Structural MRI Predictors of Late-Life Cognition Differ Across African Americans, Hispanics, and Whites

Background: Structural magnetic resonance imaging (MRI) provides key biomarkers to predict onset and track progression of Alzheimer's disease (AD). However, most published reports of relationships between MRI variables and cognition in older adults include racially, ethnically, and socioeconomically homogenous samples. Racial/ethnic differences in MRI variables and cognitive performance, as well as health, socioeconomic status, and psychological factors, raise the possibility that brain-behavior relationships may be stronger or weaker in different groups. The current study tested whether MRI predictors of cognition differ in African Americans and Hispanics, compared with non-Hispanic Whites. Methods: Participants were 638 non-demented older adults (29% non-Hispanic White, 36% African American, 35% Hispanic) in the Washington Heights-Inwood Columbia Aging Project. Composite scores of memory, language, speed/executive functioning, and visuospatial function were derived from a neuropsychological battery. Hippocampal volume, regional cortical thickness, infarcts, and white matter hyperintensity (WMH) volumes were quantified with FreeSurfer and in-house developed procedures. Multiple-group regression analysis, in which each cognitive composite score was regressed onto MRI variables, demographic variables, and cardiovascular health factors, tested which paths differed across groups. Results: Larger WMH volume was associated with worse language and speed/executive functioning among African Americans, but not among non-Hispanic Whites. Larger hippocampal volume was more strongly associated with better memory among non-Hispanic Whites compared with Hispanics. Cortical thickness and infarcts were similarly associated with cognition across groups. Conclusion: The main finding of this study was that certain MRI predictors of cognition differed across racial/ethnic groups. These results highlight the critical need for more diverse samples in the study of cognitive aging, as the type and relation of neurobiological substrates of cognitive functioning may be different for different groups.