GPT-4-based AI agents—the new expert system for detection of antimicrobial resistance mechanisms?

The European Committee on Antimicrobial Susceptibility Testing (EUCAST) recommends two steps for detecting beta-lactamases in Gram-negative bacteria. A study validated generative pre-trained transformer (GPT)-4 and GPT-agent for pre-classification of disk diffusion to indicate potential beta-lactamases. The study assigned 225 Gram-negative isolates based on phenotypic resistances against beta-lactam antibiotics and additional tests to resistance mechanisms. The GPT-agent was customized with EUCAST guidelines and compared to routine diagnostics. Results showed higher concordance and shorter argumentations for microbiologists and higher specificities for humans.