Interbeat interval-based sleep staging: work in progress toward real-time implementation

Sleep staging algorithm based on smartwatch sensors for healthy and sleep apnea populations

OBJECTIVE

Sleep stages can provide valuable insights into an individual's sleep quality. By leveraging movement and heart rate data collected by modern smartwatches, it is possible to enable the sleep staging feature and enhance users' understanding about their sleep and health conditions.

METHOD

In this paper, we present and validate a recurrent neural network based model with 23 input features extracted from accelerometer and photoplethysmography sensors data for both healthy and sleep apnea populations. We designed a lightweight and fast solution to enable the prediction of sleep stages for each 30-s epoch. This solution was developed using a large dataset of 1522 night recordings collected from a highly heterogeneous population and different versions of Samsung smartwatch.

RESULTS

In the classification of four sleep stages (wake, light, deep, and rapid eye movements sleep), the proposed solution achieved 71.6 % of balanced accuracy and a Cohen's kappa of 0.56 in a test set with 586 recordings.

CONCLUSION

The results presented in this paper validate our proposal as a competitive wearable solution for sleep staging. Additionally, the use of a large and diverse data set contributes to the robustness of our solution, and corroborates the validation of algorithm's performance. Some additional analysis performed for healthy and sleep apnea population demonstrated that algorithm's performance has low correlation with demographic variables.

Feasibility of Unobtrusively Estimating Blood Pressure Using Load Cells under the Legs of a Bed

The ability to monitor blood pressure unobtrusively and continuously, even during sleep, may promote the prevention of cardiovascular diseases, enable the early detection of cardiovascular risk, and facilitate the timely administration of treatment. Publicly available data from forty participants containing synchronously recorded signals from four force sensors (load cells located under each leg of a bed) and continuous blood pressure waveforms were leveraged in this research. The focus of this study was on using a deep neural network with load-cell data as input composed of three recurrent layers to reconstruct blood pressure (BP) waveforms. Systolic (SBP) and diastolic (DBP) blood pressure values were estimated from the reconstructed BP waveform. The dataset was partitioned into training, validation, and testing sets, such that the data from a given participant were only used in a single set. The BP waveform reconstruction performance resulted in an R2 of 0.61 and a mean absolute error < 0.1 mmHg. The estimation of the mean SBP and DBP values was characterized by Bland-Altman-derived limits of agreement in intervals of [-11.99 to 15.52 mmHg] and [-7.95 to +3.46 mmHg], respectively. These results may enable the detection of abnormally large or small variations in blood pressure, which indicate cardiovascular health degradation. The apparent contrast between the small reconstruction error and the limit-of-agreement width owes to the fact that reconstruction errors manifest more prominently at the maxima and minima, which are relevant for SBP and DBP estimation. While the focus here was on SBD and DBP estimation, reconstructing the entire BP waveform enables the calculation of additional hemodynamic parameters.

Automatic sleep stage classification based on two-channel EOG and one-channel EMG

OBJECTIVE

The sleep monitoring with Polysomnography (PSG) severely degrades the sleep quality. In order to reduce the load of sleep monitoring, an approach to automatic sleep stage classification without electroencephalogram (EEG) was proposed.

APPROACH

Totally 124 records from the public dataset ISRUC-Sleep with AASM standard were used, in which only 10 records were from the healthy group while the rest ones were from sleep disorder groups. The 124 records were collected from 116 subjects (8 subjects with two records for each subject, others with one record per subject) with their ages range in [20, 85] years. Totally 108 features were extracted from two-channel electrooculogram (EOG), and 6 features were extracted from one-channel electromyogram (EMG). A novel 'quasi-normalization' method was proposed and used for feature normalization. Then the random forest (RF) was used to classify five stages, including wakefulness, REM sleep, N1 sleep, N2 sleep and N3 sleep.

MAIN RESULTS

Using 114 normalized features from the combination of EOG (108 features) and EMG (6 features), the Cohen's kappa coefficient was 0.749 and the accuracy was 80.8% by leave-one-out cross-validation (LOOCV). As a reference for AASM standard using computer assisted method, the Cohen's kappa coefficient was 0.801 and the accuracy was 84.7% for the same dataset based on 438 normalized features from the combination of EEG (324 features), EOG (108 features) and EMG (6 features).

SIGNIFICANCE

The combination of EOG and EMG can reduce the load of sleep monitoring, and achieves comparable performances with the "gold standard" signals of EEG, EOG and EMG on sleep stage classification.