OBJECTIVE: 

To investigate sleep disturbances that induce cognitive changes over 4 years in nondemented elderlies.

METHODS: 

Data were acquired from a nationwide, population-based, prospective cohort of Korean elderlies (2,238 normal cognition [NC] and 655 mild cognitive impairment [MCI]). At baseline and 4-year follow-up assessments, sleep-related parameters (midsleep time, sleep duration, sleep latency, subjective sleep quality, sleep efficiency, and daytime dysfunction) and cognitive status were measured using the Pittsburgh Sleep Quality Index and Consortium to Establish a Registry for Alzheimer's Disease Assessment, respectively. We used logistic regression models adjusted for covariates including age, sex, education, apolipoprotein E genotype, Geriatric Depression Scale, Cumulative Illness Rating Scale, and physical activity.

RESULTS: 

In participants with NC, long sleep latency (>30 minutes), long sleep duration (≥7.95 hours), and late midsleep time (after 3:00 am) at baseline were related to the risk of cognitive decline at 4-year follow-up assessment; odds ratio (OR) was 1.40 for long sleep latency, 1.67 for long sleep duration, and 0.61 for late midsleep time. These relationships remained significant when these variables maintained their status throughout the follow-up period. Newly developed long sleep latency also doubled the risk of cognitive decline. In those with MCI, however, only long sleep latency reduced the chance of reversion to NC (OR = 0.69).

INTERPRETATION: 

As early markers of cognitive decline, long sleep latency can be used for elderlies with NC or MCI, whereas long sleep duration and relatively early sleep time might be used for cognitively normal elderlies only. Ann Neurol 2018;83:472-482.