Synergistic and Non-synergistic Associations for Cigarette Smoking and Non-tobacco Risk Factors for Cardiovascular Disease Incidence in the Atherosclerosis Risk In Communities (ARIC) Study

Abstract

Introduction: Cigarette smoking, various metabolic and lipid-related factors and hypertension are well-recognized cardiovascular disease (CVD) risk factors. Since smoking affects many of these factors, use of a single imprecise smoking metric, for example, ever or never smoked, may allow residual confounding and explain inconsistencies in current assessments of interactions.

Methods: Using a comprehensive model in pack-years and cigarettes/day for the complex smoking-related relative risk (RR) of CVD to reduce residual confounding, we evaluated interactions with non-tobacco risk factors, including additive (non-synergistic) and multiplicative (synergistic) forms. Data were from the prospective Atherosclerosis Risk in Communities (ARIC) Study from four areas of the United States recruited in 1987-1989 with follow-up through 2008. Analyses included 14 127 participants, 207 693 person-years and 2857 CVD events.

Results: Analyses revealed distinct interactions with smoking: including statistical consistency with additive (body mass index [BMI], waist to hip ratio [WHR], diabetes mellitus [DM], glucose, insulin, high density lipoproteins [HDL] and HDL(2)); and multiplicative (hypertension, total cholesterol [TC], low density lipoproteins [LDLs], apolipoprotein B [apoB], TC to HDL ratio and HDL(3)) associations, as well as indeterminate (apolipoprotein A-I [apoA-I] and triglycerides) associations.

Conclusions: The forms of the interactions were revealing but require confirmation. Improved understanding of joint associations may help clarify the public health burden of smoking for CVD, links between etiologic factors and biological mechanisms, and the consequences of joint exposures, whereby synergistic associations highlight joint effects and non-synergistic associations suggest distinct contributions.

Implications: Joint associations for cigarette smoking and non-tobacco risk factors were distinct, revealing synergistic/multiplicative (hypertension, TC, LDL, apoB, TC/HDL, HDL(3)), non-synergistic/additive (BMI, WHR, DM, glucose, insulin, HDL, HDL(2)) and indeterminate (apoA-I and TRIG) associations. If confirmed, these results may help better define the public health burden of smoking on CVD risk and identify links between etiologic factors and biologic mechanisms, where synergistic associations highlight joint impacts and non-synergistic associations suggest distinct contributions from each factor.

Figure 1.

Joint relative risk (RR) of cardiovascular disease for categories of pack-years (solid symbol) and cigarettes/day relative to never-smokers and fitted linear models (solid line) (upper panels). Lower panel shows estimated excess relative risk per pack-year (ERR/PKY) for cigarettes/day categories (solid symbol), with <20 further split into 1–4, 5–9, 10–19 cigarettes/day, and fitted models for continuous pack-years and cigarettes/day (n) with pointwise 95% confidence interval (CI) (solid line with shaded area for two-parameter model, and dash line with light dash line for 3-parameter model) (Supplementary Material).