Changing from a Western to a Mediterranean-style diet does not affect iron or selenium status: results of the New Dietary Strategies Addressing the Specific Needs of the Elderly Population for Healthy Aging in Europe (NU-AGE) 1-year randomized clinical trial in elderly Europeans

Abstract

Background: Mediterranean diets limit red meat consumption and increase intakes of high-phytate foods, a combination that could reduce iron status. Conversely, higher intakes of fish, a good source of selenium, could increase selenium status.

Objectives: A 1-y randomized controlled trial [New Dietary Strategies Addressing the Specific Needs of the Elderly Population for Healthy Aging in Europe (NU-AGE)] was carried out in older Europeans to investigate the effects of consuming a Mediterranean-style diet on indices of inflammation and changes in nutritional status.

Methods: Selenium and iron intakes and status biomarkers were measured at baseline and after 1 y in 1294 people aged 65-79 y from 5 European countries (France, Italy, the Netherlands, Poland, and the United Kingdom) who had been randomly allocated either to a Mediterranean-style diet or to remain on their habitual, Western diet.

Results: Estimated selenium intakes increased significantly with the intervention group (P < 0.01), but were not accompanied by changes in serum selenium concentrations. Iron intakes also increased (P < 0.001), but there was no change in iron status. However, when stratified by study center, there were positive effects of the intervention on iron status for serum ferritin for participants in Italy (P = 0.04) and France (P = 0.04) and on soluble transferrin receptor (sTfR) for participants in Poland (P < 0.01). Meat intake decreased and fish intake increased to a greater degree in the intervention group, relative to the controls (P < 0.01 for both), but the overall effects of the intervention on meat and fish intakes were mainly driven by data from Poland and France. Changes in serum selenium in the intervention group were associated with greater changes in serum ferritin (P = 0.01) and body iron (P = 0.01), but not sTfR (P = 0.73); there were no study center × selenium status interactions for the iron biomarkers.

Conclusions: Consuming a Mediterranean-style diet for 1 y had no overall effect on iron or selenium status, although there were positive effects on biomarkers of iron status in some countries. The NU-AGE trial was registered at clinicaltrials.gov as NCT01754012.

Keywords: Europeans; Mediterranean-style diet; elderly; fish; iron; meat; randomized controlled trial; selenium.

FIGURE 1

Flow chart of participants in the New Dietary Strategies Addressing the Specific Needs of the Elderly Population for Healthy Aging in Europe (NU-AGE) trial. AGP, ɑ1 acid glycoprotein; CRP, C-reactive protein; sTfR, soluble transferrin receptor.

FIGURE 2

Baseline biomarkers of selenium intake and status by study center in 1244 men and women aged 65–79 y. Values are means (error bars show 95% CIs), adjusted for age, sex, baseline BMI, and smoking status. Data were missing for 449 selenium intake and 65 serum selenium values. Bars sharing a letter were not significantly different after adjustment for multiple testing (q > 0.05), and were only tested where there was an overall significant difference between countries (P < 0.05, ANCOVA).

FIGURE 3

Associations between selenium intake and serum selenium status at baseline in 767 men and women aged 65–79 y, by study center. The scatter plots represent the association of selenium intake with serum selenium status. The regression lines and P values were calculated from linear regression, and r indicates a partial correlation coefficient. All models were adjusted for age, sex, baseline BMI, and smoking status.

FIGURE 4

Baseline biomarkers of iron intake and status by study center in 1247 men and women aged 65–79 y. Values are means (error bars indicate 95% CIs), adjusted for age, sex, baseline BMI, and smoking status. Serum ferritin values were adjusted for CRP, AGP, and sTfR for AGP, using a regression correction. Body iron was calculated using inflammation-adjusted values for ferritin and sTfR. Data were missing for 118 serum ferritin and body iron and 15 sTfR values. Bars sharing a letter were not significantly different after adjustment for multiple testing (q > 0.05), and were only tested where there was an overall significant difference between countries (P < 0.05, ANCOVA). AGP, ɑ1 acid glycoprotein; CRP, C-reactive protein; sTfR, soluble transferrin receptor.

FIGURE 5

Associations between serum selenium and biomarkers of iron status at baseline in 1173 men and women aged 65–79 y. The scatter plots represent the association of selenium status with biomarkers of iron status. The regression lines and P values were calculated from linear regression, and r indicates a partial correlation coefficient. Serum ferritin values were adjusted for CRP, AGP, and sTfR for AGP using a regression correction. Body iron was calculated using the inflammation-adjusted values for ferritin and sTfR. All models were adjusted for study center, age, sex, baseline BMI, and smoking status. Data were missing for 94 serum ferritin and body iron values. AGP, ɑ1 acid glycoprotein; CRP, C-reactive protein; sTfR, soluble transferrin receptor.

FIGURE 6

The 1-y change in biomarkers of iron status, by quintile of change in serum selenium, in 1077 men and women aged 65–79 y. Values are means (error bars indicate 95% CIs), adjusted for study center, age, sex, baseline BMI, smoking status, and group status. Serum ferritin values were adjusted for CRP, AGP, and sTfR for AGP, using a regression correction. Body iron was calculated using the inflammation-adjusted values for ferritin and sTfR. P values are for trends calculated using an ANCOVA. AGP, ɑ1 acid glycoprotein; CRP, C-reactive protein; Q, quintile; sTfR, soluble transferrin receptor.