The Importance of Information Extraction from Unstructured Clinical Data in Pharmacoepidemiology

Electronic health records (EHRs) and claims are important sources of real-world data used to generate real-world evidence on the safety and effectiveness of therapies. Valuable information is contained in the unstructured clinical notes and methods such as Natural Language Processing (NLP) are needed to extract the information into a structured format for analysis.

This poster examined the impact on outcome identification of using unstructured EHRs in a drug safety study examining neuropsychiatric events. It was presented at the 2025 PHUSE Computational Science Symposium (CSS).