Sleep Stage Classification by a Combination of Actigraphic and Heart Rate Signals

Yuda, Emi; Yoshida, Yutaka; Sasanabe, Ryujiro; Shiomi, Toshiaki; Hayano, Junichiro

doi:10.3390/jlpea7040028

Cited by 19 publications

(11 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…89,90 Combining heart rate variability with accelerometry data may help improve the accuracy of sleep measurement; however, the results to date do not suggest that combining these technologies improves sleep measurement. 91,92 Interestingly, the latest generation of wearable devices are now capable of measuring cardiac activity via photoplethysmography optical sensors, wherein these sensors provide a supplement to accelerometry in the classification of sleep and wake. Preliminary investigations suggest that these devices provide comparable estimations of sleep versus wake to research-grade accelerometry devices.…”

Section: Novel Technologies For Measuring Time-use Activity Behaviourmentioning

confidence: 99%

A Wrinkle in Measuring Time Use for Cognitive Health: How should We Measure Physical Activity, Sedentary Behaviour and Sleep?

Falck

Davis

Khan

et al. 2021

American Journal of Lifestyle Medicine

View full text Add to dashboard Cite

One new case of dementia is detected every 4 seconds and no effective drug therapy exists. Effective behavioural strategies to promote healthy cognitive ageing are thus essential. Three behaviours related to cognitive health which we all engage in daily are physical activity, sedentary behaviour and sleep. These time-use activity behaviours are linked to cognitive health in a complex and dynamic relationship not yet fully elucidated. Understanding how each of these behaviours is related to each other and cognitive health will help determine the most practical and effective lifestyle strategies for promoting healthy cognitive ageing. In this review, we discuss methods and analytical approaches to best investigate how these time-use activity behaviours are related to cognitive health. We highlight four key recommendations for examining these relationships such that researchers should include measures which (1) are psychometrically appropriate; (2) can specifically answer the research question; (3) include objective and subjective estimates of the behaviour and (4) choose an analytical method for modelling the relationships of time-use activity behaviours with cognitive health which is appropriate for their research question.

show abstract

Section: Novel Technologies For Measuring Time-use Activity Behaviourmentioning

confidence: 99%

A Wrinkle in Measuring Time Use for Cognitive Health: How should We Measure Physical Activity, Sedentary Behaviour and Sleep?

Falck

Davis

Khan

et al. 2021

American Journal of Lifestyle Medicine

View full text Add to dashboard Cite

show abstract

“…Yucelbas, S., et al compared the results of four different classification methods to classify 3-class sleep staging for healthy people, achieving the highest accuracy of 87.11%, but only 78.08% for patients with obstructive sleep apnea [17]. While another research using ECG and acceleration signals only achieved the accuracy of 74.5% [18]. Since the RRV based features can be extracted from ECG signals [19], the sleep staging methods involved HRV and RRV features can be simply implemented by using single-lead ECG signals.…”

Section: Introductionmentioning

confidence: 99%

A Multi-Class Automatic Sleep Staging Method Based on Long Short-Term Memory Network Using Single-Lead Electrocardiogram Signals

et al. 2019

View full text Add to dashboard Cite

To overcome the disadvantage of clinical manual sleep staging, a convenient, economical, and efficient multi-class automatic sleep staging method is proposed based on long short-term memory network (LSTM) using single-lead electrocardiogram signals. From electrocardiogram signals, heart rate variability and respiratory signals were calculated, and, then, totally 25 features were extracted. Four different classifiers, including the two-class classifier to distinguish between wake and sleep, the three-class classifier to distinguish wake, non-rapid eye movement sleep, and rapid eye movement, the four-class classifier to distinguish wake, light sleep, slow wave sleep, and rapid eye movement, and the five-class classifier to distinguish wake, sleep stage N1, sleep stage N2, sleep stage N3, and rapid eye movement, were constructed using the LSTM. The single-lead electrocardiogram data from 238 patients with full sleep stages during sleep were used for the training set and the data from other 60 patients were regarded as a validation set. The rest of 75 patients have left aside for testing set. The accuracy of two-class, three-class, four-class, and five-class sleep staging was 89.84%, 84.07%, 77.76%, and 71.16% and the Cohen's kappa statistic k was 0.52, 0.58, 0.55, and 0.52, respectively, which realized the moderate agreement with clinical analysis. When expanding the dataset to extra 1068 patients with missing sleep stages, the accuracy has no obvious reduction but the Cohen's kappa statistic k dropped to 0.51, 0.52, 0.48, and 0.43, respectively. The proposed method, in this paper, is promising for low-cost, efficient, and convenient sleep staging in home care monitoring. INDEX TERMS Electrocardiogram, heart rate variability, long short-term memory, sleep staging.

