Heart Rate Variability to Automatically Identify Hyperbaric States Considering Respiratory Component

This study's primary objective was to identify individuals whose physiological responses deviated from the rest of the study population by automatically monitoring atmospheric pressure levels to which they are exposed and using parameters derived from their heart rate variability (HRV). To achieve this, 28 volunteers were placed in a dry hyperbaric chamber, where they experienced varying pressures from 1 to 5 atmospheres, with five sequential stops lasting five minutes each at different atmospheric pressures. The HRV was dissected into two components: the respiratory component, which is linked to respiration; and the residual component, which is influenced by factors beyond respiration. Nine parameters were assessed, including the respiratory rate, four classic HRV temporal parameters, and four frequency parameters. A k-nearest neighbors classifier based on cosine distance successfully identified the atmospheric pressures to which the subjects were exposed to. The classifier achieved an 88.5% accuracy rate in distinguishing between the 5 atm and 3 atm stages using only four features: respiratory rate, heart rate, and two frequency parameters associated with the subjects' sympathetic responses. Furthermore, the study identified 6 out of 28 subjects as having atypical responses across all pressure levels when compared to the majority. Interestingly, two of these subjects stood out in terms of gender and having less prior diving experience, but they still exhibited normal responses to immersion. This suggests the potential for establishing distinct safety protocols for divers based on their previous experience and gender.

A Novel Sleep Staging Method Based on EEG and ECG Multimodal Features Combination

Accurate sleep staging evaluates the quality of sleep, supporting the clinical diagnosis and intervention of sleep disorders and related diseases. Although previous attempts to classify sleep stages have achieved high classification performance, little attention has been paid to integrating the rich information in brain and heart dynamics during sleep for sleep staging. In this study, we propose a generalized EEG and ECG multimodal feature combination to classify sleep stages with high efficiency and accuracy. Briefly, a hybrid features combination in terms of multiscale entropy and intrinsic mode function are used to reflect nonlinear dynamics in multichannel EEGs, along with heart rate variability measures over time/frequency domains, and sample entropy across scales are applied for ECGs. For both the max-relevance and min-redundancy method and principal component analysis were used for dimensionality reduction. The selected features were classified by four traditional machine learning classifiers. Macro-F1 score, macro-geometric mean, and Cohen kappa value are adopted to evaluate the classification performance of each class in an imbalanced dataset. Experimental results show that EEG features contribute more to wake stage classification while ECG features contribute more to deep sleep stages. The proposed combination achieves the highest accuracy of 84.3% and the highest kappa value of 0.794 on the support vector machine in the ISRUC-S3 dataset, suggesting the proposed multimodal features combination is promising in accuracy and efficiency compared to other state-of-the-art methods.

Multi-stage sleep classification using photoplethysmographic sensor

The conventional approach to monitoring sleep stages requires placing multiple sensors on patients, which is inconvenient for long-term monitoring and requires expert support. We propose a single-sensor photoplethysmographic (PPG)-based automated multi-stage sleep classification. This experimental study recorded the PPG during the entire night's sleep of 10 patients. Data analysis was performed to obtain 79 features from the recordings, which were then classified according to sleep stages. The classification results using support vector machine (SVM) with the polynomial kernel yielded an overall accuracy of 84.66%, 79.62% and 72.23% for two-, three- and four-stage sleep classification. These results show that it is possible to conduct sleep stage monitoring using only PPG. These findings open the opportunities for PPG-based wearable solutions for home-based automated sleep monitoring.

Automation of classification of sleep stages and estimation of sleep efficiency using actigraphy

Introduction

Sleep is a fundamental and essential physiological process for recovering physiological function. Sleep disturbance or deprivation has been known to be a causative factor of various physiological and psychological disorders. Therefore, sleep evaluation is vital for diagnosing or monitoring those disorders. Although PSG (polysomnography) has been the gold standard for assessing sleep quality and classifying sleep stages, PSG has various limitations for common uses. In substitution for PSG, there has been vigorous research using actigraphy.

