An algorithm for actigraphy-based sleep/wake scoring: Comparison with polysomnography. Issue 1 (January 2021)

• Record Type: Journal Article
• Authors: Lüdtke, Stefan; Hermann, Wiebke; Kirste, Thomas; Beneš, Heike; Teipel, Stefan
• Is Part Of: Clinical neurophysiology. Volume 132:Issue 1(2021)
• Page Start: 137
• Page End: 145
• Publication Date: 2021-01
• Subjects: Actigraphy -- Polysomnography -- Sleep/wake scoring -- Hidden Markov Model; Neurophysiology -- Periodicals; Electroencephalography -- Periodicals; Electromyography -- Periodicals; Neurology -- Periodicals; 612.8
• DOI: 10.1016/j.clinph.2020.10.019
• Languages: English
• ISSNs: 1388-2457

Abstract

Highlights: Actigraphic sleep/wake scoring allows unobtrusive, longitudinal assessment of sleep/wake cycles. We propose an algorithm that estimates a model of sleep architecture from training data and thus does not need to rely on predefined rescoring rules. The algorithm can detect sleep with higher specificity than existing methods for patients with neuropsychiatric sleep disturbances. Abstract: Objective: To evaluate the accuracy of actigraphy against polysomnography (PSG) as gold standard using a newly developed algorithm for sleep/wake discrimination that explicitly models the temporal structure of sleep. Methods: PSG was recorded in 11 men and 9 women (age 71.1 ± 5.0 ) to evaluate suspected neuropsychiatric sleep disturbances. Simultaneously, wrist actigraphy was recorded, from which 37 features were computed for each 1-min epoch. We compared prediction of PSG-derived sleep/wake states for each of these features between our newly developed algorithm, and four state-of-the-art algorithms. The algorithms were evaluated using a leave-one-subject out cross validation. Results: The new algorithm classified 84.9% of sleep epochs (sensitivity) and 74.2% of wake epochs correctly (specificity), leading to a sleep/wake scoring accuracy of 79.0%. Four out of five sleep parameters were estimated more accurately by the new algorithm than by state-of-the-art algorithms. Conclusion: The proposed algorithm achieved a significantly higher specificity than state-of-the-art algorithm, with only minor decrease in sensitivity for patients with sleep disorders. We assume this reflects the capability of the algorithm to explicitly model sleep architecture. Significance: The unobtrusive assessment of sleep/wake cycles is particularly relevant for patients with neuropsychiatric diseases that are associated with sleep disturbances, such as depression or dementia.