Higher dietary flavonoid intakes are associated with lower objectively measured body composition in women: evidence from discordant monozygotic twins

Abstract

Background: Although dietary flavonoid intake has been associated with less weight gain, there are limited data on its impact on fat mass, and to our knowledge, the contribution of genetic factors to this relation has not previously been assessed.Objective: We examined the associations between flavonoid intakes and fat mass.Design: In a study of 2734 healthy, female twins aged 18-83 y from the TwinsUK registry, intakes of total flavonoids and 7 subclasses (flavanones, anthocyanins, flavan-3-ols, flavonols, flavones, polymers, and proanthocyanidins) were calculated with the use of food-frequency questionnaires. Measures of dual-energy X-ray absorptiometry-derived fat mass included the limb-to-trunk fat mass ratio (FMR), fat mass index, and central fat mass index.Results: In cross-sectional multivariable analyses, higher intake of anthocyanins, flavonols, and proanthocyanidins were associated with a lower FMR with mean ± SE differences between extreme quintiles of -0.03 ± 0.02 (P-trend = 0.02), -0.03 ± 0.02 (P-trend = 0.03), and -0.05 ± 0.02 (P-trend < 0.01), respectively. These associations were not markedly changed after further adjustment for fiber and total fruit and vegetable intakes. In monozygotic, intake-discordant twin pairs, twins with higher intakes of flavan-3-ols (n = 154, P = 0.03), flavonols (n = 173, P = 0.03), and proanthocyanidins (n = 172, P < 0.01) had a significantly lower FMR than that of their co-twins with within-pair differences of 3-4%. Furthermore, in confirmatory food-based analyses, twins with higher intakes of flavonol-rich foods (onions, tea, and pears; P = 0.01) and proanthocyanidin-rich foods (apples and cocoa drinks; P = 0.04) and, in younger participants (aged <50 y) only, of anthocyanin-rich foods (berries, pears, grapes, and wine; P = 0.01) had a 3-9% lower FMR than that of their co-twins.Conclusions: These data suggest that higher habitual intake of a number of flavonoids, including anthocyanins, flavan-3-ols, flavonols, and proanthocyanidins, are associated with lower fat mass independent of shared genetic and common environmental factors. Intervention trials are needed to further examine the effect of flavonoid-rich foods on body composition.

Keywords: body composition; diet; fat distribution; flavonoids; twins.

FIGURE 1

Percentage differences in fat mass and fat mass distribution between extreme quantiles of intake of flavonoid-rich foods in 2734 women aged 18–83 y. Bars represent percentage differences in outcome measures between extreme quantiles of intake (portions per day). Quantile limits were selected on the basis of the best data distribution. Flavanone-rich foods (quintiles) were oranges (120 g), grapefruit (80 g), and fruit juice (160 g); anthocyanin-rich foods (quintiles) were berries (100 g), pears (170 g), grapes (80 g), and wine (125 mL); flavonol-rich foods (quintiles) were pears (170 g), tea (260 mL), and onions (60 g); flavone-rich foods (quintiles) were wine (125 mL), oranges (120 g), and peppers (80 g); and proanthocyanidin-rich foods (tertiles) were apples (100 g) and a cocoa beverage with milk (260 mL). Tea (260 mL) was the only food that contributed ≥10% to intakes of total flavonoids, flavan-3-ols, and polymers and was included individually in the figure (quartiles). *^,**P values were calculated with the use of an ANCOVA with age, smoking, physical activity, menopausal status, hormone replacement therapy use, vitamin-supplement use, alcohol use, and intakes of energy, caffeine, saturated fat, polyunsaturated fat, monounsaturated fat, whole grains, and sugar-sweetened beverages as covariates: *P < 0.05, **P < 0.01.

FIGURE 2

Mean ± SE differences in the fat mass ratio between monozygotic co-twins who were discordant for intakes of different flavonoid subclasses. Bars represent differences between twins with higher intake and twins with lower intake for the whole cohort (open bars) and in twins <50 y old (shaded bars). Discordance was defined as a within-pair difference in intake ≥1 SD. Flavanone-rich foods were oranges (120 g), grapefruit (80 g) and fruit juice (160 g); anthocyanin-rich foods were berries (100 g), pears (170 g), grapes (80 g), and wine (125 mL); flavonol-rich foods were pears (170 g), tea (260 mL), and onions (60 g); flavone-rich foods were wine (125 mL), oranges (120 g), and peppers (80 g); and proanthocyanidin-rich foods were apples (100 g) and a cocoa beverage with milk (260 mL). *^,**For comparisons of twins with higher intake with twins with lower intake (paired sample t tests): *P < 0.05, **P < 0.01.