TY - JOUR
T1 - Automating sleep stage classification using wireless, wearable sensors
AU - Boe, Alexander J.
AU - McGee Koch, Lori L.
AU - O’Brien, Megan K.
AU - Shawen, Nicholas
AU - Rogers, John A.
AU - Lieber, Richard L.
AU - Reid, Kathryn J.
AU - Zee, Phyllis C.
AU - Jayaraman, Arun
N1 - Publisher Copyright:
© 2019, The Author(s).
PY - 2019/12/1
Y1 - 2019/12/1
N2 - Polysomnography (PSG) is the current gold standard in high-resolution sleep monitoring; however, this method is obtrusive, expensive, and time-consuming. Conversely, commercially available wrist monitors such as ActiWatch can monitor sleep for multiple days and at low cost, but often overestimate sleep and cannot differentiate between sleep stages, such as rapid eye movement (REM) and non-REM. Wireless wearable sensors are a promising alternative for their portability and access to high-resolution data for customizable analytics. We present a multimodal sensor system measuring hand acceleration, electrocardiography, and distal skin temperature that outperforms the ActiWatch, detecting wake and sleep with a recall of 74.4% and 90.0%, respectively, as well as wake, non-REM, and REM with recall of 73.3%, 59.0%, and 56.0%, respectively. This approach will enable clinicians and researchers to more easily, accurately, and inexpensively assess long-term sleep patterns, diagnose sleep disorders, and monitor risk factors for disease in both laboratory and home settings.
AB - Polysomnography (PSG) is the current gold standard in high-resolution sleep monitoring; however, this method is obtrusive, expensive, and time-consuming. Conversely, commercially available wrist monitors such as ActiWatch can monitor sleep for multiple days and at low cost, but often overestimate sleep and cannot differentiate between sleep stages, such as rapid eye movement (REM) and non-REM. Wireless wearable sensors are a promising alternative for their portability and access to high-resolution data for customizable analytics. We present a multimodal sensor system measuring hand acceleration, electrocardiography, and distal skin temperature that outperforms the ActiWatch, detecting wake and sleep with a recall of 74.4% and 90.0%, respectively, as well as wake, non-REM, and REM with recall of 73.3%, 59.0%, and 56.0%, respectively. This approach will enable clinicians and researchers to more easily, accurately, and inexpensively assess long-term sleep patterns, diagnose sleep disorders, and monitor risk factors for disease in both laboratory and home settings.
UR - http://www.scopus.com/inward/record.url?scp=85089605953&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85089605953&partnerID=8YFLogxK
U2 - 10.1038/s41746-019-0210-1
DO - 10.1038/s41746-019-0210-1
M3 - Article
C2 - 31886412
AN - SCOPUS:85089605953
SN - 2398-6352
VL - 2
JO - npj Digital Medicine
JF - npj Digital Medicine
IS - 1
M1 - 131
ER -