English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Preventable adverse events as a result of medical errors present a growingconcern in the healthcare system. As drug-drug interactions (DDIs) may lead topreventable adverse events, being able to extract DDIs from drug labels into amachine-processable form is an important step toward effective dissemination ofdrug safety information. In this study, we tackle the problem of jointlyextracting drugs and their interactions, including interaction outcome, fromdrug labels. Our deep learning approach entails composing various intermediaterepresentations including sequence and graph based context, where the latter isderived using graph convolutions (GC) with a novel attention-based gatingmechanism (holistically called GCA). These representations are then composed inmeaningful ways to handle all subtasks jointly. To overcome scarcity intraining data, we additionally propose transfer learning by pre-training onrelated DDI data. Our model is trained and evaluated on the 2018 TAC DDIcorpus. 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 onER and RE respectively on the second official test set corresponding to animprovement over our prior best results by up to 6 absolute F1 points. Aftercontrolling for available training data, our model exhibits state-of-the-artperformance by improving over the next comparable best outcome by roughly threeF1 points in ER and 1.5 F1 points in RE evaluation across two official testsets.

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