Estimating the causal influence of body mass index on risk of Parkinson disease: A Mendelian randomisation study

This is one of the first true causal studies in Parkinson's disease... it uses a method called Mendelian Randomisation to estimate the effect that body mass index has on Parkinson's. Many association studies are flawed because of reverse causation (Parkinson's affects BMI rather than the other way around) or confounding (there is another/other factor(s) associated with both BMI and Parkinson's that explain the observed association). Mendelian Randomisation ought to mitigate the risk of reverse causation and confounding, and therefore the association here should represent a true causal one... I am very proud of this work which represents a large collaborative effort by the International Parkinson's Disease Genomics Consortium and colleagues at Bristol University...

PLoS Med. 2017 Jun 13;14(6):e1002314. doi: 10.1371/journal.pmed.1002314. eCollection 2017 Jun. Noyce AJ, Kia DA, Hemani G, Nicolas A, Price TR, De Pablo-Fernandez E, Haycock PC, Lewis PA, Foltynie T, Davey Smith G; International Parkinson Disease Genomics Consortium, Schrag A, Lees AJ, Hardy J, Singleton A, Nalls MA, Pearce N, Lawlor DA, Wood NW.

http://journals.plos.org/plosmedicine/article?id=10.1371/journal.pmed.1002314

BACKGROUND: Both positive and negative associations between higher body mass index (BMI) and Parkinson disease (PD) have been reported in observational studies, but it has been difficult to establish causality because of the possibility of residual confounding or reverse causation. To our knowledge, Mendelian randomisation (MR)-the use of genetic instrumental variables (IVs) to explore causal effects-has not previously been used to test the effect of BMI on PD.

METHODS AND FINDINGS: Two-sample MR was undertaken using genome-wide association (GWA) study data. The associations between the genetic instruments and BMI were obtained from the GIANT consortium and consisted of the per-allele difference in mean BMI for 77 independent variants that reached genome-wide significance. The per-allele difference in log-odds of PD for each of these variants was estimated from a recent meta-analysis, which included 13,708 cases of PD and 95,282 controls. The inverse-variance weighted method was used to estimate a pooled odds ratio (OR) for the effect of a 5-kg/m2 higher BMI on PD. Evidence of directional pleiotropy averaged across all variants was sought using MR-Egger regression. Frailty simulations were used to assess whether causal associations were affected by mortality selection. A combined genetic IV expected to confer a lifetime exposure of 5-kg/m2 higher BMI was associated with a lower risk of PD (OR 0.82, 95% CI 0.69-0.98). MR-Egger regression gave similar results, suggesting that directional pleiotropy was unlikely to be biasing the result (intercept 0.002; p = 0.654). However, the apparent protective influence of higher BMI could be at least partially induced by survival bias in the PD GWA study, as demonstrated by frailty simulations. Other important limitations of this application of MR include the inability to analyse non-linear associations, to undertake subgroup analyses, and to gain mechanistic insights.

CONCLUSIONS: In this large study using two-sample MR, we found that variants known to influence BMI had effects on PD in a manner consistent with higher BMI leading to lower risk of PD. The mechanism underlying this apparent protective effect warrants further study.