Genomic traits and social determinants of health drive bacterial antimicrobial resistance: current trends and projections to 2050

Antimicrobial resistance (AMR) is projected to increase globally, yet the genomic traits and social determinants of health driving its trajectory are poorly understood. Here, we present the first global-scale AMR forecasting analysis, integrating machine learning, Monte Carlo simulations and forecasting modelling to identify clinically relevant AMR traits projected to increase, and the key determinants driving their increase over the next 25 years. We analysed 45,645 bacterial genomes (including ESKAPE and World Health Organisation high/critical priority pathogens), 298,288 resistance profiles, spanning 84 antibiotics across 27 antimicrobial classes and 1112 determinants of health across 125 countries. We identified 78 clinically relevant AMR feature-pathogen pairs projected to rise globally by 2050. Among these, 94.9% were multidrug resistant (MDR), 89.7% globally widespread, 80.8% persisting over time, and 48.7% multi-host. Our analysis reveals mortality indicators (68.79%) are the strongest predictors, followed by socioeconomic factors (15.29%), and antibiotic consumption (4.46%). However, at the molecular level, socioeconomic disparities are the primary drivers of AMR, strongly associated to the fourteen most critical features (aadA, aadA2, APH(3')-Ia, APH(3'')-Ib, APH(6)-Id, ermB, mphA, qacEdelta1, rep_cluster_1118, sul1, sul2, TEM-34, tet(A), and tet(M)). These features emerged as primary health threats, clinically relevant, MDR, human-enriched, inter-species spreaders, plasmid-associated, and present across up to 10 hosts in at least four World Bank regions. By understanding the interplay of biological and social factors in shaping AMR trends to 2050, we provide a roadmap for targeted AMR mitigation.