Methods

For classifying sleep stages automatically, we propose machine learning models with HRV (heart rate variability)-related features and acceleration features, which were processed from the actigraphy (Maxim band) data. Those classification results were transformed into a binary classification for estimating sleep efficiency. With 30 subjects, we conducted PSG, and they slept overnight with wrist-type actigraphy. We assessed the performance of four proposed machine learning models.

Results

With HRV-related and raw features of actigraphy, Cohen's kappa was 0.974 (p < 0.001) for classifying sleep stages into five stages: wake (W), REM (Rapid Eye Movement) (R), Sleep N1 (Non-Rapid Eye Movement Stage 1, S1), Sleep N2 (Non-Rapid Eye Movement Stage 2, S2), Sleep N3 (Non-Rapid Eye Movement Stage 3, S3). In addition, our machine learning model for the estimation of sleep efficiency showed an accuracy of 0.86.

Discussion

Our model demonstrated that automated sleep classification results could perfectly match the PSG results. Since models with acceleration features showed modest performance in differentiating some sleep stages, further research on acceleration features must be done. In addition, the sleep efficiency model demonstrated modest results. However, an investigation into the effects of HRV-derived and acceleration features is required.

Autonomic Nervous System characterization in hyperbaric environments considering respiratory component and non-linear analysis of Heart Rate Variability

OBJECTIVES

an evaluation of Principal Dynamic Mode (PDM) and Orthogonal Subspace Projection (OSP) methods to characterize the Autonomic Nervous System (ANS) response in three different hyperbaric environments was performed.

METHODS

ECG signals were recorded in two different stages (baseline and immersion) in three different hyperbaric environments: (a) inside a hyperbaric chamber, (b) in a controlled sea immersion, (c) in a real reservoir immersion. Time-domain parameters were extracted from the RR series of the ECG. From the Heart Rate Variability signal (HRV), classic Power Spectral Density (PSD), PDM (a non-linear analysis of HRV which is able to separate sympathetic and parasympathetic activities) and OSP (an analysis of HRV which is able to extract the respiratory component) methods were used to assess the ANS response.

RESULTS

PDM and OSP parameters follows the same trend when compared to the PSD ones for the hyperbaric chamber dataset. Comparing the three hyperbaric scenarios, significant differences were found: i) heart rate decreased and RMSSD increased in the hyperbaric chamber and the controlled dive, but they had the opposite behavior during the uncontrolled dive; ii) power in the OSP respiratory component was lower than power in the OSP residual component in cases a and c; iii) PDM and OSP methods showed a significant increase in sympathetic activity during both dives, but parasympathetic activity increased only during the uncontrolled dive.

CONCLUSIONS

PDM and OSP methods could be used as an alternative measurement of ANS response instead of the PSD method. OSP results indicate that most of the variation in the heart rate variability cannot be described by changes in the respiration, so changes in ANS response can be assigned to other factors. Time-domain parameters reflect vagal activation in the hyperbaric chamber and in the controlled dive because of the effect of pressure. In the uncontrolled dive, sympathetic activity seems to be dominant, due to the effects of other factors such as physical activity, the challenging environment, and the influence of breathing through the scuba mask during immersion. In sum, a careful description of the changes in all the possible factors that could affect the ANS response between baseline and immersion stages in hyperbaric environments is needed for better interpretation of the results.

