Associations of Brain Structure and Neuropsychological Function With Artificial Intelligence Estimates of Biological Vascular Age.

<h4>Background</h4>Accelerated vascular aging, assessed as artificial intelligence-based vascular age (AIVA), is associated with small vessel disease that may impact brain structure and neuropsychological function.<h4>Methods</h4>In a cross-section of Framingham Heart Study participants, AIVA was estimated using a validated convolutional neural network trained to predict carotid-femoral pulse wave velocity from a normalized pressure waveform. Brain structure was assessed using magnetic resonance imaging with diffusion tensor imaging, and neuropsychological function was assessed using a standardized test battery. Analyses included magnetic resonance imaging (N=2313) and neuropsychological (N=3001) samples. We used multivariable linear and logistic regression to relate AIVA to brain structural and neuropsychological functional measures.<h4>Results</h4>The mean±SD age across participants was 62±11 years; 56% were women. In multivariable models, higher AIVA was associated with worse markers of cerebral small vessel disease (mean white matter free water: <i>β</i> [per SD], 0.09 [95% CI, 0.04-0.14]; <i>P</i><0.001; peak width of skeletonized mean diffusivity: <i>β</i>, 0.05 [95% CI, 0.00-0.10]; <i>P</i>=0.045; white matter hyperintensity volume: <i>β</i>, 0.08 [95% CI, 0.03-0.12]; <i>P</i><0.001) and higher odds of cerebrovascular injury (presence of extensive white matter hyperintensities: odds ratio [per SD], 1.22 [95% CI, 1.02-1.47]; <i>P</i>=0.03; presence of brain infarcts: odds ratio, 1.44 [95% CI, 1.02-2.04]; <i>P</i>=0.04). In addition, higher AIVA was associated with worse performance on Trails B-A (<i>β</i>, -0.05 [95% CI, -0.10 to -0.01]; <i>P</i>=0.03), similarities (<i>β</i>, -0.06 [95% CI, -0.11 to -0.01]; <i>P</i>=0.02), and global cognition (<i>β</i>, <i>-</i>0.07 [95% CI, -0.12 to -0.03]; <i>P</i>=0.002) and higher odds of prevalent depressive symptoms (odds ratio, 1.24 [95% CI, 1.08-1.41]; <i>P</i>=0.002) and high Center for Epidemiologic Studies Depression Scale score (odds ratio, 1.20 [95% CI, 1.00-1.44]; <i>P</i>=0.047). Vascular brain injury markers partially mediated the associations of AIVA with global cognition score and presence of depressive symptoms.<h4>Conclusions</h4>Peripheral pressure waveform AIVA may be a novel, noninvasive indicator of subclinical vascular brain injury and neuropsychological function.