Pulse Pressure Impairs Cognition via White Matter Disruption

Abstract

Background: In older adults, elevated pulse pressure predicts cognitive decline, independent of overall blood pressure. It is proposed to compromise cerebrovascular integrity, potentially leading to brain damage, though the underlying mechanisms remain unclear. We hypothesized that pulse pressure affects cognition by disrupting white matter microstructure, and that it does so independently of other cardiovascular risk factors.

Methods: Latent indices of pulse pressure, overall blood pressure, and heart rate variability were estimated in a cross-sectional, population-based cohort (n=708, aged 18-88 years). An indicator of white matter microstructure was derived from diffusion-weighted imaging, termed the peak width of skeletonized mean diffusivity (PSMD). Cognitive function was assessed using measures of processing speed.

Results: In robust regression, pulse pressure was significantly associated with PSMD, with PSMD also being associated with processing speed. Thus, higher pulse pressure was associated with greater white matter disruption, which in turn was associated with slower processing. This motivated testing whether PSMD mediates the effects of pulse pressure on processing speed using structural equation models. PSMD mediated this effect, accounting for 72% of the effect after adjusting for age, and remained significant after adjusting for other cardiovascular factors. We then expanded the model to show that vascular-related changes in processing speed also drive changes in higher cognitive functions.

Conclusions: High pulse pressure disrupts the microstructural integrity of white matter in the brain, leading to slower processing speed. We propose that better management of pulse pressure could help to preserve white matter integrity and reduce cognitive decline in later life.

Keywords: aged; blood pressure; cognition; heart rate; risk factors.

Figure 1.

A schematic representation of the main stages in the data processing and analysis pipeline, to investigate whether peak width of skeletonized mean diffusivity (PSMD), an indicator of white matter disruption, mediated the relationship between pulse pressure (systolic-diastolic) and cognitive decline, in the Cam-CAN data set (n ≤708). This includes regression models (middle) and structural equation models (bottom) with simple mediation models (1A–C) informing subsequent models (2A–B and 3A–B).For simplicity, the schematic does not show the quadratic latent vascular factors. Squares represent manifest variables and circles represent latent variables. Symbols: µ, mean; σ, SD. BP indicates blood pressure; BMI, body mass index; FA, fractional anisotropy, Heart R, heart rate; HRV HF, heart rate variability high frequency; HRV LF, heart rate variability low frequency; MD, mean diffusivity; PP, pulse pressure; and SSBP, steady-state blood pressure.

Figure 2.

Structural equation model 1B (n=570) with standardized betas. Dashed lines represent insignificant results. Squares represent manifest variables and circles represent latent variables. CIs=95% bootstrapped CIs. PP indicates pulse pressure; and PSMD, peak width of skeletonized mean diffusivity.

Figure 3.

Structural equation model 3B (n=564). Shows standardized betas. Dashed lines represent insignificant results. Squares represent manifest variables and circles represent latent variables. PP indicates pulse pressure; and PSMD, peak width of skeletonized mean diffusivity.