Application of data mining techniques to predict the production of aflatoxin B1 in dry-cured ham

Abstract

Dry-cured ham may be contaminated with aflatoxin B1 (AFB1) produced by Aspergillus spp. Temperature and water activity (aw) are two key parameters that affect both ham ripening and AFB1 production. The objective of this study was to predict AFB1 production by Aspergillus parasiticus and Aspergillus flavus strains in conditions related to dry-cured ham ripening using data mining techniques. J48 decision tree, isotonic regression (IR), and multiple linear regression (MLR) were tested to (a) classify and predict AFB1 concentration as a function of different days, temperatures and aw values and (b) predict the beginning of AFB1 production as a function of different temperatures and aw values. For this, a model system based on a dry-cured ham-based medium was used. The percentage of correct classification was higher than 75%. R values to predict the concentration of AFB1 when applying MLR were 0.81, being higher than those obtained after using IR. The models developed were validated with experimental data obtained after inoculating samples of dry-cured ham with two aflatoxigenic strains. The predicted AFB1 concentration showed correlation coefficients ≥0.74 and prediction errors ≤0.38, confirming the feasibility of the prediction equations obtained. This information may help to make informed decisions to minimise the hazard posed by AFB1 in dry-cured ham.