Fusarium graminearum is a mould that causes serious diseases in cereals worldwide and that synthesises mycotoxins such as deoxynivalenol (DON), which can seriously affect human and animal health. Predicting the level of mycotoxin accumulation in food is very difficult, because of the complexity of the influencing parameters. In this work, we have studied the possibility of using artificial neural networks (NN) to predict DON level attained in F. graminearum wheat cultures taking as inputs the fungal contamination level of the cereal, the water activity as a measure of the available water for fungal growth in the cereal, the temperature and time. DON analysis was performed by gas chromatography with electron capture detection. The data matrix was used to train and validate various types of NN using MATLAB 7.0. The aim was to obtain a network that provided the best possible fit between predicted and target DON levels by minimising the mean-square error of test. Radial basis function-NNs attained lower errors and better generalisation than multi-layer perceptron networks to predict DON accumulation in wheat. This is the first time that NNs have been used to predict DON accumulation in wheat based on the studied factors.