Global prediction of antimicrobial resistance trends using statistical and machine learning models: Evaluating...

Antimicrobial resistance (AMR) is a pressing global health challenge, particularly affecting low- and middle-income countries. This study aims to evaluate the spread of AMR both across time and across different regions of the world.

We analysed clinical isolates from 65 countries. A country-specific time-series forecasting (i.e. seasonal autoregressive integrated moving average (SARIMA), long short-term memory (LSTM), and seasonal autoregressive integrated moving average-LSTM hybrid models) were performed for Acinetobacter baumannii in Argentina (2004-2030) as a case study to demonstrate model applicability for national-level prediction. Moreover, interrupted time series regression was applied to predict antibiotic-resistance trends and assess the global impact of national action plans.

Southeast Asia and Africa exhibited the highest AMR burdens, with Indonesia (0.65), Egypt (0.52), and Malawi (0.49) having the highest resistance scores. An income-based gradient was observed across key pathogens, third-generation cephalosporin and carbapenem-resistant Escherichia coli, Klebsiella pneumoniae, and A. baumannii were significantly more prevalent in low- and middle-income countries. Gender-wise analysis revealed significantly higher resistance rates in males across most antibiotics, especially levofloxacin. Age-stratified analyses revealed higher resistance in elderly populations, particularly to fluoroquinolones and β-lactams. Forecasting for A. baumannii in Argentina (2004-2030) indicated a continued upward resistance across β-lactam and fluoroquinolones, with LSTM achieving the lowest root mean square error across five antibiotics. The interrupted time series revealed a prenational action plan decline but no significant postimplementation change.

This study provides a comprehensive data-driven framework to monitor and forecast AMR, evaluate policy interventions, and, hence, suggest targeted interventions and strategies for each income group and region, moving beyond the one-size-fits-all approach.