Forecasting Bacterial Antimicrobial Resistance Trends Using Machine Learning on WHO GLASS Surveillance Data: A Retrieval-Augmented Generation Approach for Policy Decision Support
A new research paper proposes a machine learning approach to forecast bacterial antimicrobial resistance (AMR) trends using data from the WHO Global Antimicrobial Resistance and Use Surveillance System (GLASS). The study benchmarks six models, finding that XGBoost performs best, reducing error by over 85% compared to a naive baseline. To translate these forecasts into actionable policy, a Retrieval-Augmented Generation (RAG) system powered by Gemma 4 was developed to provide evidence-based guidance without fabricating information. AI
IMPACT This research demonstrates a novel application of ML and RAG for public health policy, potentially improving global response to antimicrobial resistance.