Associations between Taste Perception Profiles and Empirically Derived Dietary Patterns: An Exploratory Analysis among Older Adults with Metabolic Syndrome

Abstract

Taste perception is a primary driver of food choices; however, little is known about how perception of all five tastes (sweet, salt, sour, bitter, umami) collectively inform dietary patterns. Our aim was to examine the associations between a multivariable measure of taste perception-taste perception profiles-and empirically derived dietary patterns. The cohort included 367 community-dwelling adults (55-75 years; 55% female; BMI = 32.2 ± 3.6 kg/m²) with metabolic syndrome from PREDIMED-Plus, Valencia. Six taste perception profiles were previously derived via data-driven clustering (Low All, High Bitter, High Umami, Low Bitter and Umami, High All But Bitter, High All But Umami); three dietary patterns were derived via principal component analysis (% variance explained = 20.2). Cross-sectional associations between profiles and tertials of dietary pattern adherence were examined by multinomial logistic regression. Overall, there were several significant differences in dietary pattern adherence between profiles: the vegetables, fruits, and whole grains pattern was significantly more common for the High All But Umami profile (OR range for high vs. low adherence relative to other profiles (1.45-1.99; 95% CI minimum lower, maximum upper bounds: 1.05, 2.74), the non-extra virgin olive oils, sweets, and refined grains pattern tended to be less common for Low All or High Bitter profiles (OR range: 0.54-0.82), while the alcohol, salty foods, and animal fats pattern tended to be less common for Low Bitter and Umami and more common for High All But Bitter profiles (OR range: 0.55-0.75 and 1.11-1.81, respectively). In conclusion, among older adults with metabolic syndrome, taste perception profiles were differentially associated with dietary patterns, suggesting the benefit of integrating taste perception into personalized nutrition guidance.

Keywords: bitter; data-driven; dietary patterns; individual differences; personalized nutrition; salt; sour; sweet; taste; taste perception; umami.

Figure 1

Six taste perception profiles derived via a data-driven clustering approach in the PREDIMED-Plus Valencia cohort; N = 367 (adapted with permission [24]). Mean perception of each taste for each profile is depicted in solid black lines; mean ± 1 SD perception of each taste for the overall cohort is represented by dark gray lines and shaded areas, respectively. Taste perception scores ranged from 0–5; 0 is the innermost pentagon and 5 is the outer most pentagon.

Figure 2

Rotated food group factor loadings from principal component analysis for three empirically derived dietary patterns. EVOO, extra virgin olive oil; SSBs, sugar-sweetened beverages.

Figure 3

Heat map showing the odds (in log(odds)) of having high, relative to low, adherence to each empirically derived dietary pattern among participants with each taste perception profile (N = 367 participants included in each heat map). Regression models were adjusted for age, sex, physical activity, smoking status, medication use, type 2 diabetes, and BMI. The profiles on the vertical axis are the test profiles and those on the horizontal axis are the reference profiles; together they lay the grid for all unique pairwise comparisons. Colors indicate the magnitude of association; darker purple indicates higher odds of having high adherence and darker orange indicates lower odds of having high adherence relative to the reference profile. For example, in the left panel, the dark purple square at the lower left indicates that relative to individuals with a Low All profile (reference), those with a High All But Umami profile had significantly higher odds of having high, relative to low, adherence to the Veg/Fruit/WG dietary pattern. * p < 0.05, ** p < 0.01.