A New Sleep Staging System for Type III Sleep Studies Equipped with a Tracheal Sound Sensor

Type III sleep studies record cardio-respiratory channels only. Compared with polysomnography, which also records electrophysiological channels, they present many advantages: they are less expensive, less time-consuming, and more likely to be performed at home. However, their accuracy is limited by missing sleep information. That is why many studies present specific cardio-respiratory parameters to assess the causal effects of sleep stages upon cardiac or respiratory activities. For this paper, we gathered many parameters proposed in literature, leading to 1,111 features. The pulse oximeter, the PneaVoX sensor (recording tracheal sounds), respiratory inductance plethysmography belts, the nasal cannula and the actimeter provided the 112 worthiest ones for automatic sleep scoring. Then, a 3-step model was implemented: classification with a multi-layer perceptron, sleep transition rules corrections (from the AASM guidelines), and sequence corrections using a Viterbi hidden Markov model. The whole process was trained and tested using 300 and 100 independent recordings provided from patients suspected of having sleep breathing disorders. Results indicated that the system achieves substantial agreement with manual scoring for classifications into 2 stages (wake vs. sleep: mean Cohen's Kappa of 0.63 and accuracy rate Acc of 87.8%) and 3 stages (wake vs. R stage vs. NREM stage: mean of 0.60 and Acc of 78.5%). It indicates that the method could provide information to help specialists while diagnosing sleep. The presented model had promising results and may enhance clinical diagnosis.

Automatic sleep staging using heart rate variability, body movements, and recurrent neural networks in a sleep disordered population

STUDY OBJECTIVES

To validate a previously developed sleep staging algorithm using heart rate variability (HRV) and body movements in an independent broad cohort of unselected sleep disordered patients.

METHODS

We applied a previously designed algorithm for automatic sleep staging using long short-term memory recurrent neural networks to model sleep architecture. The classifier uses 132 HRV features computed from electrocardiography and activity counts from accelerometry. We retrained our algorithm using two public datasets containing both healthy sleepers and sleep disordered patients. We then tested the performance of the algorithm on an independent hold-out validation set of sleep recordings from a wide range of sleep disorders collected in a tertiary sleep medicine center.

RESULTS

The classifier achieved substantial agreement on four-class sleep staging (wake/N1-N2/N3/rapid eye movement [REM]), with an average κ of 0.60 and accuracy of 75.9%. The performance of the sleep staging algorithm was significantly higher in insomnia patients (κ = 0.62, accuracy = 77.3%). Only in REM parasomnias, the performance was significantly lower (κ = 0.47, accuracy = 70.5%). For two-class wake/sleep classification, the classifier achieved a κ of 0.65, with a sensitivity (to wake) of 72.9% and specificity of 94.0%.

CONCLUSIONS

This study shows that the combination of HRV, body movements, and a state-of-the-art deep neural network can reach substantial agreement in automatic sleep staging compared with polysomnography, even in patients suffering from a multitude of sleep disorders. The physiological signals required can be obtained in various ways, including non-obtrusive wrist-worn sensors, opening up new avenues for clinical diagnostics.

A review on current trends in automatic sleep staging through bio-signal recordings and future challenges

Sleep staging is a vital process conducted in order to analyze polysomnographic data. To facilitate prompt interpretation of these recordings, many automatic sleep staging methods have been proposed. These methods rely on bio-signal recordings, which include electroencephalography, electrocardiography, electromyography, electrooculography, respiratory, pulse oximetry and others. However, advanced, uncomplicated and swift sleep-staging-evaluation is still needed in order to improve the existing polysomnographic data interpretation. The present review focuses on automatic sleep staging methods through bio-signal recording including current and future challenges.

Wearable monitoring of sleep-disordered breathing: estimation of the apnea-hypopnea index using wrist-worn reflective photoplethysmography

A large part of the worldwide population suffers from obstructive sleep apnea (OSA), a disorder impairing the restorative function of sleep and constituting a risk factor for several cardiovascular pathologies. The standard diagnostic metric to define OSA is the apnea-hypopnea index (AHI), typically obtained by manually annotating polysomnographic recordings. However, this clinical procedure cannot be employed for screening and for long-term monitoring of OSA due to its obtrusiveness and cost. Here, we propose an automatic unobtrusive AHI estimation method fully based on wrist-worn reflective photoplethysmography (rPPG), employing a deep learning model exploiting cardiorespiratory and sleep information extracted from the rPPG signal trained with 250 recordings. We tested our method with an independent set of 188 heterogeneously disordered clinical recordings and we found it estimates the AHI with a good agreement to the gold standard polysomnography reference (correlation = 0.61, estimation error = 3±10 events/h). The estimated AHI was shown to reliably assess OSA severity (weighted Cohen's kappa = 0.51) and screen for OSA (ROC-AUC = 0.84/0.86/0.85 for mild/moderate/severe OSA). These findings suggest that wrist-worn rPPG measurements that can be implemented in wearables such as smartwatches, have the potential to complement standard OSA diagnostic techniques by allowing unobtrusive sleep and respiratory monitoring.

