Differences Due to Sex and Sweetener on the Bioavailability of (Poly)phenols in Urine Samples: A Machine Learning Approach.

Metabolic diseases have been related to the overdrinking of high-sugar content beverages. As a result, the demand for alternative formulations based on plant-based ingredients with health-promoting properties has increased during the last few years. Nonetheless, the design and production of effective formulations requires understanding the bioavailability of these compounds. For this purpose, a two-month longitudinal trial with 140 volunteers was conducted to measure the beneficial effects of a maqui-citrus beverage, rich in (poly)phenols. From data obtained by quantifying metabolites present in urine samples, biostatistical and machine learning (data imputation, feature selection, and clustering) methods were applied to assess whether a volunteer's sex and the sweetener added to the beverage (sucrose, sucralose, or stevia) affected the bioavailability of (poly)phenol metabolites. Several metabolites have been described as being differentially influenced: 3,4-dihydroxyphenylacetic acid and naringenin with its derivatives were positively influenced by stevia and men, while eriodictyol sulfate and homoeridictyol glucunoride concentrations were enhanced with stevia and women. By examining groups of volunteers created by clustering analysis, patterns in metabolites' bioavailability distribution as a function of sex and/or sweeteners (or even due to an uncontrolled factor) were also discovered. These results underline the potential of stevia as a (poly)phenol bioavailability enhancer. Furthermore, they also evidence sex affects the bioavailability of (poly)phenols, pointing at a sex-dependent metabolic pathway regulation.

Bioactive Compounds in Plasma as a Function of Sex and Sweetener Resulting from a Maqui-Lemon Beverage Consumption Using Statistical and Machine Learning Techniques.

The present study analyses the effect of a beverage composed of citrus and maqui (Aristotelia chilensis) with different sweeteners on male and female consumers. Beverages were designed and tested (140 volunteers) as a source of polyphenols, in a previous work. Plasma samples were taken before and after two months of daily intake. Samples were measured for bioactive-compound levels with metabolomics techniques, and the resulting data were analysed with advanced versions of ANOVA and clustering analysis, to describe the effects of sex and sweetener factors on bioactive compounds. To improve the results, machine learning techniques were applied to perform feature selection and data imputation. The results reflect a series of compounds which are more regulated for men, such as caffeic acid or 3,4-dihydroxyphenylacetic acid, and for women, trans ferulic acid (TFA) or naringenin glucuronide. Regulations are also observed with sweeteners, such as TFA with stevia in women, or vanillic acid with sucrose in men. These results show that there is a differential regulation of these two families of polyphenols by sex, and that this is influenced by sweeteners.