Neural network models for growth of Salmonella serotypes in ground chicken subjected to temperature abuse during cold storage for application in HACCP and risk assessment

摘要

Predictive microbiology models are valuable tools for helping to assess and manage the risk of illness from food contaminated with human pathogens, such as Salmonella. However, multiple versions of a model may be needed for different food safety applications, such as hazard analysis and critical control point (HACCP) programs and risk assessment. A neural network model for growth of Salmonella in ground chicken as a function of time (0 to 8 days) at 16 ℃ and serotype (n = 8) was developed. The proportion of residuals in an acceptable prediction zone (pAPZ) from -1 log (fail-safe) to 0.5 log (fail-dangerous) was 0.948 for training data (n = 192) and 0.988 for testing data (n = 84). A pAPZ ≥0.7 indicated that the model provided predictions with acceptable bias and accuracy. Thus, the model was successfully validated. Different versions of the model were developed for application in HACCP and risk assessment.