Retrofitting Vector Representations of Adverse Event Reporting Data to Structured Knowledge to Improve Pharmacovigilance Signal Detection

TL;DR

This paper enhances vector representations of adverse event reports by retrofitting them with structured knowledge from RxNorm, significantly improving pharmacovigilance signal detection over traditional methods.

Contribution

It introduces a novel retrofitting approach that incorporates lexical knowledge into vector embeddings, boosting signal detection accuracy in pharmacovigilance.

Findings

Retrofitted embeddings outperform disproportionality metrics.

Rescaling during retrofitting further improves detection performance.

Method is effective on minimally preprocessed data.

Abstract

Adverse drug events (ADE) are prevalent and costly. Clinical trials are constrained in their ability to identify potential ADEs, motivating the development of spontaneous reporting systems for post-market surveillance. Statistical methods provide a convenient way to detect signals from these reports but have limitations in leveraging relationships between drugs and ADEs given their discrete count-based nature. A previously proposed method, aer2vec, generates distributed vector representations of ADE report entities that capture patterns of similarity but cannot utilize lexical knowledge. We address this limitation by retrofitting aer2vec drug embeddings to knowledge from RxNorm and developing a novel retrofitting variant using vector rescaling to preserve magnitude. When evaluated in the context of a pharmacovigilance signal detection task, aer2vec with retrofitting consistently outperforms disproportionality metrics when trained on minimally preprocessed data. Retrofitting with rescaling results in further improvements in the larger and more challenging of two pharmacovigilance reference sets used for evaluation.