Development and validation of a neural network model for predicting growth of Salmonella Newport on diced Roma tomatoes during simulated salad preparation and serving: extrapolation to other serotypes

Abstract

Summary A study was undertaken to model growth of Salmonella on tomatoes for developing and validating a predictive model for use in risk assessment. Cylindrical portions (0.14 g) of Roma tomato pulp were inoculated with a low dose (0.89 log MPN) of Salmonella Newport. The inoculated tomato portions were incubated for 0–8 h at 16–40 °C in 2 °C increments to obtain most probable number (MPN) data for model development and validation. A multiple‐layer feedforward neural network model with two hidden layers of two nodes each was developed. The proportion of residuals in an acceptable prediction zone (pAPZ) from −1 (fail‐safe) to 0.5 log (fail‐dangerous) was 0.93 (194/209) for dependent data and 0.96 (86/90) for independent data for interpolation. A pAPZ ≥0.7 indicated that the model provided acceptable predictions. Thus, the model was successfully validated. It was also validated for extrapolation to seven other Salmonella serotypes.

Evaluation of microbiological and physico‐chemical parameters of retail ready‐to‐eat mono‐varietal salads

“…Furthermore, these products are generally investigated considering mix of vegetables, but very limited information are available on the bacterial evolution of mono‐varietal salads to predict the microbial dynamics of each species. The development and validation of food models for predicting growth of given pathogenic bacteria is of relevance (Oscar, ) for future applications on ready‐to‐eat vegetable salads.…”

Predictive model for growth of Salmonella Newport on Romaine lettuce

“…Recently, a model (multiple‐layer feed forward neural network) for growth of the same strain of Salmonella Newport (0.85 log) on Roma tomato portions (0.14 g) incubated at times (0–8 hr) and temperatures (16–40°C) observed during meal preparation was developed and validated (interpolation) using the APZ method (Oscar, ). This model was also validated for extrapolation to other serotypes of Salmonella (e.g., Montevideo, Thompson, Hadar, Heidelberg, and Typhimurium var 5‐) using the APZ method.…”

“…Thus, the current model can be improved by validating it for extrapolation to other serotypes and if serotypes are found that grow differently than Salmonella Newport, the model could be expanded to include these serotypes as was done in a previous study (Oscar, ). In general, most serotypes of Salmonella have similar growth kinetics (Oscar, , ) but a few, such as Enteritidis (Oscar, ), Kentucky (Oscar, ), and 8.20:–: z 6 (Oscar, ), grow slower…”

“…Thus, it is possible that the model could be “fail‐dangerous” instead. A way to avoid this issue is to develop a model with a single strain, like was done in this study, and then validate the model for extrapolation to other strains as was done in previous studies (Oscar, , ). In addition, a model developed with a single strain can be expanded to include other strains that growth differently.…”

Membrane fatty acids composition and fluidity modification in Salmonella Typhimurium by culture temperature and resistance under pulsed electric fields

“…Therefore, S. Typhimurium, as a major foodborne pathogen (Oscar, ), was employed to explore the relationships among growth temperature, fatty acid composition of cytomembrane and PEF resistance of S. Typhimurium cells. The alteration of fatty acid composition induced by different growth temperatures was analysed and thus the correlation between PEF resistance and membrane fatty acid composition of cell was elucidated.…”