show abstract

“…For example, during non-rapid eye movement (REM) sleep, there is an increase in high-frequency power and a decrease in low-frequency power of heart rate variability; during REM sleep and wake, the opposite is true. [12][13][14] Studies using research-grade devices have demonstrated the benefits of heart rate and heart rate variability assessment for sleep classification. [12][13][14] However, it remains less clear whether the addition of heart rate and heart rate variability measurement adds to the accuracy of sleep detection in consumer wearable devices.…”

Section: Introductionmentioning

confidence: 99%

“…[12][13][14] Studies using research-grade devices have demonstrated the benefits of heart rate and heart rate variability assessment for sleep classification. [12][13][14] However, it remains less clear whether the addition of heart rate and heart rate variability measurement adds to the accuracy of sleep detection in consumer wearable devices. Results from several studies suggest that consumer wearable devices with heart rate technology are comparable to actigraphy for the differentiation between sleep and wake, but accurate detection of sleep stages remains poor.…”

Section: Introductionmentioning

confidence: 99%

Validation of sleep measurement in a multisensor consumer grade wearable device in healthy young adults

Kanady

Ruoff

Straus

et al. 2020

Journal of Clinical Sleep Medicine

View full text Add to dashboard Cite

Study Objectives: Our objective was to examine the ability of a consumer-grade wearable device (Basis B1) with accelerometer and heart rate technology to assess sleep patterns compared with polysomnography (PSG) and research-grade actigraphy in healthy adults. Methods: Eighteen adults underwent consecutive nights of sleep monitoring using Basis B1, actigraphy, and PSG; 40 nights were used in analyses. Discrepancies in gross sleep parameters and epoch-by-epoch agreements in sleep/wake classification were assessed. Results: Basis B1 accuracy was 54.20 ± 8.20%, sensitivity was 98.90 ± 2.70%, and specificity was 8.10 ± 15.00%. Accuracy, sensitivity, and specificity for distinguishing between the different sleep stages were 60-72%, 48-62%, and 57-86%, respectively. Pearson correlations demonstrated strong associations between Basis B1 and PSG estimates of sleep onset latency and total sleep time; moderate associations for sleep efficiency, duration of light sleep, and duration of rapid eye movement sleep; and a weak association for duration of deep sleep. Basis B1 significantly overestimates total sleep time, sleep efficiency, and duration of light sleep and significantly underestimates wake after sleep onset and duration of deep sleep. Conclusions: Basis B1 demonstrated utility for estimates of gross sleep parameters and performed similarly to actigraphy for estimates of total sleep time. Basis B1 specificity was poor, and Basis B1 is not useful for the assessment of wake. Basis B1 accuracy for sleep stages was better than chance but is not a suitable replacement for PSG assessment. Despite low cost, ease of use, and attractiveness for patients, consumer devices are not yet accurate or reliable enough to guide treatment decision making in clinical settings.

show abstract

Sleep Stage Classification by a Combination of Actigraphic and Heart Rate Signals

Cited by 19 publications

References 18 publications

A Wrinkle in Measuring Time Use for Cognitive Health: How should We Measure Physical Activity, Sedentary Behaviour and Sleep?

A Wrinkle in Measuring Time Use for Cognitive Health: How should We Measure Physical Activity, Sedentary Behaviour and Sleep?

A Multi-Class Automatic Sleep Staging Method Based on Long Short-Term Memory Network Using Single-Lead Electrocardiogram Signals

Validation of sleep measurement in a multisensor consumer grade wearable device in healthy young adults

Contact Info

Product

Resources

About