The field of medication attribute extraction and pharmacovigilance is moving towards more accurate and efficient methods of extracting and analyzing data from Electronic Health Records (EHRs) and pharmacovigilance databases. Recent developments have focused on customizing large language models to extract specific attributes from heterogeneous EHR systems, enabling consistent cross-site analyses of medication exposure, adherence, and retention. Additionally, there is a growing need for publicly available datasets and tools to support the development of more robust and accurate drug recommendation systems. Noteworthy papers include:

• Customizing Open Source LLMs for Quantitative Medication Attribute Extraction across Heterogeneous EHR Systems, which presents a practical framework for extracting medication attributes from EHRs with high accuracy.
• CDrugRed: A Chinese Drug Recommendation Dataset for Discharge Medications in Metabolic Diseases, which introduces a publicly available dataset for drug recommendation in metabolic diseases.
• SurVigilance: An Application for Accessing Global Pharmacovigilance Data, which streamlines the process of retrieving safety data from multiple pharmacovigilance databases.