Dataset Information

Automating sleep stage classification using wireless, wearable sensors.

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.

SUBMITTER: Boe AJ

PROVIDER: S-EPMC6925191 | biostudies-literature | 2019

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Automating sleep stage classification using wireless, wearable sensors.

Boe Alexander J AJ McGee Koch Lori L LL O'Brien Megan K MK Shawen Nicholas N Rogers John A JA Lieber Richard L RL Reid Kathryn J KJ Zee Phyllis C PC Jayaraman Arun A

NPJ digital medicine 20191220

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-resoluti ...[more]

PMID: 31886412

Similar Datasets

Project description:BackgroundThe characterization of limb biomechanics has broad implications for analyzing and managing motion in aging, sports, and disease. Motion capture videography and on-body wearable sensors are powerful tools for characterizing linear and angular motions of the body, though are often cumbersome, limited in detection, and largely non-portable. Here we examine the feasibility of utilizing an advanced wearable sensor, fabricated with stretchable electronics, to characterize linear and angular movements of the human arm for clinical feedback. A wearable skin-adhesive patch with embedded accelerometer and gyroscope (BioStampRC, MC10 Inc.) was applied to the volar surface of the forearm of healthy volunteers. Arms were extended/flexed for the range of motion of three different regimes: 1) horizontal adduction/abduction 2) flexion/extension 3) vertical abduction. Data were streamed and recorded revealing the signal "pattern" of movement in three separate axes. Additional signal processing and filtering afforded the ability to visualize these motions in each plane of the body; and the 3-dimensional motion envelope of the arm.ResultsEach of the three motion regimes studied had a distinct pattern - with identifiable qualitative and quantitative differences. Integration of all three movement regimes allowed construction of a "motion envelope," defining and quantifying motion (range and shape - including the outer perimeter of the extreme of motion - i.e. the envelope) of the upper extremity. The linear and rotational motion results from multiple arm motions match measurements taken with videography and benchtop goniometer.ConclusionsA conformal, stretchable electronic motion sensor effectively captures limb motion in multiple degrees of freedom, allowing generation of characteristic signatures which may be readily recorded, stored, and analyzed. Wearable conformal skin adherent sensor patchs allow on-body, mobile, personalized determination of motion and flexibility parameters. These sensors allow motion assessment while mobile, free of a fixed laboratory environment, with utility in the field, home, or hospital. These sensors and mode of analysis hold promise for providing digital "motion biomarkers" of health and disease.

Dataset Information

Automating sleep stage classification using wireless, wearable sensors.

Publications

Automating sleep stage classification using wireless, wearable sensors.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets