Automating sleep stage classification using wireless, wearable sensors

Alexander J Boe; Lori L McGee Koch; Megan K O'Brien; Nicholas Shawen; John A Rogers; Richard L Lieber; Kathryn J Reid; Phyllis C Zee; Arun Jayaraman

doi:10.1038/s41746-019-0210-1

Automating sleep stage classification using wireless, wearable sensors

NPJ Digit Med. 2019 Dec 20:2:131. doi: 10.1038/s41746-019-0210-1. eCollection 2019.

Authors

Alexander J Boe^#^{1

2}, Lori L McGee Koch^#^{1

3}, Megan K O'Brien^{1

4}, Nicholas Shawen^{1

5}, John A Rogers⁶, Richard L Lieber^{2

4

7}, Kathryn J Reid³, Phyllis C Zee³, Arun Jayaraman^{1

4}

Affiliations

¹ Max Nader Lab for Rehabilitation Technologies and Outcomes Research, Shirley Ryan AbilityLab, Chicago, IL 60611 USA.
² 2Department of Biomedical Engineering, Northwestern University, Evanston, IL 60208 USA.
³ 3Department of Neurology, Northwestern University, Chicago, IL 60611 USA.
⁴ 4Department of Physical Medicine and Rehabilitation, Northwestern University, Chicago, IL 60611 USA.
⁵ 5Medical Scientist Training Program, Northwestern University Feinberg School of Medicine, Chicago, IL 60611 USA.
⁶ 6Center for Bio-Integrated Electronics, Departments of Materials Science and Engineering, Biomedical Engineering, Electrical Engineering and Computer Science, Northwestern University, Evanston, IL 60208 USA.
⁷ Shirley Ryan AbilityLab, Chicago, IL 60611 USA.

^# Contributed equally.

Abstract

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.

Keywords: Biomarkers; Biotechnology; Computational science.

Abstract

Grants and funding