Relationship between reported and measured sleep times: the sleep heart health study (SHHS)

Abstract

Study objective: Subjective and objective assessments of sleep may be discrepant due to sleep misperception and measurement effects, the latter of which may change the quality and quantity of a person's usual sleep. This study compared sleep times from polysomnography (PSG) with self-reports of habitual sleep and sleep estimated on the morning after a PSG in adults.

Design: Total sleep time and sleep onset latency obtained from unattended home PSGs were compared to sleep times obtained from a questionnaire completed before the PSG and a Morning Survey completed the morning after the PSG.

Participants: A total of 2,113 subjects who were > or = 40 years of age were included in this analysis.

Measures and results: Subjects were 53% female, 75% Caucasian, and 38% obese. The mean habitual sleep time (HABTST), morning estimated sleep time (AMTST), and PSG total sleep times (PSGTST) were 422 min, 379 min, and 363 min, respectively. The mean habitual sleep onset latency, morning estimated sleep onset latency, and PSG sleep onset latency were 17.0 min, 21.8 min, and 16.9 min, respectively. Models adjusting for related demographic factors showed that HABTST and AMTST differ significantly from PSGTST by 61 and 18 minutes, respectively. Obese and higher educated people reported less sleep time than their counterparts. Similarly, small but significant differences were seen for sleep latency.

Conclusions: In a community population, self-reported total sleep times and sleep latencies are overestimated even on the morning following overnight PSG.

Figure 1

Unadjusted mean total sleep time (TST) and sleep onset latency (SOL) for habitual (HAB), morning estimated (AM), and polysomnogram (PSG) measures from mixed-effects linear regression models.

Figure 2

Linear prediction of total sleep time by age.

Figure 3

Linear prediction of sleep onset latency by age.