Using actigraphy to assess sleep characteristics

Abstract

Research points to the importance of circadian rhythms for health; their disruptions are associated with various diseases. This has led to the development of circadian medicine, which focuses on using knowledge of physiological rhythms to optimize treatment and diagnostic methods. Our article highlights the role of actigraphy, a non-invasive method for assessing sleep-wake cycles, in the study and diagnosis of sleep. Actigraphs, wearable devices shaped like watches, use motion sensors to monitor activity, providing important data on sleep quality. Particular attention is given to the methodology for obtaining actigraphy data and the analysis of sleep parameters, which includes the assessment of total sleep time, sleep efficiency, and frequency of awakenings. The importance of accurate methodology and validated algorithms for actigraphy data analysis is emphasized through a review of various sleep assessment algorithms and their application in clinical and research settings. Additionally, the paper explores the potential use of artificial intelligence, including machine and deep learning, to improve sleep data analysis. The conclusion emphasizes that despite the reliability of actigraphy for determining sleep phases, additional studies are needed to validate it in clinical use. This highlights the potential of actigraphy as an important tool in circadian medicine and sleep studies, which requires its further development and integration with new technological advances.

Keywords

• actigraph
• circadian rhythms
• machine learning
• sleep phases
• noninvasive monitoring