(In Peer Review - ID 1598979 @Frontiers in Medicine) Automatic Extraction of SmPC document for IDMP data model construction using Open-Source Foundation Model LLM RAG: A preliminary experiment for Pharmaceutical Regulatory Affairs.
Published Tentatively July 2025
This research introduces an automated approach using open-source Large Language Models with Retrieval-Augmented Generation (RAG) to extract critical data from SmPC documents for building the IDMP data model, crucial in pharmaceutical regulatory compliance. The study aims to streamline and enhance the accuracy of data extraction for regulatory affairs, reducing the manual workload in aligning with IDMP standards.
Recommended citation: EU ISO IDMP IG Chapter 2: Data elements for the electronic submission of information on medicinal products for human use. European Medicines Agency, v2.1.1.