English

PVLens: Enhancing Pharmacovigilance Through Automated Label Extraction

Computation and Language 2025-03-28 v2 Machine Learning

Abstract

Reliable drug safety reference databases are essential for pharmacovigilance, yet existing resources like SIDER are outdated and static. We introduce PVLens, an automated system that extracts labeled safety information from FDA Structured Product Labels (SPLs) and maps terms to MedDRA. PVLens integrates automation with expert oversight through a web-based review tool. In validation against 97 drug labels, PVLens achieved an F1 score of 0.882, with high recall (0.983) and moderate precision (0.799). By offering a scalable, more accurate and continuously updated alternative to SIDER, PVLens enhances real-time pharamcovigilance with improved accuracy and contemporaneous insights.

Keywords

Cite

@article{arxiv.2503.20639,
  title  = {PVLens: Enhancing Pharmacovigilance Through Automated Label Extraction},
  author = {Jeffery L Painter and Gregory E Powell and Andrew Bate},
  journal= {arXiv preprint arXiv:2503.20639},
  year   = {2025}
}