Association Between Cannabis Use and Brain Structures: A Mendelian Randomization Study

Background Observational studies suggested that cannabis use was associated with alternation of brain structures; however, as subjected to confounding factors, they were difficult to make causal inferences and direction determinations. In this study, a two-sample Mendelian randomization (MR) analysis was employed to examine the potential causal association between cannabis use and brain structures. Methods The genome-wide association studies (GWAS) data for lifetime cannabis use (LCU), cannabis use disorder (CUD), and brain cortical and subcortical structures were utilized in this study. Cortical structures were divided into 34 distinct gyral-defined regions with surface area (SA) and thickness (TH) measured. Subcortical structures encompassed volumes from seven specified regions. The primary estimator used in our analysis was inverse-variance weighted (IVW), complemented by MR-Egger and weighted median methods to enhance the robustness of the results. The Cochran's Q test, funnel plots, and MR-Egger intercept tests were used to detect heterogeneity and pleiotropy. Results No causal relationship was detected between LCU and global cortical SA or TH. However, at the regional cortex level, LCU was associated with decreased TH in the fusiform ((3 (3 =-0.0168 mm, SE = 0.00581, P = 0.0039) and lateral occipital ((3 (3 =-0.0141 mm, SE = 0.00531, P = 0.0079) regions, while increasing TH in the postcentral region ((3 (3 = 0.0093 mm, SE = 0.00445, P = 0.0374). At the subcortical level, LCU was found to increase the brainstem volume ((3 (3 = 0.224 mm3, 3 , SE = 0.09, P = 0.0128). CUD did not show any causal association with brain structure at either cortical or subcortical levels. Nonetheless, after applying multiple comparison corrections, the P values for the MR analysis of causal relationships between cannabis use and these brain structures did not meet the significance threshold. Conclusion The evidence for cannabis use causally influencing brain structures is insufficient.