A Potential Association Between Retinal Changes, Subjective Memory Impairment, and Anxiety in Older Adults at Risk for Alzheimer's Disease: A 27-Month Pilot Study

Abstract

Introduction: The utility of subjective memory impairment (SMI) as a risk marker for preclinical Alzheimer's disease (AD) remains unclear; however, recent studies have identified a correlation between retinal biomarkers and onset of preclinical disease. This study examines the relationship between retinal biomarkers that have been associated with cerebral amyloid, an early hallmark of AD, and SMI scores in patients at risk for developing AD.

Methods: Forty-nine cognitively normal subjects were followed over 27 months and evaluated using a combination of neuropsychological, psychological, and retinal imaging instruments. Subjective memory testing was conducted using the memory assessment clinic questionnaire (MACQ) and Depression, Anxiety, and Stress Scales (DASS). Multivariate linear analysis was conducted using STATA software.

Results: Positive correlations were found between retinal nerve fiber layer (RNFL) volume and scores obtained from the MAC-Q at 27 months (MAC-Q_27), the DASS questionnaire for anxiety at 27 months (DASS-A_27), and the change in DASS-A over 27 months (dDASSA). There was also a significant positive correlation between these variables and the change in RNFL thickness over 27 months (dRNFL). MACQ_27, DASSA_27, and dDASS-A accounted for 35.7% of RFNL variance at 27 months and 21.5% of dRFNL variance.

Discussion: These findings suggest that worse subjective memory complaints and anxiety scores may be associated with one of the most commonly used structural anatomical retinal markers of early disease burden in AD. If so, these results lend support to SMI as a valid risk marker for later cognitive decline.

Keywords: Alzheimer’s disease; preclinical Alzheimer’s disease; retinal biomarkers; retinal nerve fiber layer; subjective cognitive decline; subjective memory impairment.

FIGURE 1

Individual regression models for MACQ_27 using baseline RNFL volumes (RNFL) as the dependent variable.

FIGURE 2

Individual regression models for DASSA_27 using baseline RNFL volumes (RNFL) as the dependent variable.

FIGURE 3

Individual regression models for dDASSA using baseline RNFL volumes (RNFL) as the dependent variable.

FIGURE 4

Individual regression models for MACQ_27 using change in RNFL volume (dRNFL) as the dependent variable.

FIGURE 5

Individual regression models for DASSA_27 using change in RNFL volume (dRNFL) as the dependent variable.

FIGURE 6

Individual regression models for dDASSA using change in RNFL volume (dRNFL) as the dependent variable.