When does sedentary behavior become sleep? A proposed framework for classifying activity during sleep-wake transitions

The Sedentary Behavior Research Network recently published a consensus definition for sedentary behavior as 'any waking behavior characterized by an energy expenditure <= 1.5 metabolic equivalents, while in a sitting, reclining, or lying posture.' While this is a great step toward theoretical and methodological unity, further clarity around issues of classifying sedentary behavior while in bed is needed, specifically during sleep-wake transitions. A thigh-worn inclinometer with a 24-h wear protocol is recommended for best practice assessment of sedentary behavior, but this method introduces challenges for activity classification and data reduction. The constant stream of data collection does not distinguish waking sedentary activities in bed, e.g., watching television or reading, from sleep. Moreover, correct classification during sleep-wake transitions is not well established. Sleep-related behaviors can include time spent trying to fall asleep (sleep onset latency), night awakenings while attempting to fall back asleep (wakefulness after sleep onset), and unsuccessful attempts to fall back asleep in the morning (wakefulness after sleep offset). While these behaviors technically fit into the current definition of sedentary behavior, sleep-related behaviors belong in the sleep domain, are a normal part of the sleep-wake cycle, and are not likely an intervention target for sedentary behavior reduction. For these reasons, we argue that sleep-related behaviors should not be classified as sedentary. The research implications of using this framework for classifying sedentary behavior via 24-h thigh inclinometers include that diaries must ask participants to report the time they got into bed, began attempting to fall asleep ('lights out'), woke up for the day, and got out of bed for the day. Using these diaries, researchers must manually extract the relevant period of wakefulness (and remove sleep-related and sleep time). The importance of this more burdensome protocol for researchers and participants, and across various subject populations, should be evaluated in future research.