Abnormal P-Wave Axis and Ischemic Stroke: The ARIC Study (Atherosclerosis Risk In Communities)

Abstract

Background and purpose: Abnormal P-wave axis (aPWA) has been linked to incident atrial fibrillation and mortality; however, the relationship between aPWA and stroke has not been reported. We hypothesized that aPWA is associated with ischemic stroke independent of atrial fibrillation and other stroke risk factors and tested our hypothesis in the ARIC study (Atherosclerosis Risk In Communities), a community-based prospective cohort study.

Methods: We included 15 102 participants (aged 54.2±5.7 years; 55.2% women; 26.5% blacks) who attended the baseline examination (1987-1989) and without prevalent stroke. We defined aPWA as any value outside 0 to 75° using 12-lead ECGs obtained during study visits. Each case of incident ischemic stroke was classified in accordance with criteria from the National Survey of Stroke by a computer algorithm and adjudicated by physician review. Multivariable Cox regression was used to estimate hazard ratios and 95% confidence intervals for the association of aPWA with stroke.

Results: During a mean follow-up of 20.2 years, there were 657 incident ischemic stroke cases. aPWA was independently associated with a 1.50-fold (95% confidence interval, 1.22-1.85) increased risk of ischemic stroke in the multivariable model that included atrial fibrillation. When subtyped, aPWA was associated with a 2.04-fold (95% confidence interval, 1.42-2.95) increased risk of cardioembolic stroke and a 1.32-fold (95% confidence interval, 1.03-1.71) increased risk of thrombotic stroke.

Conclusions: aPWA is independently associated with ischemic stroke. This association seems to be stronger for cardioembolic strokes. Collectively, our findings suggest that alterations in atrial electric activation may predispose to cardiac thromboembolism independent of atrial fibrillation.

Keywords: arrhythmias, cardiac; atrial fibrillation; electrophysiology; stroke.

Figure 1

Stroke classification scheme in the Atherosclerosis Risk in Communities Study. Definite ischemic strokes comprised of all definite cardioembolic strokes and all definite thrombotic strokes. Definite thrombotic strokes were then classified as lacunar and non-lacunar strokes.

Figure 2

Association between baseline P-wave axis and definite ischemic stroke modeled using an unadjusted restricted cubic spine. Data presented as hazard ratios (solid line) and 95% confidence intervals (shaded area).