Artificial neural network data fusion-mediated dual-mode sensor based on Fe3O4@PdIr for Salmonella Typhimurium detection in food

Colorimetric/electrochemical sensor was established for S. typhimurium detection. • A specific aptamer for capturing S. typhimurium has enhanced detection accuracy. • Fe 3 O 4 @PdIr showed enhanced POD-like activity and electrochemical performance. • ANN model achieved dual signal fusion and output a single detection result. • The sensor showed low LOD value of 1.66 CFU/mL assisted by ANN data fusion. Salmonella Typhimurium ( S. typhimurium ) is a major foodborne pathogen that poses a serious threat to public health. In this study, a colorimetric/electrochemical dual-mode biosensor assisted by artificial neural network (ANN) was developed for the sensitive detection of S. typhimurium . Fe 3 O 4 @PdIr nanocomposites with enhanced peroxidase-like activity and electrochemical performance were prepared and conjugated with an aptamer specific to S. typhimurium to obtain Fe 3 O 4 @PdIr-Apt. Through the sandwich binding of Fe 3 O 4 @PdIr-Apt and Apt to the target, the nanocomposites were attached to microplates or Au electrodes, thereby generating colorimetric and electrochemical signals. The ANN model deeply resolved the complex nonlinear relationship between the dual signals, enabling mutual correction and ultimately performing data fusion to output a single detection result, which significantly reduced the mean square error while improving detection sensitivity and reliability. This sensor exhibited a wide linear range of 2.7–2.7 × 10 8  CFU/mL and a low detection limit of 1.66 CFU/mL. Additionally, this method was successfully applied to the detection of S. typhimurium in pork and milk, with a recovery rate of 95.19% ~ 104.07%. It indicated that the constructed sensor holds great practical potential for S. typhimurium detection. Download: Download high-res image (117KB) Download: Download full-size image