Self-reported sleep duration mitigates the association between inflammation and cognitive functioning in hospitalized older men

Abstract

Examination of predictors of late-life cognitive functioning is particularly salient in at-risk older adults, such as those who have been recently hospitalized. Sleep and inflammation are independently related to late-life cognitive functioning. The potential role of sleep as a moderator of the relationship between inflammation and global cognitive functioning has not been adequately addressed. We examined the relationship between self-reported sleep duration, inflammatory markers, and general cognitive functioning in hospitalized older men. Older men (n = 135; Mean age = 72.9 ± 9.7 years) were recruited from inpatient rehabilitation units at a VA Medical Center to participate in a cross-sectional study of sleep. Participants completed the Mini-Mental State Examination and Pittsburgh Sleep Quality Index, and underwent an 8 a.m. blood draw to measure inflammatory markers [i.e., C-reactive protein (CRP), tumor necrosis factor alpha (TNFα), soluble intercellular adhesion molecule-1 (sICAM-1), and interleukin-6 (IL-6)]. Hierarchical regression analyses (controlling for age, education, race, depression, pain, health comorbidity, and BMI) revealed that higher levels of CRP and sICAM are associated with higher global cognitive functioning in older men with sleep duration ≥6 h (β = -0.19, β = -0.18, p's < 0.05, respectively), but not in those with short sleep durations (p's > 0.05). In elderly hospitalized men, sleep duration moderates the association between inflammation and cognitive functioning. These findings have implications for the clinical care of older men within medical settings.

Keywords: cognition; hospitalization; inflammation; older adults; sleep duration.

Figure 1

Interaction between CRP (left panel, mg/L) and sICAM (right panel, ng/mL) and sleep duration. CRP, sICAM, and MMSE variables were transformed using the Blom transformation prior to analyses. All variables were transformed back to their original metric prior to graphing. Values to the left of the vertical bold lines fall within the regions of significance.