Computer vision algorithms outperform actigraphy

Barnett, Natalie; Glazer, Assaf; Ivry, Tor; Ankri, Yanai; Veler, Haviva

doi:10.1183/23120541.sleepandbreathing-2019.p134

Cited by 8 publications

(10 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Videosomnography technologies, such as Nanit (Barnett et al, 2019), are another option that can document caregiving frequency (i.e., caregiver visits to the bedside) as well as provide sleep measures (e.g., SE, duration; Horger et al, 2021). Research data can be obtained from Nanit without video review to protect participant privacy, or the researcher can choose to download video data for additional analyses, such as delirium screening.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Sleep disruption and delirium in critically ill children: Study protocol feasibility

Kalvas

Harrison

Solove

et al. 2022

Research in Nursing & Health

View full text Add to dashboard Cite

Delirium is a serious complication of pediatric critical illness. Sleep disruption is frequently observed in children with delirium, and circadian rhythm dysregulation is one proposed cause of delirium. Children admitted to the pediatric intensive care unit (PICU) experience multiple environmental exposures with the potential to disrupt sleep. Although researchers have measured PICU light and sound exposure, sleep, and delirium, these variables have not yet been fully explored in a single study. Furthermore, caregiving patterns have not often been included as a component of the PICU environment. Measuring the light and sound exposure, caregiving patterns, and sleep of critically ill children requires continuous PICU bedside data collection. This presents multiple methodological challenges. In this paper, we describe the protocol for an observational pilot study of the PICU environment, sleep, and delirium experienced by a sample of 10 critically ill children 1-4 years of age. We also evaluate and discuss the feasibility (i.e., acceptability, implementation, practicality) of the study protocol. Light and sound exposure were measured with bedside sensors. Caregiving was quantified through video recording. Sleep was measured via actigraphy and confirmed by video recording. Delirium screening with the Cornell Assessment of Pediatric Delirium was conducted twice daily, either in person or via video review. This study provides a refined measurement framework to inform future, large-scale studies and the development of nurse-driven sleep promotion interventions.

show abstract

Section: Discussionmentioning

confidence: 99%

mentioning

confidence: 99%

Sleep disruption and delirium in critically ill children: Study protocol feasibility

Kalvas

Harrison

Solove

et al. 2022

Research in Nursing & Health

View full text Add to dashboard Cite

show abstract

“…New sleep measurement techniques such as autovideosomnography should also be employed to measure the nature of movement during infant sleep as a function of motor development (Horger, Marsiliani, et al., 2021). Autovideosomnography is an emerging technology that video records infants in their cribs and processes the video through a computer vision algorithm using the infants' location and movement to code sleep‐wake states (Barnett et al., 2019). Directly observing from video whether there is a change in sleep‐dependent movement patterns related to the skill being acquired could help us better understand the relation between motor skill onset and sleep‐dependent movement.…”

Section: Discussionmentioning

confidence: 99%

Infant motor development predicts the dynamics of movement during sleep

DeMasi

Horger

Scher

et al. 2022

Infancy

View full text Add to dashboard Cite

The characteristics of infant sleep change over the first year. Generally, infants wake and move less at night as they grow older. However, acquisition of new motor skills leads to temporary increases in night waking and movement at night. Indeed, sleep‐dependent movement at night is important for sensorimotor development. Nevertheless, little is known about how movement during sleep changes as infants accrue locomotor experience. The current study investigated whether infant sleep and movement during sleep were predicted by infants' walking experience. Seventy‐eight infants wore an actigraph to measure physical activity during sleep. Parents reported when their infants first walked across a room >10 feet without stopping or falling. Infants in the midst of walking skill acquisition had worse sleep than an age‐group estimate. Infants with more walk experience had more temporally sporadic movement during sleep and a steeper hourly increase in physical activity over the course of the night. Ongoing motor skill consolidation changes the characteristics of movement during sleep and may alter sleep state‐dependent memory consolidation. We propose a model whereby changes in gross motor activity during night sleep reflect movement‐dependent consolidation.

show abstract

“…Similar to actigraphy and manual videosomnography, auto‐videosomnography analyzes sleep‐wake patterns based on infant motion and stillness. These motion data are translated into validated sleep metrics using Nanit’s computer‐vision algorithm (Barnett, Glazer, Ivry, Ankri, & Veler, 2019; Kahn, Barnett, Glazer, & Gradisar, 2020b).…”

Section: Methodsmentioning

confidence: 99%

Sleeping through COVID‐19: a longitudinal comparison of 2019 and 2020 infant auto‐videosomnography metrics

Kahn

Gradisar

2021

Child Psychology Psychiatry

View full text Add to dashboard Cite

Background: With the outbreak of the COVID-19 pandemic, pediatric experts called attention to the potential adverse effects of living restrictions (e.g., lockdown) on child well-being, but at the same time-acknowledged their possible benefits. To date, only few data-driven reports have been published on child sleep during COVID-19, and all have been based on parent-or self-reports. This study used auto-videosomnography to capture the effects of COVID-19 stay-at-home orders imposed in the USA on objectively measured infant sleep. Methods: Auto-videosomnography metrics of infants assessed nightly between January and May 2020 were compared with metrics of an equivalent infant cohort, assessed in the corresponding 2019 period. A total of 610 infants (50.7% girls) aged 6-18 months (M = 11.8, SD = 3.6) were included, with 71,472 analyzed nights. Multilevel models were applied to assess differences between 2019 and 2020 infant sleep pre-and during-lockdown. Results: Whereas infant cohorts were equivalent in demographic and January-March/April sleep characteristics, during the 2020 lockdown infants had longer nighttime sleep durations (M difference = 11.0 min, p = .01), later morning rise times (M difference = 9.5 min, p = .008), and later out-of-crib times (M difference = 12.3 min, p < .0001), compared to the equivalent 2019 period. In addition, weekday-weekend differences in sleep onset and midpoint times were diminished during 2020 homeconfinement compared to the equivalent 2019 period (2019: M difference = 5.5 min, p < .0001; M difference = 4.5 min, p < .0001; 2020: M difference = 2.3 min, p = .01; M difference = 3.1 min, p < .0001, respectively). Conclusions: Notwithstanding the negative implications of COVID-19 living restrictions in other domains, our findings indicate that there might be a silver lining-in promoting longer and more consistent infant sleep. These benefits should be considered in determining policy for the current and future pandemics.

show abstract

Computer vision algorithms outperform actigraphy

Cited by 8 publications

References 0 publications

Sleep disruption and delirium in critically ill children: Study protocol feasibility

Sleep disruption and delirium in critically ill children: Study protocol feasibility

Infant motor development predicts the dynamics of movement during sleep

Sleeping through COVID‐19: a longitudinal comparison of 2019 and 2020 infant auto‐videosomnography metrics

Contact Info

Product

Resources

About