A sleep stage estimation algorithm based on cardiorespiratory signals derived from a suprasternal pressure sensor.

Automatic estimation of sleep structure is an important aspect in moving sleep monitoring from clinical laboratories to people's homes. However, the transition to more portable systems should not happen at the expense of important physiological signals, such as respiration. Here, we propose the use of cardiorespiratory signals obtained by a suprasternal pressure (SSP) sensor to estimate sleep stages. The sensor is already used for diagnosis of sleep-disordered breathing (SDB) conditions, but besides respiratory effort it can detect cardiac vibrations transmitted through the trachea. We collected the SSP sensor signal in 100 adults (57 male) undergoing clinical polysomnography for suspected sleep disorders, including sleep apnea syndrome, insomnia, and movement disorders. Here, we separate respiratory effort and cardiac activity related signals, then input these into a neural network trained to estimate sleep stages. Using the original mixed signal the results show a moderate agreement with manual scoring, with a Cohen's kappa of 0.53 in Wake/N1-N2/N3/rapid eye movement sleep discrimination and 0.62 in Wake/Sleep. We demonstrate that decoupling the two signals and using the cardiac signal to estimate the instantaneous heart rate improves the process considerably, reaching an agreement of 0.63 and 0.71. Our proposed method achieves high accuracy, specificity, and sensitivity across different sleep staging tasks. We also compare the total sleep time calculated with our method against manual scoring, with an average error of -1.83 min but a relatively large confidence interval of ±55 min. Compact systems that employ the SSP sensor information-rich signal may enable new ways of clinical assessments, such as night-to-night variability in obstructive sleep apnea and other sleep disorders.

Automated Scoring of Sleep and Associated Events.

Conventionally, sleep and associated events are scored visually by trained technologists according to the rules summarized in the American Academy of Sleep Medicine Manual. Since its first publication in 2007, the manual was continuously updated; the most recent version as of this writing was published in 2020. Human expert scoring is considered as gold standard, even though there is increasing evidence of limited interrater reliability between human scorers. Significant advances in machine learning have resulted in powerful methods for addressing complex classification problems such as automated scoring of sleep and associated events. Evidence is increasing that these autoscoring systems deliver performance comparable to manual scoring and offer several advantages to visual scoring: (1) avoidance of the rather expensive, time-consuming, and difficult visual scoring task that can be performed only by well-trained and experienced human scorers, (2) attainment of consistent scoring results, and (3) proposition of added value such as scoring in real time, sleep stage probabilities per epoch (hypnodensity), estimates of signal quality and sleep/wake-related features, identifications of periods with clinically relevant ambiguities (confidence trends), configurable sensitivity and rule settings, as well as cardiorespiratory sleep staging for home sleep apnea testing. This chapter describes the development of autoscoring systems since the first attempts in the 1970s up to the most recent solutions based on deep neural network approaches which achieve an accuracy that allows to use the autoscoring results directly for review and interpretation by a physician.

Procedural memory consolidation is associated with heart rate variability and sleep spindles.

Sleep and memory studies often focus on overnight rather than long-term memory changes, traditionally associating overnight memory change (OMC) with sleep architecture and sleep patterns such as spindles. In addition, (para-)sympathetic innervation has been associated with OMC after a daytime nap using heart rate variability (HRV). In this study we investigated overnight and long-term performance changes for procedural memory and evaluated associations with sleep architecture, spindle activity (SpA) and HRV measures (R-R interval [RRI], standard deviation of R-R intervals [SDNN], as well as spectral power for low [LF] and high frequencies [HF]). All participants (N = 20, Mage  = 23.40 ± 2.78 years) were trained on a mirror-tracing task and completed a control (normal vision) and learning (mirrored vision) condition. Performance was evaluated after training (R1), after a full-night sleep (R2) and 7 days thereafter (R3). Overnight changes (R2-R1) indicated significantly higher accuracy after sleep, whereas a significant long-term (R3-R2) improvement was only observed for tracing speed. Sleep architecture measures were not associated with OMC after correcting for multiple comparisons. However, individual SpA change from the control to the learning night indicated that only "SpA enhancers" exhibited overnight improvements for accuracy and long-term improvements for speed. HRV analyses revealed that lower SDNN and LF power was associated with better OMC for the procedural speed measure. Altogether, this study indicates that overnight improvement for procedural memory is specific for spindle enhancers, and is associated with HRV during sleep following procedural learning.

The effect of daytime napping and full-night sleep on the consolidation of declarative and procedural information.

