Predictors and Implications of Accelerated Cognitive Aging

Abstract

Aging is a major risk factor for both normal and pathological cognitive decline. However, individuals vary in their rate of age-related decline. We developed an easily interpretable composite measure of cognitive age, and related both the level of cognitive age and cognitive slope to sociodemographic, genetic, and disease indicators and examine its prediction of dementia transition. Using a sample of 19,594 participants from the Health and Retirement Study, cognitive age was derived from a set of performance tests administered at each wave. Our findings reveal different conclusions as they relate to levels versus slopes of cognitive age, with more pronounced differences by sex and race/ethnicity for absolute levels of cognitive decline rather than for rates of declines. We also find that both level and slope of cognitive age are inversely related to education, as well as increased for persons with APOE ε4 and/or diabetes. Finally, results show that the slope in cognitive age predicts subsequent dementia among non-demented older adults. Overall, our study suggests that this measure is applicable to cross-sectional and longitudinal studies on cognitive aging, decline, and dementia with the goal of better understanding individual differences in cognitive decline.

Keywords: APOE; Aging; Cognitive Decline; Dementia; Education; Polygenic Risk Score.

Figure 1:. Distributions and Definitions of Cognitive Age Level and Slope

Overall the difference in cognitive and chronological age was fairly normally distributed (Figure 1a), with HRS participants, on average, having cognitive ages equal to their chronological ages. Similarly, most participants’ cognitive age appeared to rise at the same rate as their chronological age, producing a slope equal to one for change in cognitive age over change in chronological age (figure 1b). However, some participants display accelerated cognitive aging rates (slopes greater than one), while others display decelerated cognitive aging rates (slopes less than one). In general, a slope of two suggests a person’s cognitive age is increasing twice as fast as his/her chronological age, while a slope of 0.5 suggests a person’s cognitive age is increasing at half the rate of his/her chronological aging (figure 1c).

Figure 2:. Trend in Cognitive Aging versus Chronological Aging.

Smoothed spline graphs were used to determine the overall linearity of the change in cognitive age as a function of the change in chronological age within the older HRS population. Even when allowing for up to 10 breakpoints, the trend appears to remained mostly linear.

Figure 3:. Age-Stratified Associations between Cognitive Age and Sociodemographic, Metabolic, and Genetic Factors

Associations between cognitive age and sex (figure 2a), race/ethnicity (figure 2c), underweight BMI (figure 2d), heart disease (figure 2e), and PRS (figure 2h) did not differ systematically by age. However, education appeared to exhibit a diminishing association with cognitive age in later life, suggesting the possibility of mortality selection (figure 2b)—under educated individuals with high cognitive ages are more likely to be removed from the population by mortality prior to reaching old age. Conversely, the associations with cognitive age for APOE ε4 (figure 2g) and diabetes (figure 2f), increase with age, suggesting that the rate of cognitive aging may differ as a function of APOE ε4 or diabetes status, creating a growing divergence in cognitive functioning over time. Finally, Obesity appears to have differential associations by age (figure 2d). For instance, in middle age it is associated with a higher cognitive age, compared to the cognitive ages of those with normal BMI, whereas at older ages, obese individuals appear to have lower cognitive ages than persons with normal BMI—suggesting that among older adults, a higher BMI is protective.