Automatic Sleep Disorders Classification Using Ensemble of Bagged Tree Based on Sleep Quality Features

Sleep disorder is a medical disease of the sleep patterns, which commonly suffered by the elderly. Sleep disorders diagnosis and treatment are considered to be challenging due to a time-consuming and inconvenient process for the patient. Moreover, the use of Polysomnography (PSG) in sleep disorder diagnosis is a high-cost process. Therefore, we propose an efficient classification method of sleep disorder by merely using electrocardiography (ECG) signals to simplify the sleep disorders diagnosis process. Different from many current related studies that applied a five-minute epoch to observe the main frequency band of the ECG signal, we perform a pre-processing technique that suitable for the 30-seconds epoch of the ECG signal. By this simplification, the proposed method has a low computational cost so that suitable to be implemented in an embedded hardware device. Structurally, the proposed method consists of five stages: (1) pre-processing, (2) spectral features extraction, (3) sleep stage detection using the Decision-Tree-Based Support Vector Machine (DTB-SVM), (4) assess the sleep quality features, and (5) sleep disorders classification using ensemble of bagged tree classifiers. We evaluate the effectiveness of the proposed method in the task of classifying the sleep disorders into four classes (insomnia, Sleep-Disordered Breathing (SDB), REM Behavior Disorder (RBD), and healthy subjects) from the 51 patients of the Cyclic Alternating Pattern (CAP) sleep data. Based on experimental results, the proposed method presents 84.01% of sensitivity, 94.17% of specificity, 86.27% of overall accuracy, and 0.70 of Cohen’s kappa. This result indicates that the proposed method able to reliably classify the sleep disorders merely using the 30-seconds epoch ECG in order to address the issue of a multichannel signal such as the PSG.

Sleep-Wake Classification using Statistical Features Extracted from Photoplethysmographic Signals

Sleep quality has a significant impact on human mental and physical health. Detecting sleep-wake stages is of paramount importance in the study of sleep. The gold standard method for sleep-wake stages classification is the multi-sensors based polysomnography (PSG) systems, which is normally recorded in clinical settings. The main drawback of PSG is the inconvenience to the subjects and can hamper the normal sleep. This paper describes an automated approach for classifying sleep-wake stages using finger-tip photoplethysmographic (PPG) signal. The proposed system used statistical features of PPG signal and supervised machine learning models including K-nearest neighbors (KNN) and support vector machine (SVM). The models are trained using 80% events (3486 sleep-wake events) from the dataset and the rest 20% events (872 sleep-wake events) are used for testing. On the test events, cubic KNN, weighted KNN, quadratic SVM and medium Gaussian SVM show 69.27%, 70.53%, 71.33% and 72.36% overall accuracy respectively for predicting the sleep and wake stages. This result advocates that the statistical features of PPG are capable of recognizing the changes in physiological states. The KNN and SVM classifier adopt the statistical features from PPG signal to differentiate between the wake and sleep stages.

