Radar-based sleep stage classification in children undergoing polysomnography: a pilot-study.

STUDY OBJECTIVES: Unobtrusive monitoring of sleep and sleep disorders in children presents challenges. We investigated the possibility of using Ultra-Wide band (UWB) radar to measure sleep in children. METHODS: Thirty-two children scheduled to undergo a clinical polysomnography participated; their ages ranged from 2 months to 14 years. During the polysomnography, the children's body movements and breathing rate were measured by an UWB-radar. A total of 38 features were calculated from the motion signals and breathing rate obtained from the raw radar signals. Adaptive boosting was used as machine learning classifier to estimate sleep stages, with polysomnography as gold standard method for comparison. RESULTS: Data of all participants combined, this study achieved a Cohen's Kappa coefficient of 0.67 and an overall accuracy of 89.8% for wake and sleep classification, a Kappa of 0.47 and an accuracy of 72.9% for wake, rapid-eye-movement (REM) sleep, and non-REM sleep classification, and a Kappa of 0.43 and an accuracy of 58.0% for wake, REM sleep, light sleep and deep sleep classification. CONCLUSION: Although the current performance is not sufficient for clinical use yet, UWB radar is a promising method for non-contact sleep analysis in children.

Cervical Spinal Cord Compression and Sleep-Disordered Breathing in Syndromic Craniosynostosis.

BACKGROUND AND PURPOSE: Cerebellar tonsillar herniation arises frequently in syndromic craniosynostosis and causes central and obstructive apneas in other diseases through spinal cord compression. The purposes of this study were the following: 1) to determine the prevalence of cervical spinal cord compression in syndromic craniosynostosis, and 2) to evaluate its connection with sleep-disordered breathing. MATERIALS AND METHODS: This was a cross-sectional study including patients with syndromic craniosynostosis who underwent MR imaging and polysomnography. Measures encompassed the compression ratio at the level of the odontoid process and foramen magnum and the cervicomedullary angle. MR imaging studies of controls were included. Linear mixed models were developed to compare patients with syndromic craniosynostosis with controls and to evaluate the association between obstructive and central sleep apneas and MR imaging parameters. RESULTS: One hundred twenty-two MR imaging scans and polysomnographies in 89 patients were paired; 131 MR imaging scans in controls were included. The mean age at polysomnography was 5.7 years (range, 0.02-18.9 years). The compression ratio at the level of the odontoid process was comparable with that in controls; the compression ratio at the level of the foramen magnum was significantly higher in patients with Crouzon syndrome (+27.1, P < .001). The cervicomedullary angle was significantly smaller in Apert, Crouzon, and Saethre-Chotzen syndromes (-4.4°, P = .01; -10.2°, P < .001; -5.2°, P = .049). The compression ratios at the level of the odontoid process and the foramen magnum, the cervicomedullary angle, and age were not associated with obstructive apneas (P > .05). Only age was associated with central apneas (P = .02). CONCLUSIONS: The prevalence of cervical spinal cord compression in syndromic craniosynostosis is low and is not correlated to sleep disturbances. However, considering the high prevalence of obstructive sleep apnea in syndromic craniosynostosis and the low prevalence of compression and central sleep apnea in our study, we would, nevertheless, recommend a polysomnography in case of compression on MR imaging studies.