Examining the day-to-day bidirectional associations between physical activity, sedentary behavior, screen time, and sleep health during school days in adolescents

Abstract

Background: Adolescence is a vulnerable period for experiencing poor sleep health. Growing studies have demonstrated lifestyle behaviors including physical activity (PA), screen time (SCT), and sedentary behaviors (SED) as the potential factors associated with sleep health in adolescents; yet, the evidence is inconclusive and the directionality of temporal associations across school days are not well understood. This study examined the day-to-day bidirectional associations of lifestyle behaviors with sleep health parameters in adolescents.

Methods: A total of 263 adolescents (58% boys) in 6th - 8th grades wore an accelerometer for 24-hour across the three consecutive school days and completed recording SCT in time-diary and answering sleep quality (SQ) questions for each day. Sleep-wake patterns as well as time spent in moderate- and vigorous-intensity PA (MVPA) and SED were objectively quantified from the wrist-worn accelerometry data across the two segments of the day (during and after school hours). Mixed model analyses were conducted to test bidirectional associations between lifestyle factors and sleep health parameters in each temporal direction across the days. Additionally, indirect associations across the days were tested using an autoregressive cross-lagged model analysis in the framework of path analysis.

Results: MVPA minutes in a day did not predict sleep health parameters that night. The bidirectional associations were partially observed between SED and sleep health, but the significance and direction of the associations largely varied by the time segment of a day as well as types of sleep health parameters. Additionally, greater SCT during the day was associated with lower SQ that night (b = -0.010; P = .018), and greater SQ was associated with greater MVPA during school hours (b = 6.45; P = .028) and lower SED after school hours (b = -39.85; P = .029) the next day. Lastly, there were significant indirect associations of SCT with sleep health parameters across the days indicating multi-day lagged effects of SCT on sleep health the later nights.

Conclusion: This study highlights the importance of lowering SCT for better sleep health in adolescents during school days. Additionally, perceived SQ is shown to be a potential significant predictor promoting healthy behaviors the next day independent of sleep-wake patterns. Further studies are warranted to confirm the observed temporal associations between SCT, SQ, and behavioral outcomes in this vulnerable population.

Fig 1

An autoregressive cross-lagged path model examining temporal and bidirectional associations between daily activity counts, SCT, and following sleep health parameters across the three school days: (a) total sleep time; (b) sleep efficiency; (c) sleep fragment; and (d) sleep quality. Screen time and sleep quality were log-transformed, and activity counts were multiplied by 10,000 to reduce the unit size. Only significant path coefficients are boldly reported in the form of the unstandardized coefficient. Complete results are reported in S2 Table through 5 for each sleep health outcome.