance by improving over the next comparable best outcome by roughly three F1 points in ER and 1.5 F1 points in RE evaluation across two official test sets.