Study of the Total Antioxidant Capacity (TAC) in Native Cereal-Pulse Flours and the Influence of the Baking Process on TAC Using a Combined Bayesian and Support Vector Machine Modeling Approach

During the last few years, the increasing evidence of dietary antioxidant compounds and reducing chronic diseases and the relationship between diet and health has promoted an important innovation within the baked product sector, aiming at healthier formulations. This study aims to develop a tool based on mathematical models to predict baked goods' total antioxidant capacity (TAC). The high variability of antioxidant properties of flours based on the aspects related to the type of grain, varieties, proximal composition, and processing, among others, makes it very difficult to innovate on food product development without specific analysis. Total phenol content (TP), oxygen radical absorbance capacity (ORAC), and ferric-reducing antioxidant power assay (FRAP) were used as markers to determine antioxidant capacity. Three Bayesian-type models are proposed based on a double exponential parameterized curve that reflects the initial decrease and subsequent increase as a consequence of the observed processes of degradation and generation, respectively, of the antioxidant compounds. Once the values of the main parameters of each curve were determined, support vector machines (SVM) with an exponential kernel allowed us to predict the values of TAC, based on baking conditions (temperature and time), proteins, and fibers of each native grain.

Automated summary

In recent years, the relationship between dietary antioxidant compounds and reducing chronic diseases has led to innovation in the baked product sector in order to develop healthier formulations. This study aims to develop a mathematical model-based tool for predicting the total antioxidant capacity (TAC) of baked goods. The variability of antioxidant properties in flours due to factors such as grain type, varieties, composition, and processing makes it challenging to innovate in food product development without specific analysis. Bayesian-type models based on parameterized double exponential curves were proposed to reflect the degradation and generation processes of antioxidant compounds. Support vector machines (SVM) with an exponential kernel were used to predict TAC values based on baking conditions, proteins, and fibers of each grain.