Nordic dietary patterns and cardiometabolic outcomes: a systematic review and meta-analysis of prospective cohort studies and randomised controlled trials

Abstract

Aims/hypothesis: Nordic dietary patterns that are high in healthy traditional Nordic foods may have a role in the prevention and management of diabetes. To inform the update of the EASD clinical practice guidelines for nutrition therapy, we conducted a systematic review and meta-analysis of Nordic dietary patterns and cardiometabolic outcomes.

Methods: We searched MEDLINE, EMBASE and The Cochrane Library from inception to 9 March 2021. We included prospective cohort studies and RCTs with a follow-up of ≥1 year and ≥3 weeks, respectively. Two independent reviewers extracted relevant data and assessed the risk of bias (Newcastle-Ottawa Scale and Cochrane risk of bias tool). The primary outcome was total CVD incidence in the prospective cohort studies and LDL-cholesterol in the RCTs. Secondary outcomes in the prospective cohort studies were CVD mortality, CHD incidence and mortality, stroke incidence and mortality, and type 2 diabetes incidence; in the RCTs, secondary outcomes were other established lipid targets (non-HDL-cholesterol, apolipoprotein B, HDL-cholesterol, triglycerides), markers of glycaemic control (HbA_1c, fasting glucose, fasting insulin), adiposity (body weight, BMI, waist circumference) and inflammation (C-reactive protein), and blood pressure (systolic and diastolic blood pressure). The Grading of Recommendations, Assessment, Development and Evaluation (GRADE) approach was used to assess the certainty of the evidence.

Results: We included 15 unique prospective cohort studies (n=1,057,176, with 41,708 cardiovascular events and 13,121 diabetes cases) of people with diabetes for the assessment of cardiovascular outcomes or people without diabetes for the assessment of diabetes incidence, and six RCTs (n=717) in people with one or more risk factor for diabetes. In the prospective cohort studies, higher adherence to Nordic dietary patterns was associated with 'small important' reductions in the primary outcome, total CVD incidence (RR for highest vs lowest adherence: 0.93 [95% CI 0.88, 0.99], p=0.01; substantial heterogeneity: I²=88%, p_Q<0.001), and similar or greater reductions in the secondary outcomes of CVD mortality and incidence of CHD, stroke and type 2 diabetes (p<0.05). Inverse dose-response gradients were seen for total CVD incidence, CVD mortality and incidence of CHD, stroke and type 2 diabetes (p<0.05). No studies assessed CHD or stroke mortality. In the RCTs, there were small important reductions in LDL-cholesterol (mean difference [MD] -0.26 mmol/l [95% CI -0.52, -0.00], p_MD=0.05; substantial heterogeneity: I²=89%, p_Q<0.01), and 'small important' or greater reductions in the secondary outcomes of non-HDL-cholesterol, apolipoprotein B, insulin, body weight, BMI and systolic blood pressure (p<0.05). For the other outcomes there were 'trivial' reductions or no effect. The certainty of the evidence was low for total CVD incidence and LDL-cholesterol; moderate to high for CVD mortality, established lipid targets, adiposity markers, glycaemic control, blood pressure and inflammation; and low for all other outcomes, with evidence being downgraded mainly because of imprecision and inconsistency.

Conclusions/interpretation: Adherence to Nordic dietary patterns is associated with generally small important reductions in the risk of major CVD outcomes and diabetes, which are supported by similar reductions in LDL-cholesterol and other intermediate cardiometabolic risk factors. The available evidence provides a generally good indication of the likely benefits of Nordic dietary patterns in people with or at risk for diabetes.

Registration: ClinicalTrials.gov NCT04094194.

Funding: Diabetes and Nutrition Study Group of the EASD Clinical Practice.

Keywords: Cardiovascular disease; Meta-analysis; Nordic diet; Prospective cohort; Randomised controlled trial; Systematic review.

Fig. 1

PRISMA flowchart showing the literature search

Fig. 2

Summary plot of the association between Nordic dietary patterns and CVD, CHD, stroke and type 2 diabetes incidence and CVD mortality in prospective cohort studies. Pooled risk estimates are represented by the orange circles. The p values are for generic inverse variance random-effects models. Between-study heterogeneity was assessed using the Cochran Q statistic, where p<0.10 is considered statistically significant, and quantified by the I² statistic, where I²≥50% is considered evidence of substantial heterogeneity [37]. Evidence from prospective cohort studies is rated as being of low certainty according to the GRADE approach and can be downgraded in five domains and upgraded in three domains. The filled black squares indicate where outcomes were downgraded and/or upgraded

Fig. 3

Dose–response relation between the Nordic diet score and (a) incidence of CVD (RR_{per-diet-score} 0.98 [95% CI 0.97, 0.99], p_linear<0.001, p_{departure-from-linearity}=0.60), (b) CVD mortality (RR_{per-diet-score} 0.94 [95% CI 0.93, 0.96], p_linear<0.001, p_{departure-from-linearity}=0.11), (c) incidence of CHD (RR_{per-diet-score} 0.98 [95% CI 0.96, 0.99], p_linear<0.001, p_{departure-from-linearity}=0.13), (d) incidence of stroke (RR_{per-diet-score} 0.97 [95% CI 0.95, 0.99], p_linear<0.001, p_{departure-from-linearity}=0.97) and (e) incidence of type 2 diabetes (RR_{per-diet-score} 0.97 [95% CI 0.95, 0.99], p_linear<0.001, p_{departure-from-linearity}=1.00). The red lines represent the linear models and the black lines represent the non-linear models. The dotted lines represent the 95% CIs for the non-linear models

Fig. 4

Summary plot of the effect of Nordic dietary patterns on cardiometabolic risk factors in RCTs. Data are expressed as weighted MDs with 95% CIs using the generic inverse variance method modelled by random effects ( five trials available) or fixed effects (fewer than five trials available). To allow the pooled effect estimates for each endpoint to be displayed on the same axis, MDs were transformed to standardised mean differences (SMDs). The pseudo 95% CI for each transformed SMD was derived directly from the original MD and 95% CI. Between-study heterogeneity was assessed by the Cochran Q statistic, where p<0.10 is considered statistically significant, and quantified by the I² statistic, where I²≥50% is considered evidence of substantial heterogeneity [61]. Evidence from RCTs is rated as being of high certainty according to the GRADE approach and can be downgraded in five domains. The filled black squares indicate where outcomes were downgraded. ^aAlthough all studies were conducted in Nordic countries and in those who were overweight or obese, we did not downgrade the evidence in this domain as there is no biological reason why the results would differ in other populations. ^bUnable to assess publication bias because of fewer than ten studies per outcome. ^cBecause of the difference in directionality of HDL-cholesterol compared with the other outcomes with regard to the signal for benefit or harm, the signs for the MD and SMD were changed. To convert total cholesterol, LDL-cholesterol and HDL-cholesterol to mg/dl, multiply by 38.67; to convert TG to mg/dl, multiply by 88.57; to convert blood glucose to mg/dl, multiply by 18.02; to convert CRP to mg/l, multiply by 0.105. NA, not available