Assessment of salmon sashimi processing conditions for Listeria monocytogenes cross-contamination and effectiveness of CLPSO-BP neural network model constructed for predicting microbial transfer.

During preparation stages of ready-to-eat (RTE) foods, they can be cross-contaminated with Listeria monocytogenes which could result to outbreaks of foodborne listeriosis. In this study, the effects of gloves, cutting boards and cleaning methods on the transmission of L. monocytogenes during the processing of salmon sashimi were investigated. Subsequently, an improved particle swarm algorithm optimized BP neural network prediction model (CLPSO-BP) was developed based on Lévy flight and chaotic mapping. After processing contaminated salmons with gloves, we found that the surfaces of the gloves contained a significant amount of L. monocytogenes (5.24 log CFU/g), and 10.69% of the bacteria were subsequently transferred to uninfected salmon after being processed with the same gloves. Contamination of the processing tools with L. monocytogenes was reduced by up to 3 log CFU/g and the transfer rate was reduced by up to 50% after cleaning with room temperature water and detergent. In contrast, no bacteria were found after wiping the surfaces of the tools 70 °C hot water and detergent. The mean squared error (MSE) for the CLPSO-BP modeling tests was 0.1003, indicating accurate predictions. Overall, choosing an appropriate cleaning method and changing gloves regularly can help to avoid cross-contamination when processing RTE foods. • Sufficient independent tests were conducted to determine the range of transfer rates. • CLPSO-BP model has been developed to predict cross-contamination scenarios. • The improved PSO algorithm yields accurate results with small sample sizes. [ABSTRACT FROM AUTHOR]