Using Large Language Models to Assist Antimicrobial Resistance Policy Development: Integrating the Environment into Health Protection Planning

Antimicrobial resistance (AMR) is a significant global health and economic threat, leading to the development of National Action Plans (NAPs). However, in low-to-middle-income countries, gaps exist between aspirations and actions. A multilingual database containing policy guidance from 146 countries was compiled to bridge these gaps. The AMR-Policy GPT, a large language model with advanced retrieval-augmented generation capabilities, was developed to search and summarize evidence from plans, metadata, and technical knowledge. The prototype has the potential to support inclusive, evidence-informed AMR policy guidance for governments, research, and public agencies.