Is there a dose-response relation of dietary glycemic load to risk of type 2 diabetes? Meta-analysis of prospective cohort studies

Abstract

Background: Although much is known about the association between dietary glycemic load (GL) and type 2 diabetes (T2D), prospective cohort studies have not consistently shown a positive dose-response relation.

Objective: We performed a comprehensive examination of evidence on the dose response that links GL to T2D and sources of heterogeneity among all prospective cohort studies on healthy adults available in the literature.

Design: We conducted a systematic review of all prospective cohort studies and meta-analyses to quantify the GL-T2D relation both without and with adjustment for covariates.

Results: Among 24 prospective cohort studies identified by August 2012, the GL ranged from ∼60 to ∼280 g per daily intake of 2000 kcal (8.4 MJ). In a fully adjusted meta-analysis model, the GL was positively associated with RR of T2D of 1.45 (95% CI: 1.31, 1.61) for a 100-g increment in GL (P < 0.001; n = 24 studies; 7.5 million person-years of follow-up). Sex (P = 0.03), dietary instrument validity (P < 0.001), and ethnicity (European American compared with other; P = 0.04) together explained 97% of the heterogeneity among studies. After adjustment for heterogeneities, we used both funnel and trim-and-fill analyses to identify a negligible publication bias. Multiple influence, cumulative, and forecast analyses indicated that the GL-T2D relation tended to have reached stability and to have been underestimated. The relation was apparent at all doses of GL investigated, although it was statistically significant only at >95 g GL/2000 kcal.

Conclusion: After we accounted for several sources of heterogeneity, findings from prospective cohort studies that related the GL to T2D appear robust and consistently indicate strong and significantly lower T2D risk in persons who consume lower-GL diets. This review was registered at http://www.crd.york.ac.uk/PROSPERO as CRD42011001810.

FIGURE 1.

Summary of the study methodology, processes of review, and outcomes of inclusion and exclusion criteria. Reasons for exclusion are detailed online (see “Supplemental data” in the online issue). *Data from 2 reports from the same study at different times (16, 30) were combined before meta-analysis. Literature searches were conducted in week 3 of August 2012. MEDLINE and EMBASE were searched through PROQUEST (http://search.proquest.com) via the Royal Society of Medicine (http://www.rsm.ac.uk; see Search Strategies under “Supplemental data” for details). n_r, number of reports; k, number of studies.

FIGURE 2.

Meta-analysis without covariates that relates RR of type 2 diabetes to GL by sex group. Study means are denoted by gray boxes (larger points have greater weight). Horizontal lines denote 95% CIs. Arrowheads indicate truncations. Diamonds show combined-study means and corresponding 95% CIs. The scale is logarithmic with RR and 95% CIs shown untransformed. Individual studies are identified by first author, date, and citation. P values were calculated by using the z test for RR and the Q test for I². *Data from the same study reported at different follow-up durations (20 and 26 y) (16, 30) were combined before meta-analysis. AA, African American; CA, Caucasian American; EA, European American; GL, glycemic load; I², variance among studies as a percentage of the total variance; JA, Japanese American; LCI, lower CI; NH, Native Hawaiian; ref., reference; UCI, upper CI; %WT, weight based on random effects.

FIGURE 3.

Range over which GL and RR of type 2 diabetes are related. Data points are bubbles and show RRs per 100 g GL for study quantiles from the lowest quantile (Q₁) to each higher quantile (Q_n) after adjustment for the 4 hypothesized covariates. Bubbles increase in size with increase in weight of the data point. Curvilinearity of the trend and 95% CIs for the adjusted RR per 100 g GL was permitted by fitting a one-step pooled cubic-spline metaregression with 3 equally dispersed knots to the lnRR. Larger bubbles have greater precision and weight. The inset shows the corresponding funnel plot for model residuals. GL, glycemic load.