Sleep classification from wrist-worn accelerometer data using random forests
Autor: | Jian Wang, Eus J.W. Van Someren, Kalaivani Sundararajan, Séverine Sabia, Bart H W Te Lindert, Vincent T. van Hees, Sonja Georgievska, Philip R. Gehrman, Jennifer R Ramautar, Diego R. Mazzotti, Michael N. Weedon, Lars Ridder |
---|---|
Přispěvatelé: | Psychiatry, Amsterdam Neuroscience - Mood, Anxiety, Psychosis, Stress & Sleep, Amsterdam Neuroscience - Systems & Network Neuroscience, APH - Mental Health, Netherlands Institute for Neuroscience (NIN) |
Jazyk: | angličtina |
Rok vydání: | 2021 |
Předmět: |
0301 basic medicine
Adult Male Sleep Wake Disorders Adolescent Computer science Epidemiology Science Polysomnography Neurophysiology Accelerometer Machine learning computer.software_genre Article Machine Learning 03 medical and health sciences Wearable Electronic Devices Young Adult 0302 clinical medicine Deep Learning Accelerometry medicine Humans Aged Sleep disorder Multidisciplinary medicine.diagnostic_test business.industry Actigraphy Sleep disorders Middle Aged medicine.disease Random forest 030104 developmental biology Test set Medicine Female Sleep (system call) Artificial intelligence Sleep Stages F1 score business Sleep computer 030217 neurology & neurosurgery Algorithms |
Zdroj: | Scientific Reports, 11(1):24. Nature Publishing Group Sundararajan, K, Georgievska, S, te Lindert, B H W, Gehrman, P R, Ramautar, J, Mazzotti, D R, Sabia, S, Weedon, M N, van Someren, E J W, Ridder, L, Wang, J & van Hees, V T 2021, ' Sleep classification from wrist-worn accelerometer data using random forests ', Scientific Reports, vol. 11, no. 1, 24 . https://doi.org/10.1038/s41598-020-79217-x Scientific Reports Scientific Reports, Vol 11, Iss 1, Pp 1-10 (2021) Scientific Reports, 11(1). Nature Publishing Group |
ISSN: | 2045-2322 |
Popis: | Accurate and low-cost sleep measurement tools are needed in both clinical and epidemiological research. To this end, wearable accelerometers are widely used as they are both low in price and provide reasonably accurate estimates of movement. Techniques to classify sleep from the high-resolution accelerometer data primarily rely on heuristic algorithms. In this paper, we explore the potential of detecting sleep using Random forests. Models were trained using data from three different studies where 134 adult participants (70 with sleep disorder and 64 good healthy sleepers) wore an accelerometer on their wrist during a one-night polysomnography recording in the clinic. The Random forests were able to distinguish sleep-wake states with an F1 score of 73.93% on a previously unseen test set of 24 participants. Detecting when the accelerometer is not worn was also successful using machine learning ($$\hbox {F1-score} > 93.31\%$$ F1-score > 93.31 % ), and when combined with our sleep detection models on day-time data provide a sleep estimate that is correlated with self-reported habitual nap behaviour ($$\hbox {r}=.60$$ r = . 60 ). These Random forest models have been made open-source to aid further research. In line with literature, sleep stage classification turned out to be difficult using only accelerometer data. |
Databáze: | OpenAIRE |
Externí odkaz: |