Estimation of the apnea-hypopnea index in a heterogeneous sleep-disordered population using optimised cardiovascular features

Obstructive sleep apnea (OSA) is a highly prevalent sleep disorder, which results in daytime symptoms, a reduced quality of life as well as long-term negative health consequences. OSA diagnosis and severity rating is typically based on the apnea-hypopnea index (AHI) retrieved from overnight poly(somno)graphy. However, polysomnography is costly, obtrusive and not suitable for long-term recordings. Here, we present a method for unobtrusive estimation of the AHI using ECG-based features to detect OSA-related events. Moreover, adding ECG-based sleep/wake scoring yields a fully automatic method for AHI-estimation. Importantly, our algorithm was developed and validated on a combination of clinical datasets, including datasets selectively including OSA-pathology but also a heterogeneous, “real-world” clinical sleep disordered population (262 participants in the validation set). The algorithm provides a good representation of the current gold standard AHI (0.72 correlation, estimation error of 0.56 ± 14.74 events/h), and can also be employed as a screening tool for a large range of OSA severities (ROC AUC ≥ 0.86, Cohen’s kappa ≥ 0.53 and precision ≥70%). The method compares favourably to other OSA monitoring strategies, showing the feasibility of cardiovascular-based surrogates for sleep monitoring to evolve into clinically usable tools.

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

Automated sleep stage classification using heart rate variability (HRV) may provide an ergonomic and low-cost alternative to gold standard polysomnography, creating possibilities for unobtrusive home-based sleep monitoring. Current methods however are limited in their ability to take into account long-term sleep architectural patterns. A long short-term memory (LSTM) network is proposed as a solution to model long-term cardiac sleep architecture information and validated on a comprehensive data set (292 participants, 584 nights, 541.214 annotated 30 s sleep segments) comprising a wide range of ages and pathological profiles, annotated according to the Rechtschaffen and Kales (R&K) annotation standard. It is shown that the model outperforms state-of-the-art approaches which were often limited to non-temporal or short-term recurrent classifiers. The model achieves a Cohen’s k of 0.61 ± 0.15 and accuracy of 77.00 ± 8.90% across the entire database. Further analysis revealed that the performance for individuals aged 50 years and older may decline. These results demonstrate the merit of deep temporal modelling using a diverse data set and advance the state-of-the-art for HRV-based sleep stage classification. Further research is warranted into individuals over the age of 50 as performance tends to worsen in this sub-population.

Photoplethysmographic Waveform Versus Heart Rate Variability to Identify Low-Stress States: Attention Test

Our long-term goal is the development of an automatic identifier of attentional states. In order to accomplish it, we should first be able to identify different states based on physiological signals. So, the first aim of this paper is to identify the most appropriate features to detect a subject's high performance state. For that, a database of electrocardiographic (ECG) and photoplethysmographic (PPG) signals is recorded in two unequivocally defined states (rest and attention task) from up to 50 subjects as a sample of the population. Time and frequency parameters of heart/pulse rate variability have been computed from the ECG/PPG signals, respectively. Additionally, the respiratory rate has been estimated from both signals and also six morphological parameters from PPG. In total, 26 features are obtained for each subject. They provide information about the autonomic nervous system and the physiological response of the subject to an attention demand task. Results show an increase of sympathetic activation when the subjects perform the attention test. The amplitude and width of the PPG pulse were more sensitive than the classical sympathetic markers ([Formula: see text] and [Formula: see text]) for identifying this attentional state. State classification accuracy reaches a mean of [Formula: see text], a maximum of [Formula: see text], and a minimum of 85%, in the 100 classifications made by only selecting four parameters extracted from the PPG signal (pulse amplitude, pulsewidth, pulse downward slope, and mean pulse rate). These results suggest that attentional states could be identified by PPG.

Autonomic Nervous System Measurement in Hyperbaric Environments Using ECG and PPG Signals

