Concept Negation in Free Text Components of Vaccine Safety Reports

摘要

Large amounts of information are locked up in free text components of clinical reports. Surveillance systems that monitor adverse events following immunizations (AEFI) can utilize these components after concept extraction using natural language processing (NLP). Specifically, our method for the identification and filtering of negated concepts using the Unified Medical Language System (UMLS) potentially improves the quality of AEFI surveillance systems.