Higher dietary inflammation is associated with increased odds of depression independent of Framingham Risk Score in the National Health and Nutrition Examination Survey

Abstract

Cardiovascular disease (CVD) may increase depression risk. Risk for future CVD, which can be estimated by the Framingham Risk Score (FRS), and depression risk are both linked to systemic inflammation. Dietary consumption of proinflammatory food can be measured using the Dietary Inflammatory Index (DII) score. We examined the potential impact of DII on depression and whether this effect is independent of FRS. We hypothesized that (1) both FRS and DII would be associated with depression (Patient Health Questionnaire-9 ≥ 10) and (2) associations between DII and depressive symptoms (continuous) would be mediated by FRS. Data were included from adults without CVD who were participants of the 2007-2012 National Health and Nutrition Examination Survey (n = 11 624). Using logistic regression, we tested cross-sectional associations of FRS, DII (adjusting for FRS), and joint effects of FRS and DII with depression. Finally, using the Sobel method, we tested whether FRS mediates the relationship between DII and depressive symptoms. Individuals with FRS or DII scores in the top 2 quartiles had higher odds of depressive symptoms than those in the bottom quartile. The association of DII with depressive symptoms remained after FRS adjustment. The joint effects of elevated DII and FRS were additive. There was no evidence for mediation by FRS between DII and depressive symptoms. Thus, higher DII remained associated with increased odds of depressive symptoms net CVD risk. Collectively, the joint effects of CVD risk and DII indicate that a proinflammatory diet could add to risk for depressive symptoms even in those with a high FRS.

Keywords: Cardiovascular disease risk; Depression; Dietary inflammation; Systemic inflammation.

Figure 1

Selection of study sample from 2007–2012 NHANES data for this analysis. Adults age 18 and older without CVD diagnosis (history of heart attack, angina, stroke, CHD) and with non-missing data on depression, daily food/nutrient intake, CVD risk factors and other related covariates were included in this analysis. Participants with extreme values (<500 or ≥ 5000 kcal) of energy intake on the 24-hour dietary recall interview were also excluded from the study. Leaving the final n=11,624 before weighting (weighted n in thousands: total n=159,079; current depression n=11,480; no current depression n= 147,599).

Figure 2

Current Depression by Framingham Risk Score Quartiles. Displays the percent of those with current depression (orange) and the percent of those without current depression (PHQ-9 ≥ 10) (blue) by each quartile of the FRS. Quartiles of FRS were defined using the total population. Those with current depression were more likely to be in higher quartiles of the FRS (p<0.0001 for trend). 95% Confidence Limits are presented on bars. *p<0.05

Figure 3

Current depression by Dietary Inflammation Index Score Quartiles. Displays the percent of those with current depression (orange) and the percent of those without current depression (PHQ-9 ≥ 10) (blue) by each quartile of the DII score. Quartiles of DII were defined using the total population. Those with current depression were more likely to be in higher quartiles of the DII score (p<0.0001 for trend). 95% Confidence Limits are presented on bars. *p<0.05

Figure 4

Multivariate Analysis for Odds of Depression. All multivariate associations were simultaneously adjusted for race/ethnicity, education, annual household income, cholesterol-lowering medication, history of cancer, body mass index, and physical activity. Models of DII score were additionally adjusted for age, gender, current smoker, dietary supplements use, and total caloric intake. Elevated FRS and DII score were defined as above the median score.

Figure 5

Mediation analysis examining if FRS statistically mediates the relationship between DII and depression symptomology. Path diagrams for 1) the total effect of the DII on depression symptomology (c) and 2) the indirect effect of DII on depression symptomology through the mediator FRS. * denotes p<0.05