Unexpected Issues in Pharmacoepidemiology Studies Applying Natural Language Processing to Clinical Notes

This presentation uses the Sentinel Innovation Center's MOSAIC-NLP (Multi-source Observational Safety study for Advanced Information Classification using NLP) project as a case study to describe strategies to address unexpected methodological challenges and discuss how to advance the use of natural language processing (NLP) of clinical notes to support population-based pharmacoepidemiology studies. It was presented at the 2023 DIA Real-World Evidence Conference.