Investigating possible causal effects of externalizing behaviors on tobacco initiation: A Mendelian randomization analysis

Abstract

Observational studies suggest childhood externalizing disorders are associated with increased smoking and earlier initiation. However, causality cannot be inferred from observational data alone. The current study uses two-sample MR to examine the causal relationship between externalizing behaviors and tobacco use. Single nucleotide polymorphisms (SNPs) associated with aggression were obtained from the Early Life Epidemiology Consortium (mean age 8), ADHD from the Integrative Psychiatric Research and Psychiatric Genomics Consortiums (age range 6-18), and tobacco initiation and age of onset from the Tobacco and Genetics Consortium. SNPs were combined using the inverse variance weighted approach, weighted median approach, and MR-Egger regression. There was no clear evidence of an effect of aggression on tobacco initiation or age of onset for childhood aggression (initiation: β -0.002, 95% CI -0.005, 0.001, P = 0.286; age: β -0.001 95% CI -0.002, 0.000, P = 0.310) or adolescent aggression (initiation: β -0.001, 95% CI -0.006, 0.003, P = 0.610; age: β 0.000, 95% CI 0.000, 0.001, P = 0.183)]. However, there was some evidence of an association of ADHD on tobacco initiation (OR 1.23, 95% CI 1.10, 1.35, P = 0.016), although no clear evidence of an effect of ADHD on age of onset (OR = 1.022, 95% CI 0.992, 1.052, P = 0.215). Our results provide some evidence that genetic risk of childhood ADHD is causally related to increased risk of tobacco initiation; however, the causal estimate is relatively small. We found no clear evidence that genetic risk of childhood aggression is causally related to the risk of tobacco initiation or age of onset.

Keywords: Externalizing behavior; Mendelian randomization; Tobacco use.