Data-Driven Early Warning Approach for Antimicrobial Resistance Prediction-Anomaly Detection Based on High-Level Indicators.

Environmental conditions are increasingly recognized as important contributors to the emergence and spread of antimicrobial resistance (AMR), yet early detection of high-risk situations remains difficult. This study developed a data-driven framework to identify anomalous environmental profiles associated with potential AMR risk. Using an unsupervised anomaly detection method (Isolation Forest) applied to multivariate indicators-including pesticide use, land use change, precipitation, and crop type-we detected unusual environmental patterns without prior AMR data. The anomaly detection analysis highlighted pesticide use, population density, land use change, and fertilizer application as the dominant environmental factors, together explaining the largest share of variation in anomaly scores (each contributing around one-quarter to one-third of the model's decisions). In the subset of anomalous cases, fertilizer and pesticide intensity exerted the strongest negative impact, confirming their role as key drivers of atypical environmental profiles. Extreme precipitation and crop-specific production patterns also emerged as influential in certain cases. These results show that our interpretable framework can both rank global drivers and reveal context-dependent risks, thereby enabling the development of early-warning strategies for AMR surveillance.