Unhealthy Behaviours and Risk of Parkinson's Disease: A Mendelian Randomisation Study

Abstract

Background: Tobacco smoking and alcohol intake have been identified in observational studies as potentially protective factors against developing Parkinson's disease (PD); the impact of body mass index (BMI) on PD risk is debated. Whether such epidemiological associations are causal remains unclear. Mendelian randomsation (MR) uses genetic variants to explore the effects of exposures on outcomes; potentially reducing bias from residual confounding and reverse causation.

Objective: Using MR, we examined relationships between PD risk and three unhealthy behaviours: tobacco smoking, alcohol intake, and higher BMI.

Methods: 19,924 PD cases and 2,413,087 controls were included in the analysis. We performed genome-wide association studies to identify single nucleotide polymorphisms associated with tobacco smoking, alcohol intake, and BMI. MR analysis of the relationship between each exposure and PD was undertaken using a split-sample design.

Results: Ever-smoking reduced the risk of PD (OR 0.955; 95%confidence interval [CI] 0.921-0.991; p = 0.013). Higher daily alcohol intake increased the risk of PD (OR 1.125, 95%CI 1.025-1.235; p = 0.013) and a 1 kg/m2 higher BMI reduced the risk of PD (OR 0.988, 95%CI 0.979-0.997; p = 0.008). Sensitivity analyses did not suggest bias from horizontal pleiotropy or invalid instruments.

Conclusion: Using split-sample MR in over 2.4 million participants, we observed a protective effect of smoking on risk of PD. In contrast to observational data, alcohol consumption appeared to increase the risk of PD. Higher BMI had a protective effect on PD, but the effect was small.

Keywords: 23andMe; BMI; Parkinson’s disease; alcohol; smoking.

Fig. 1

Forest plot of Mendelian randomisation causal association estimates between risk of Parkinson’s disease and unhealthy behaviours derived from meta-analysis of the 23andMe and IPDGC datasets. The pooled odds ratio (OR), derived from meta-analysis of the inverse variance weighted estimates, and 95%confidence intervals are shown. For smoking, the unit of exposure is never versus ever smoking. For alcohol, the unit of exposure is 1-group difference in daily alcohol intake. For BMI, the unit of exposure is 1 kg/m². OR, odds ratio; PD, Parkinson’s disease.

Fig. 2

Funnel plots of individual variant effects for the smoking instrument (from cohort 1 (A) and cohort 2 (B)) plotted against the inverse of their standard error.

Fig. 3

Funnel plots of individual variant effects for the alcohol instrument (from cohort 1 (A) and cohort 2 (B)) plotted against the inverse of their standard error.

Fig. 4

Funnel plots of individual variant effects for the BMI instrument (from cohort 1 (A) and cohort 2 (B)) plotted against the inverse of their standard error.