Appetite ratings of foods are predictable with an in vitro advanced gastrointestinal model in combination with an in silico artificial neural network

The expected increase of global obesity prevalence makes it necessary to have information about the effects of meal intakes on the feeling of appetite. Because human clinical studies are time and cost intensive, there is a need for a reliable alternative. The aim of this study was to develop and evaluate an in vitro-in silico technology to predict the feelings of fullness and hunger after consumption of different types of meals. In this technology the results from an in vitro gastrointestinal model (tiny-TIMagc) on gastric viscosity and intestinal digestion of different meals were used as input data for an in silico artificial neural network (ANN). The predictions of the feeling of fullness and hunger were compared with actual human scores for these parameters after intake of the same type of meals. From these first series of experiments, with a relatively small number of in vitro digestive parameters as input for in silico modeling, a reasonable prediction of appetite rating for foods can be realized at a time- and cost-effective way. [Display omitted] •Evaluation of in vitro-in silico technology to predict appetite feelings•In vitro viscosity and digestion as input data for in silico modeling•In vitro-in silico prediction was validated versus actual human appetite data•Even small number of in vitro data for in silico modeling result in good prediction