Memory complaints and risk of cognitive impairment after nearly 2 decades among older women

Abstract

Objectives: To investigate the association between subjective memory complaints (SMCs) and long-term risk of cognitive impairment in aging because most previous studies have followed individuals for only a few years.

Methods: Participants were 1,107 cognitively normal, community-dwelling older women (aged 65 years and older at baseline) in a prospective study of aging. SMCs were assessed shortly after baseline and repeatedly over time with the yes/no question, "Do you feel you have more problems with memory than most?" Cognitive status 18 years later (normal or impaired with mild cognitive impairment or dementia) was determined by an expert panel. Using logistic regression, we investigated the association between SMCs over time and risk of cognitive impairment, adjusting for demographics, baseline cognition, and characteristics that differed between those with and without SMCs.

Results: At baseline, 8.0% of participants (n = 89) endorsed SMCs. Baseline SMCs were associated with increased risk of cognitive impairment 18 years later (adjusted odds ratio [OR] = 1.7, 95% confidence interval 1.1-2.8). Results were unchanged after excluding participants with depression. The association between SMCs and cognitive impairment was greatest at the last SMC assessment time point (18 years before diagnosis: adjusted OR = 1.7 [1.1-2.9]; 14 years before diagnosis: adjusted OR = 1.6 [0.9-2.7]; 10 years before diagnosis: adjusted OR = 1.9 [1.1-3.1]; 4 years before diagnosis: adjusted OR = 3.0 [1.8-5.0]).

Conclusions: SMCs are associated with cognitive impairment nearly 2 decades later among older women. SMCs may be a very early symptom of an insidious neurodegenerative disease process, such as Alzheimer disease.

Figure. SMCs at varying time points before the diagnostic evaluation and risk of cognitive impairment

Results of logistic regression analyses examining the association between SMCs assessed at varying time points before the diagnostic evaluation and risk of cognitive impairment. Adjusted models include adjustment for demographics (age, education) as well as mMMSE score, history of myocardial infarction, and depressive symptoms as measured at each SMC assessment time point. At each time point, individuals with an impaired mMMSE score at that time point were excluded (using −1.5 SD age- and education-based cutoffs). CI = confidence interval; mMMSE = modified Mini-Mental State Examination; SMC = subjective memory complaint.