Performance of an automated sleep scoring approach for actigraphy data in children and adolescents
Year: 2025
Type: article
Abstract: STUDY OBJECTIVES: GGIR is an R package for processing raw acceleration data to estimate sleep health parameters. We aimed to (1) assess the performance of three sleep algorithms within GGIR against PSG for detecting sleep/wake in clinically referred, typically-developing children (criterion validity); and (2) describe GGIR-derived sleep estimates from typically developing children enrolled in multiple cohort studies (face validity). METHODS: For criterion evaluation, children (8-16 years, N = 30) wore an actigraphy device for one night during in-lab polysomnography with performance assessed using epoch-by-epoch analyses. For face validity evaluation, four community/free living datasets were used: (1) Bone Mineral Accretion in Young Children (3-5 years, N = 310), (2) School Summer Sleep (5-8 years, N = 118), (3) Sleep and Growth Study 2 (12-13 years; N = 291), and (4) Early Life Exposure to Environmental Toxicants (9-18 years; N = 543). All raw acceleration data were processed using GGIR (v.3.0-0) with the Cole-Kripke (CK), Sadeh (S), and van Hees (vH) algorithm settings. RESULTS: Following the in-lab test, 60 per cent of children were diagnosed with mild to severe obstructive sleep apnea (OSA). For criterion evaluation, the 30-s epoch-by-epoch analyses revealed that average balanced accuracies were 0.80 (Sensitivity = 0.80; Specificity = 0.79), 0.76 (Sensitivity = 0.86; Specificity = 0.65), and 0.67 (Sensitivity = 0.95, Specificity = 0.39) for GGIR-CK, GGIR-vH, and GGIR-S, respectively. For face validity evaluation, sleep estimates mirrored the in-lab performance metrics (e.g. sleep duration estimates were similar when using GGIR-CK and GGIR-VH but approximately 1 h longer when using GGIR-S). CONCLUSIONS: The in-lab performance metrics from typically developing children with and without OSA and cohort-based descriptive statistics from samples of typically developing children provide benchmark data to guide investigators on the suitability of GGIR for automated processing of raw acceleration data for pediatric sleep estimation.
Source: SLEEP
Authors: Pin-Wei Chen, Erica C Jansen, Christopher M Cielo, Ariel A Williamson, Margaret Banker, Michael Kaye, Peter X K Song, Karen E Peterson, Alejandra Cantoral, Martha María Téllez-Rojo, Cathy Goldstein, Khadija Zanna, Akane Sano, Jennette P Moreno, Heidi Kalkwarf, Babette S Zemel, Jonathan A Mitchell
Institutions: Children's Hospital of Philadelphia, University of Michigan, University of Pennsylvania, Oregon Health & Science University, University of Oregon, Northwestern University, Universidad Iberoamericana, Rice University, Baylor College of Medicine, Children's Nutrition Research Center at Baylor College of Medicine, Cincinnati Children's Hospital Medical Center, University of Cincinnati
Language: English
Topic: Sleep and related disorders
Subfield: Experimental and Cognitive Psychology
Field: Psychology
Domain: Social Sciences
Open Access status: green
Awards: Lifecourse Exposures & Diet: Epigenetics, Maturation & Metabolic Syndrome, E3Gen: Multigenerational Effects of Toxicant Exposures on Life Course Health and Neurocognitive Outcomes in the ELEMENT Birth Cohorts, Sleep and Circadian Rhythms in Adolescence: Epigenetic Pathways of Cardiometabolic Risk, Effects of Sleep on Bone Density and Strength in Adolescence: A Prospective Longitudinal Study, E3Gen: Multigenerational Influences of Social Structure on Toxicant Exposures and Life Course Health in the ELEMENT Cohort, Michigan Nutrition Obesity Research Center, Michigan Center on Lifestage Environmental Exposures and Disease (M-LEEaD)
OpenAlex ID: W4414379666