The main aim of this paper was to characterize the Autonomic Nervous System response in hyperbaric environments using electrocardiogram (ECG) and pulse-photoplethysmogram (PPG) signals. To that end, 26 subjects were introduced into a hyperbaric chamber and five stages with different atmospheric pressures (1 atm; descent to 3 and 5 atm; ascent to 3 and 1 atm) were recorded. Respiratory information was extracted from the ECG and PPG signals and a combined respiratory rate was studied. This information was also used to analyze Heart Rate Variability (HRV) and Pulse Rate Variability (PRV). The database was cleaned by eliminating those cases where the respiratory rate dropped into the low frequency band (LF: 0.04-0.15 Hz) and those in which there was a discrepancy between the respiratory rates estimated using the ECG and PPG signals. Classical temporal and frequency indices were calculated in such cases. The ECG results showed a time-related dependency, with the heart rate and sympathetic markers (normalized power in LF and LF/HF ratio) decreasing as more time was spent inside the hyperbaric environment. A dependence between the atmospheric pressure and the parasympathetic response, as reflected in the high-frequency band power (HF: 0.15-0.40 Hz), was also found, with power increasing with atmospheric pressure. The combined respiratory rate also reached a maximum in the deepest stage; thus, highlighting a significant difference between this stage and the first one. The PPG data gave similar findings and also allowed the oxygen saturation to be computed; therefore, we propose the use of this signal for future studies in hyperbaric environments.

Electrodermal activity patterns in sleep stages and their utility for sleep versus wake classification

As the prevalence of sleep disorders is increasing, new methods for ambulatory sleep measurement are required. This paper presents electrodermal activity in different sleep stages and a sleep detection algorithm based on electrodermal activity. We analysed electrodermal activity and polysomnographic data of 43 healthy subjects and 48 patients with sleep disorders. Electrodermal activity was measured using an ambulatory device worn at the wrist. Two parameters to describe electrodermal activity were defined based on previous literature: EDASEF (electrodermal activity-smoothed feature) as parameter for skin conductance level; and EDAcounts (number of electrodermal activity-peaks) as skin conductance responses. Analysis of variance indicated significant EDASEF differences between the sleep stages wake versus N1, wake versus N2, wake versus slow-wave sleep, and wake versus rapid eye movement. The analysis of EDAcounts also showed significant differences, especially in the stages slow-wave sleep versus rapid eye movement. Between healthy subjects and patients, a significant disparity of EDAcounts was revealed in stage N1. Furthermore, the variances of EDASEF and EDAcounts in N1, N2 slow-wave sleep and rapid eye movement were higher in the patient group (p [F test] < .05). Next, an electrodermal activity-based sleep/wake discriminating algorithm was constructed. The optimized algorithm achieved an average sensitivity and specificity for sleep detection of 97% and 75%. The epoch agreement rate (average accuracy) was 86%. These outcomes are comparative to sleep detection algorithms based on actigraphy or heart rate variability. The results of this study indicate that electrodermal activity is not only a robust parameter for describing sleep, but also a potential suitable method for ambulatory sleep monitoring.

Validation of Photoplethysmography-Based Sleep Staging Compared With Polysomnography in Healthy Middle-Aged Adults

Study Objectives

To compare the accuracy of automatic sleep staging based on heart rate variability measured from photoplethysmography (PPG) combined with body movements measured with an accelerometer, with polysomnography (PSG) and actigraphy.

Methods

Using wrist-worn PPG to analyze heart rate variability and an accelerometer to measure body movements, sleep stages and sleep statistics were automatically computed from overnight recordings. Sleep-wake, 4-class (wake/N1 + N2/N3/REM) and 3-class (wake/NREM/REM) classifiers were trained on 135 simultaneously recorded PSG and PPG recordings of 101 healthy participants and validated on 80 recordings of 51 healthy middle-aged adults. Epoch-by-epoch agreement and sleep statistics were compared with actigraphy for a subset of the validation set.

Results

The sleep-wake classifier obtained an epoch-by-epoch Cohen's κ between PPG and PSG sleep stages of 0.55 ± 0.14, sensitivity to wake of 58.2 ± 17.3%, and accuracy of 91.5 ± 5.1%. κ and sensitivity were significantly higher than with actigraphy (0.40 ± 0.15 and 45.5 ± 19.3%, respectively). The 3-class classifier achieved a κ of 0.46 ± 0.15 and accuracy of 72.9 ± 8.3%, and the 4-class classifier, a κ of 0.42 ± 0.12 and accuracy of 59.3 ± 8.5%.

