A combined DHA-rich fish oil and cocoa flavanols intervention does not improve cognition or brain structure in older adults with memory complaints: results from the CANN randomized, controlled parallel-design study

Abstract

Background: There is evidence that both omega-3 long-chain polyunsaturated fatty acids (PUFAs) (eicosapentaenoic acid [EPA] and docosahexaenoic acid [DHA]) and cocoa flavanols can improve cognitive performance in both healthy individuals and in those with memory complaints. However, their combined effect is unknown.

Objectives: To investigate the combined effect of EPA/DHA and cocoa flavanols (OM3FLAV) on cognitive performance and brain structures in older adults with memory complaints.

Methods: A randomized placebo-controlled trial of DHA-rich fish oil (providing 1.1 g/d DHA and 0.4 g/d EPA) and a flavanol-rich dark chocolate (providing 500 mg/d flavan-3-ols) was conducted in 259 older adults with either subjective cognitive impairment or mild cognitive impairment. Participants underwent assessment at baseline, 3 mo, and 12 mo. The primary outcome was the number of false-positives on a picture recognition task from the Cognitive Drug Research computerized assessment battery. Secondary outcomes included other cognition and mood outcomes, plasma lipids, brain-derived neurotrophic factor (BDNF), and glucose levels. A subset of 110 participants underwent structural neuroimaging at baseline and at 12 mo.

Results: 197 participants completed the study. The combined intervention had no significant effect on any cognitive outcomes, with the exception of reaction time variability (P = 0.007), alertness (P < 0.001), and executive function (P < 0.001), with a decline in function observed in the OM3FLAV group (118.6 [SD 25.3] at baseline versus 113.3 [SD 25.4] at 12 mo for executive function) relative to the control, and an associated decrease in cortical volume (P = 0.039). Compared with the control group, OM3FLAV increased plasma HDL, total cholesterol ratio (P < 0.001), and glucose (P = 0.008) and reduced TG concentrations (P < 0.001) by 3 mo, which were sustained to 12 mo, with no effect on BDNF. Changes in plasma EPA and DHA and urinary flavonoid metabolite concentrations confirmed compliance to the intervention.

Conclusions: These results suggest that cosupplementation with ω-3 PUFAs and cocoa flavanols for 12 mo does not improve cognitive outcomes in those with cognitive impairment. This trial was registered at clinicaltrials.gov as NCT02525198.

Keywords: aging; cognition; flavonoids; mild cognitive impairment; omega-3; polyphenols; subjective cognitive impairment.

FIGURE 1

CONSORT flowchart diagram. A total of N = 258 participants were randomly assigned to either a DHA-rich fish oil and cocoa flavanol mixture (OM3FLAV; n = 129) or a control product (n = 129).

FIGURE 2

Impact of 3-mo and 12-mo consumption of a DHA-rich fish oil and cocoa flavanol mixture (OM3FLAV; n = 104 at 3 mo and n = 95 at 12 mo) or a control product (n = 108 at 3 mo and n = 102 at 12 mo) on plasma fatty acid profiles and urinary excretion of a flavanol metabolite. (A) Non-esterified AA (NEFA AA); (B) Non-esterified eicosapentaenoic acid (NEFA EPA); (C) Non-esterified docosahexaenoic acid (NEFA DHA); (D) Hydroxyphenyl-γ-valearolactone sulfate. Data are presented as floating bars (min-max) with the horizontal line indicating the mean. Bar colors are as follows: blue (baseline), green (3 mo), and red (12 mo).

FIGURE 3

Picture recognition new stimuli accuracy (%) at baseline and following 3 mo or 12 mo of a DHA-rich fish oil and cocoa flavanol mixture (OM3FLAV; n = 104 at 3 mo and n = 95 at 12 mo) or a control product (n = 108 at 3 mo and n = 102 at 12 mo). Data are presented as floating bars (min-max) with the horizontal line indicating the mean. Bar colors are as follows: blue (baseline), green (3 mo), and red (12 mo).

FIGURE 4

Structural MRI assessment of (A) hippocampal volume; (B) cortical volume; (C) cortical white matter volume; and (D) ventricular volume following 12-mo consumption of a DHA-rich fish oil and cocoa flavanol mixture (OM3FLAV; n = 48) or a control product (n = 62). Data are presented as floating bars (min-max) with the horizontal line indicating the mean. Bar colors are as follows: blue (baseline) and red (12 mo).