Large Language Models for World Health Organization–Uppsala Monitoring Centre Drug–Adverse Event Causality Assessment Using Food and Drug Administration Adverse Event Reporting System Cases: Comparative Performance Study - Takeaways - MDSpire

Large Language Models for World Health Organization–Uppsala Monitoring Centre Drug–Adverse Event Causality Assessment Using Food and Drug Administration Adverse Event Reporting System Cases: Comparative Performance Study

  • By

  • Young Mi Ha

  • Minjung Kim

  • YoungIn Bang

  • Daejin Choi

  • Jae Hyun Kim

  • Sandy Jeong Rhie

  • Yoshihiro Noguchi

  • Myeong Gyu Kim

  • July 8, 2026

  • 0 min

Share

  • 1

    Postmarketing pharmacovigilance is crucial for identifying adverse drug reactions not captured in clinical trials.

  • 2

    Causality assessment between drugs and adverse events is essential for signal detection and patient safety.

  • 3

    The WHO-UMC causality assessment system relies on expert interpretation, introducing subjectivity and variability.

  • 4

    Large language models (LLMs) have potential for analyzing unstructured text in adverse event reports.

  • 5

    This study aims to evaluate LLM performance in drug-AE causality assessment using structured FAERS cases.

Original Source(s)

Large Language Models for World Health Organization–Uppsala Monitoring Centre Drug–Adverse Event Causality Assessment Using Food and Drug Administration Adverse Event Reporting System Cases: Comparative Performance Study

  • by Young Mi Ha, Minjung Kim, YoungIn Bang, Daejin Choi, Jae Hyun Kim, Sandy Jeong Rhie, Yoshihiro Noguchi, Myeong Gyu Kim

  • July 8, 2026

Related Content

Same-Day COVID, Flu Vaccination Appears Safe

Study found no increased 90-day risk of serious adverse events with coadministration compared with vaccination alone.

Secretary Kennedy, Administrator Oz Launch ‘Make Hospital Food Healthier’ Pledge

EASIX as a moderately effective prognostic marker for mortality in severe acute pancreatitis: a retrospective study