Abstract
Antimicrobial resistance (AMR) presents a significant global challenge, creating an urgent need for rapid and sensitive antimicrobial susceptibility testing (AST) methods to guide timely treatment decisions. Traditional AST techniques, such as broth microdilution, disk diffusion, and gradient diffusion assays, require extended incubation times, delaying critical therapeutic interventions. In this study, we present a dynamic holographic laser speckle imaging (DhLSI) system, coupled with machine learning algorithms, for rapid assessment of bacterial susceptibility upon antibiotic treatment. Our method operates by utilizing a reference beam to enhance the detection of weak scattering signals, capable of performing AST at bacterial concentrations as low as 10(3) CFU/mL, while producing results consistent with those obtained using the standard concentration of 10(5) CFU/mL. By employing artificial neural networks (ANN) to analyze dynamic speckle patterns, the DhLSI system can determine bacterial susceptibility within 2-3 h. The system was validated using model Gram-positive and Gram-negative bacterial strains, as well as two antibiotic treatments with different mechanisms of action. Experiments conducted on bacteria incubated on different days demonstrated consistent performance. This approach offers a rapid, label-free platform for early-stage infection diagnosis and effective antimicrobial stewardship, with the potential to be implemented in clinical settings to address AMR challenges.