Cognition, reserve, and amyloid deposition in normal aging

Abstract

Objective: To determine whether amyloid deposition is associated with impaired neuropsychological (NP) performance and whether cognitive reserve (CR) modifies this association.

Methods: In 66 normal elderly controls and 17 patients with Alzheimer disease (AD), we related brain retention of Pittsburgh Compound B (PiB) to NP performance and evaluated the impact of CR using education and American National Adult Reading Test intelligence quotient as proposed proxies.

Results: We found in the combined sample of subjects that PiB retention in the precuneus was inversely related to NP performance, especially in tests of memory function, but also in tests of working memory, semantic processing, language, and visuospatial perception. CR significantly modified the relationship, such that at progressively higher levels of CR, increased amyloid deposition was less or not at all associated with poorer neuropsychological performance. In a subsample of normal controls, both the main effect of amyloid deposition of worse memory performance and the interaction with CR were replicated using a particularly challenging memory test.

Interpretation: Amyloid deposition is associated with lower cognitive performance both in AD patients and in the normal elderly, but the association is modified by CR, suggesting that CR may be protective against amyloid-related cognitive impairment.

FIGURE 1

Neuropsychological performance versus precuneus Pittsburgh Compound B (PiB) retention. In each panel, subjects are color-coded by tertile strata of increasing cognitive reserve (CR), expressed as residual American National Adult Reading Test (AMNART) intelligence quotient (IQ): low, medium, and high. Solid lines represent the ordinary least squares regression lines for each stratum. Note that data points shown are not adjusted for age or education, as in the regression analyses (see Table 2). (A) In the full sample of subjects (N = 83), neuropsychological (NP) performance represented by the canonical variate was inversely related to PiB retention, but the effect was attenuated at higher levels of IQ. (B) In the subset of PiB-positive subjects (defined as global mean cortical PiB distribution volume ratio [DVR] ≥ 1.15; n = 55), canonical variate NP performance was inversely related to PiB retention, but no interaction with CR was observed, that is, regression lines are nearly parallel. (C) In the subset of NC subjects (n = 66), the relation of canonical variate NP performance to PiB retention did not reach significance; instead, the significant interaction effect with CR resulted in a systematic splaying of the data according to CR, identified as strata of AMNART IQ. (D) In the further subset of NC subjects with data from the more challenging MCT (n = 34), both a significant main effect of PiB on NP performance and a significant interaction with CR were observed. NC-MCT = normal control Memory Capacity Test.