Adverse drug event presentation and tracking (ADEPT): semiautomated high throughput pharmacovigilance using real-world data

摘要

To advance use of real-world data (RWD) for pharmacovigilance, we sought to integrate a high-sensitivity natural language processing (NLP) pipeline for detecting potential adverse drug events (ADEs) with easily interpretable output for high-efficiency human review and adjudication of true ADEs.