Sleep stage classification from heart-rate variability using long short-term memory neural networks

Radha, Mustafa; Fonseca, Pedro; Moreau, Arnaud; Ross, Marco; Cerny, Andreas; Anderer, P.; Long, Xi; Aarts, Ronald M.

doi:10.1038/s41598-019-49703-y

Cited by 134 publications

(117 citation statements)

References 57 publications

Supporting

Mentioning

111

Contrasting

Order By: Relevance

“…The current state-of-the-art results extract dozens, if not hundreds, of expert-informed engineered features from physiological signals such as ECG/PPG and then use these as inputs to complex machine learning models to predict sleep stages [19][20][21][22] . The models either use features of neighboring time epochs explicitly to predict the stage for each time epoch 19 or use implicitly temporal models such as recurrent neural networks (RNNs) 20 . Such models have two important drawbacks that we address with our novel architecture: strength of the correlation is between cardiac features and PSG sleep stages it is not known a priori.…”

Section: Discussionmentioning

confidence: 99%

Deep learning for automated sleep staging using instantaneous heart rate

et al. 2020

View full text Add to dashboard Cite

Clinical sleep evaluations currently require multimodal data collection and manual review by human experts, making them expensive and unsuitable for longer term studies. Sleep staging using cardiac rhythm is an active area of research because it can be measured much more easily using a wide variety of both medical and consumer-grade devices. In this study, we applied deep learning methods to create an algorithm for automated sleep stage scoring using the instantaneous heart rate (IHR) time series extracted from the electrocardiogram (ECG). We trained and validated an algorithm on over 10,000 nights of data from the Sleep Heart Health Study (SHHS) and Multi-Ethnic Study of Atherosclerosis (MESA). The algorithm has an overall performance of 0.77 accuracy and 0.66 kappa against the reference stages on a held-out portion of the SHHS dataset for classifying every 30 s of sleep into four classes: wake, light sleep, deep sleep, and rapid eye movement (REM). Moreover, we demonstrate that the algorithm generalizes well to an independent dataset of 993 subjects labeled by American Academy of Sleep Medicine (AASM) licensed clinical staff at Massachusetts General Hospital that was not used for training or validation. Finally, we demonstrate that the stages predicted by our algorithm can reproduce previous clinical studies correlating sleep stages with comorbidities such as sleep apnea and hypertension as well as demographics such as age and gender.

show abstract

Section: Discussionmentioning

confidence: 99%

Deep learning for automated sleep staging using instantaneous heart rate

et al. 2020

View full text Add to dashboard Cite

show abstract

“…In the case of the four-stage sleep stages, light sleep (N1 and N2) is classified into one category. The recognition accuracy was 89% for four-stage cases and 78% for five-stage cases, higher than conventional studies with 69% [ 27 ] and 67% accuracy [ 28 , 29 , 30 ]. This also shows that our HRV estimation algorithm is sufficient for sleep stage classification.…”

Section: Discussionmentioning

confidence: 61%

“…This leads to the development of automatic sleep stage classification. Unfortunately, conventional algorithms utilizing heart rate features did not have a high accuracy for five-stage sleep stage classification [ 28 , 29 , 30 ]. Some studies tried combine sleep stages to simplify the problem.…”

Section: Discussionmentioning

confidence: 99%

“…Conventional studies of sleep stage classification tend to have low accuracy for in this respect, especially for five-stage classification. In recent years, Wei et al [ 28 ] and Radha et al [ 29 ] proposed a deep learning approach for sleep stage classification, utilizing heart rate features. The authors of [ 30 ] compare different machine learning models utilizing ECG features.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Sleep Stage Estimation from Bed Leg Ballistocardiogram Sensors

Mitsukura

Sumali

Nagura

et al. 2020

Sensors

View full text Add to dashboard Cite

Ballistocardiogram (BCG) is a graphical representation of the subtle oscillations in body movements caused by cardiovascular activity. Although BCGs cause less burden to the user, electrocardiograms (ECGs) are still commonly used in the clinical scene due to BCG sensors’ noise sensitivity. In this paper, a robust method for sleep time BCG measurement and a mathematical model for predicting sleep stages using BCG are described. The novel BCG measurement algorithm can be described in three steps: preprocessing, creation of heartbeat signal template, and template matching for heart rate variability detection. The effectiveness of this algorithm was validated with 99 datasets from 36 subjects, with photoplethysmography (PPG) to compute ground truth heart rate variability (HRV). On average, 86.9% of the inter-beat intervals were detected and the mean error was 8.5ms. This shows that our method successfully extracted beat-to-beat intervals from BCG during sleep, making its usability comparable to those of clinical ECGs. Consequently, compared to other conventional BCG systems, even more accurate sleep heart rate monitoring with a smaller burden to the patient is available. Moreover, the accuracy of the sleep stages mathematical model, validated with 100 datasets from 25 subjects, is 80%, which is higher than conventional five-stage sleep classification algorithms (max: 69%). Although, in this paper, we applied the mathematical model to heart rate interval features from BCG, theoretically, this sleep stage prediction algorithm can also be applied to ECG-extracted heart rate intervals.

show abstract

“…However, different modalities and the information they collect may be highly complementary and, in practice, aggregating sleep data from various sources may make models more robust and tolerant both to noise and missing data. Such complementary fusion protocols have been shown to significantly improve the classification performance of sleep stages 79,80 .…”

Section: Sleep Monitoring Outside the Laboratorymentioning

confidence: 99%

The future of sleep health: a data-driven revolution in sleep science and medicine

et al. 2020

View full text Add to dashboard Cite

In recent years, there has been a significant expansion in the development and use of multi-modal sensors and technologies to monitor physical activity, sleep and circadian rhythms. These developments make accurate sleep monitoring at scale a possibility for the first time. Vast amounts of multi-sensor data are being generated with potential applications ranging from large-scale epidemiological research linking sleep patterns to disease, to wellness applications, including the sleep coaching of individuals with chronic conditions. However, in order to realise the full potential of these technologies for individuals, medicine and research, several significant challenges must be overcome. There are important outstanding questions regarding performance evaluation, as well as data storage, curation, processing, integration, modelling and interpretation. Here, we leverage expertise across neuroscience, clinical medicine, bioengineering, electrical engineering, epidemiology, computer science, mHealth and human-computer interaction to discuss the digitisation of sleep from a inter-disciplinary perspective. We introduce the state-ofthe-art in sleep-monitoring technologies, and discuss the opportunities and challenges from data acquisition to the eventual application of insights in clinical and consumer settings. Further, we explore the strengths and limitations of current and emerging sensing methods with a particular focus on novel data-driven technologies, such as Artificial Intelligence.

show abstract

Sleep stage classification from heart-rate variability using long short-term memory neural networks

Cited by 134 publications

References 57 publications

Deep learning for automated sleep staging using instantaneous heart rate

Deep learning for automated sleep staging using instantaneous heart rate

Sleep Stage Estimation from Bed Leg Ballistocardiogram Sensors

The future of sleep health: a data-driven revolution in sleep science and medicine

Contact Info

Product

Resources

About