CoChat

The DOI matches its Crossref record; 45 of the 45 references it cites were found in a registry or an index.

Automating sleep stage classification using wireless, wearable sensors

Open access

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.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41746-019-0210-1

Cites

45 of 45 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig. 1 Performance of ActiWatch wrist sensor. Confusion matrix for the ActiWatch in a two-stage resolution, depicting average classification rate of wake and sleep stages. The ActiWatch demonstrated high recall of sleep (high sensitivity) but often misclassified Wake as sleep (low specificity).
Fig. 1 Performance of ActiWatch wrist sensor. Confusion matrix for the ActiWatch in a two-stage resolution, depicting average classification rate of wake and sleep stages. The ActiWatch demonstrated high recall of sleep (high sensitivity) but often misclassified Wake as sleep (low specificity).CC BY · PubMed Central
Fig. 2 Performance of a bagging decision tree classifier for different sleep staging resolutions. Confusion matrices (top), Receiver Operating Characteristic (ROC) curves (middle), and interquartile range (IQR) plots of model performance (bottom), obtained from leave-one-out cross-validation subject, for a two-stage wake vs. sleep classification, b three-stage wake vs. NREM vs. REM classification, c four-stage wake vs. light vs. deep vs. REM classification. ROC curves show the trade-off between sensitivity and specificity for a given model across subjects (line: mean; shading: standard deviation). Area under the ROC curve (AUROC) is listed for each stage; a value of 1.0 denotes a perfect classifier, whereas a value of 0.5 denotes a classifier that performs no better than random and has no predictive power. IQR plots illustrate how well the model generalizes across subjects, with smaller ranges indicating good performance and high generalizability irrespective of the subject (center line: median; box limits: upper and lower quartiles; whiskers: 1.5 × IQR; points: outliers).
Fig. 2 Performance of a bagging decision tree classifier for different sleep staging resolutions. Confusion matrices (top), Receiver Operating Characteristic (ROC) curves (middle), and interquartile range (IQR) plots of model performance (bottom), obtained from leave-one-out cross-validation subject, for a two-stage wake vs. sleep classification, b three-stage wake vs. NREM vs. REM classification, c four-stage wake vs. light vs. deep vs. REM classification. ROC curves show the trade-off between sensitivity and specificity for a given model across subjects (line: mean; shading: standard deviation). Area under the ROC curve (AUROC) is listed for each stage; a value of 1.0 denotes a perfect classifier, whereas a value of 0.5 denotes a classifier that performs no better than random and has no predictive power. IQR plots illustrate how well the model generalizes across subjects, with smaller ranges indicating good performance and high generalizability irrespective of the subject (center line: median; box limits: upper and lower quartiles; whiskers: 1.5 × IQR; points: outliers).CC BY · PubMed Central
Fig. 3 Effect of number of training subjects on model performance. Mean and standard deviation (shading) of AUROC for a wake, b NREM, and c REM classes in the three-stage bagging classifier model. The gradual increase in AUROC for each class suggests that a training set larger than N = 11 would continue to improve classification performance.
Fig. 3 Effect of number of training subjects on model performance. Mean and standard deviation (shading) of AUROC for a wake, b NREM, and c REM classes in the three-stage bagging classifier model. The gradual increase in AUROC for each class suggests that a training set larger than N = 11 would continue to improve classification performance.CC BY · PubMed Central
Fig. 4 Sensor systems and placement during overnight sleep. a Each participant wore three systems, including the proposed sensor set, consisting of accelerometers (ACC), electrocardiography (ECG), and skin temperature (TEMP), in addition to the wrist actigraphy control device measuring activity counts (ACT) and the gold standard system (PSG). b Size and profile comparison of the proposed sensors with the control device. (iButton: Copyright Maxim Integrated Products. Used by permission. ActiWatch: Permission to use ActiWatch Spectrum image was granted by Philips Respironics. BioStampRC: Permission to use BioStampRC image was granted by MC10, Inc.).
Fig. 4 Sensor systems and placement during overnight sleep. a Each participant wore three systems, including the proposed sensor set, consisting of accelerometers (ACC), electrocardiography (ECG), and skin temperature (TEMP), in addition to the wrist actigraphy control device measuring activity counts (ACT) and the gold standard system (PSG). b Size and profile comparison of the proposed sensors with the control device. (iButton: Copyright Maxim Integrated Products. Used by permission. ActiWatch: Permission to use ActiWatch Spectrum image was granted by Philips Respironics. BioStampRC: Permission to use BioStampRC image was granted by MC10, Inc.).CC BY · PubMed Central
Fig. 5 Time synchronization of independent data collection systems. ActiWatch was synchronized with the BioStampRC by aligning activity counts; BioStampRC was synchronized to the PSG by aligning ECG signals.
Fig. 5 Time synchronization of independent data collection systems. ActiWatch was synchronized with the BioStampRC by aligning activity counts; BioStampRC was synchronized to the PSG by aligning ECG signals.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 45 references

Cited by

See all 98

Metadata

Authors
Boe, A. J., McGee Koch, L. L., O’Brien, M. K., Shawen, N., Rogers, J. A., Lieber, R. L., Reid, K. J., Zee, P. C., & Jayaraman, A.
Affiliations
Northwestern University (US)
Corresponding author
Jayaraman, Arun
Venue
npj Digital Medicine
Published
2019-12-20
Volume
2
Issue
1
Pages
131-131
ISSN
2398-6352 (ISSN-L)
OpenAlex
W2996617683
Cited by
98
References
45
Citations by year
2026: 11 · 2025: 6 · 2024: 24 · 2023: 18 · 2022: 15 · 2021: 17 · 2020: 7
FWCI
4.36
Type
journal article
Language
en
Open access
Licence
Locations
  • npj Digital Medicine (publishedVersion, cc-by)
  • Europe PMC (PubMed Central) (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
Funders
U.S. Department of Health & Human Services | National Institutes of Health (T32GM008152)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
  • Physical Sciences › Engineering › Biomedical Engineering › Non-Invasive Vital Sign Monitoring
  • Social Sciences › Psychology › Experimental and Cognitive Psychology › Sleep and related disorders
Keywords
sleep stage classification, wearable sensors, wireless sensors, REM sleep detection, NREM sleep, hand acceleration, electrocardiogram, skin temperature, polysomnography alternative, sleep monitoring, sleep disorders

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Automating sleep stage classification using wireless, wearable sensors. https://app.cochat.ai/papers/10.1038/s41746-019-0210-1
The paper
Boe, A. J., McGee Koch, L. L., O’Brien, M. K., Shawen, N., Rogers, J. A., Lieber, R. L., Reid, K. J., Zee, P. C., & Jayaraman, A. (2019). Automating sleep stage classification using wireless, wearable sensors. npj Digital Medicine. https://doi.org/10.1038/s41746-019-0210-1

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.