Conclusions

The moderate epoch-by-epoch agreement and, in particular, the good agreement in terms of sleep statistics suggest that this technique is promising for long-term sleep monitoring, although more evidence is needed to understand whether it can complement PSG in clinical practice. It also offers an improvement in sleep/wake detection over actigraphy for healthy individuals, although this must be confirmed on a larger, clinical population.

Inclusion of Respiratory Frequency Information in Heart Rate Variability Analysis for Stress Assessment

Respiratory rate and heart rate variability (HRV) are studied as stress markers in a database of young healthy volunteers subjected to acute emotional stress, induced by a modification of the Trier Social Stress Test. First, instantaneous frequency domain HRV parameters are computed using time-frequency analysis in the classical bands. Then, the respiratory rate is estimated and this information is included in HRV analysis in two ways: 1) redefining the high-frequency (HF) band to be centered at respiratory frequency; 2) excluding from the analysis those instants where respiratory frequency falls within the low-frequency (LF) band. Classical frequency domain HRV indices scarcely show statistical differences during stress. However, when including respiratory frequency information in HRV analysis, the normalized LF power as well as the LF/HF ratio significantly increase during stress ( p-value 0.05 according to the Wilcoxon test), revealing higher sympathetic dominance. The LF power increases during stress, only being significantly different in a stress anticipation stage, while the HF power decreases during stress, only being significantly different during the stress task demanding attention. Our results support that joint analysis of respiration and HRV obtains a more reliable characterization of autonomic nervous response to stress. In addition, the respiratory rate is observed to be higher and less stable during stress than during relax ( p-value 0.05 according to the Wilcoxon test) being the most discriminative index for stress stratification (AUC = 88.2 % ).

Improving sleep/wake detection via boundary adaptation for respiratory spectral features

In previous work, respiratory spectral features have been successfully used for sleep/wake detection. They are usually extracted from several frequency bands. However, these traditional bands with fixed frequency boundaries might not be the most appropriate to optimize the sleep and wake separation. This is caused by the between-subject variability in physiology, or more specifically, in respiration during sleep. Since the optimal boundaries may relate to mean respiratory frequency over the entire night. Therefore, we propose to adapt these boundaries for each subject in terms of his/her mean respiratory frequency. The adaptive boundaries were considered as those being able to maximize the separation between sleep and wake states by means of their mean power spectral density (PSD) curves overnight. Linear regression models were used to address the association between the adaptive boundaries and mean respiratory frequency based on training data. This was then in turn used to estimate the adaptive boundaries of each test subject. Experiments were conducted on the data from 15 healthy subjects using a linear discriminant classifier with a leave-one-subject-out cross-validation. We reveal that the spectral boundary adaptation can help improve the performance of sleep/wake detection when actigraphy is absent.

Automatic detection of overnight deep sleep based on heart rate variability: a preliminary study

This preliminary study investigated the use of cardiac information or more specifically, heart rate variability (HRV), for automatic deep sleep detection throughout the night. The HRV data can be derived from cardiac signals, which were obtained from polysomnography (PSG) recordings. In total 42 features were extracted from the HRV data of 15 single-night PSG recordings (from 15 healthy subjects) for each 30-s epoch, used to perform epoch-by-epoch classification of deep sleep and non-deep sleep (including wake state and all the other sleep stages except deep sleep). To reduce variation of cardiac physiology between subjects, we normalized each feature per subject using a simple Z-score normalization method by subtracting the mean and dividing by the standard deviation of the feature values. A correlation-based feature selection (CFS) method was employed to select informative features as well as removing feature redundancy and a linear discriminant (LD) classifier was applied for deep and non-deep sleep classification. Results show that the use of Z-score normalization can significantly improve the classification performance. A Cohen's Kappa coefficient of 0.42 and an overall accuracy of 81.3% based on a leave-one-subject-out cross-validation were achieved.