Antimicrobial resistance recommendations via electronic health records with graph representation and patient population modeling

The study presents a deep learning framework for generating Antimicrobial Resistance (AMR) recommendations using electronic health records (EHRs). The framework uses a deep graph neural network to model correlations between medical events, incorporates population-level observation to address pathogen evolution, and adopts a multi-task learning strategy for simultaneous recommendations on multiple AMRs. Extensive experimental evaluations on over 110,000 patients with urinary tract infections validate the efficacy of the approach, demonstrating the potential of EHR-based systems in AMR recommendation.