Background: Systolic or diastolic blood pressure (BP) variability is associated with an increased risk of cardiovascular events. We assessed whether BP variability measured by mean arterial pressure (MAP) was associated with increased risk of heart failure (HF) and death in individuals with or without hypertension.Methods: We evaluated 9,305 Atherosclerosis Risk in Communities (ARIC) study participants with or without hypertension and calculated BP variability based on MAP values from visit 1 to 4 [expressed as standard deviation (SD), average real variability (ARV), coefficient of variation (CV), and variability independent of the mean (VIM)]. Multivariate-adjusted Cox regression model and restricted cubic spline curve were used to evaluate the associations of MAP variability with all-cause mortality and HF.Results: During a median follow-up of 16.8 years, 1,511 had an HF event and 2,903 died. Individuals in the highest quartile of VIM were both associated with a 21% higher risk of all-cause mortality [hazard ratio (HR), 1.21; 95% CI, 1.09–1.35] and HF (HR, 1.21; 95% CI, 1.04–1.39) compared with the lowest quartile of VIM. Cubic spline curves reveal that the risk of deaths and HF increased with MAP variability when it reached a higher level. Results were similar in individuals with normotension (all-cause mortality: HR, 1.30; 95% CI, 1.09–1.55; HF, HR, 1.49; 95% CI, 1.12–1.98).Conclusions: In individuals with or without hypertension, greater visit-to-visit MAP variability was associated with a higher risk of all-cause mortality and HF, indicating that the BP variability assessed by MAP might be a potential risk factor for HF and death.