Retrofitting Vector Representations of Adverse Event Reporting Data to Structured Knowledge to Improve Pharmacovigilance Signal Detection
This work addresses the limitation of statistical methods in leveraging drug-ADE relationships for pharmacovigilance, offering incremental improvements in signal detection for post-market drug safety monitoring.
The paper tackled the problem of improving pharmacovigilance signal detection by retrofitting vector representations of adverse event reporting data to structured knowledge, resulting in consistent outperformance over disproportionality metrics and further improvements with a novel rescaling variant in challenging datasets.
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.