Many studies investigating sleep and memory consolidation have evaluated full-night sleep rather than alternative sleep periods such as daytime naps. This multi-centre study followed up on, and was compared with, an earlier full-night study (Schabus et al., 2004) investigating the relevance of daytime naps for the consolidation of declarative and procedural memory. Seventy-six participants were randomly assigned to a nap or wake group, and performed a declarative word-pair association or procedural mirror-tracing task. Performance changes from before to after a 90-min retention interval filled with sleep or quiet wakefulness were evaluated between groups. Associations between performance changes, sleep architecture, spindles, and slow oscillations were investigated. For the declarative task we observed a trend towards stronger forgetting across a wake period compared with a nap period, and a trend towards memory increase over the full-night. For the procedural task, accuracy was significantly decreased following daytime wakefulness, showed a trend to increase with a daytime nap, and significantly increased across full-night sleep. For the nap protocol, neither sleep stages, spindles, nor slow oscillations predicted performance changes. A direct comparison of day and nighttime sleep revealed that daytime naps are characterized by significantly lower spindle density, but higher spindle activity and amplitude compared with full-night sleep. In summary, data indicate that daytime naps protect procedural memories from deterioration, whereas full-night sleep improves performance. Given behavioural and physiological differences between day and nighttime sleep, future studies should try to characterize potential differential effects of full-night and daytime sleep with regard to sleep-dependent memory consolidation.

Oscillatory theta activity during memory formation and its impact on overnight consolidation: a missing link?

Sleep has been shown to promote memory consolidation driven by certain oscillatory patterns, such as sleep spindles. However, sleep does not consolidate all newly encoded information uniformly but rather "selects" certain memories for consolidation. It is assumed that such selection depends on salience tags attached to the new memories before sleep. However, little is known about the underlying neuronal processes reflecting presleep memory tagging. The current study sought to address the question of whether event-related changes in spectral theta power (theta ERSP) during presleep memory formation could reflect memory tagging that influences subsequent consolidation during sleep. Twenty-four participants memorized 160 word pairs before sleep; in a separate laboratory visit, they performed a nonlearning control task. Memory performance was tested twice, directly before and after 8 hr of sleep. Results indicate that participants who improved their memory performance overnight displayed stronger theta ERSP during the memory task in comparison with the control task. They also displayed stronger memory task-related increases in fast sleep spindle activity. Furthermore, presleep theta activity was directly linked to fast sleep spindle activity, indicating that processes during memory formation might indeed reflect memory tagging that influences subsequent consolidation during sleep. Interestingly, our results further indicate that the suggested relation between sleep spindles and overnight performance change is not as direct as once believed. Rather, it appears to be mediated by processes beginning during presleep memory formation. We conclude that theta ERSP during presleep memory formation reflects cortico-hippocampal interactions that lead to a better long-term accessibility by tagging memories for sleep spindle-related reprocessing.

Advanced Analysis of Pharmaco-Sleep Data in Humans.

Pharmaco-sleep studies in humans aim at the description of the effects of drugs, most frequently substances that act on the central nervous system, by means of quantitative analysis of biosignals recorded in subjects during sleep. Up to 2007, the only standard for the classification of sleep macrostructure that found worldwide acceptance were the rules published in 1968 by Rechtschaffen and Kales. In May 2007, the AASM Manual for the Scoring of Sleep and Associated Events was published by the American Academy of Sleep Medicine, and concerning the classification of sleep stages, these new rules are supposed to replace those developed by Rechtschaffen and Kales. As compared to the rather low interrater reliability of manual sleep scoring, semiautomated approaches may achieve a reliability close to 1 (Cohen's kappa 0.99 for 2 semiautomated scorings as compared to 0.76 for 2 manual scorings) without any decline in validity. Depending on the aim of the pharmaco-sleep study, additional analyses concerning sleep fragmentation, sleep microstructure, sleep depth, sleep processes and local aspects of sleep should be considered. For some of these additional features, rules for visual scoring have been established, while for others automatic analysis is obligatory. Generally, for reasons of cost-effectiveness but also reliability, automatic analysis is preferable to visual analysis. However, the validity of the automatic method applied has to be proven.

The effects of aging on sleep architecture in healthy subjects.

This chapter presents normative data on healthy sleep, as measured by polysomnography (PSG), from "supernormal" subjects across the age range from 20 to about 90 years. The data originates from the SIESTA project database established in the late 1990s. While that data has been published and used in research in many ways, the novelty of the current analysis is (a) the focus on normative data following the latest sleep staging standard (AASM 2012), and (b) the results after narrowing down the data set by excluding outliers due to disturbed sleep pattern that can occur in a sleep lab and are thus not examples of "normal" sleep. Results demonstrate interesting dependencies of sleep architecture on age, in particular a reduction in total sleep time and changes in sleep stage distributions toward lighter sleep, which differ in detail between the two genders.

Estimating the Severity of Obstructive Sleep Apnea Using ECG, Respiratory Effort and Neural Networks.

OBJECTIVE: wearable sensor technology has progressed significantly in the last decade, but its clinical usability for the assessment of obstructive sleep apnea (OSA) is limited by the lack of large and representative datasets simultaneously acquired with polysomnography (PSG). The objective of this study was to explore the use of cardiorespiratory signals common in standard PSGs which can be easily measured with wearable sensors, to estimate the severity of OSA. METHODS: an artificial neural network was developed for detecting sleep disordered breathing events using electrocardiogram (ECG) and respiratory effort. The network was combined with a previously developed cardiorespiratory sleep staging algorithm and evaluated in terms of sleep staging classification performance, apnea-hypopnea index (AHI) estimation, and OSA severity estimation against PSG on a cohort of 653 participants with a wide range of OSA severity. RESULTS: four-class sleep staging achieved a κ of 0.69 versus PSG, distinguishing wake, combined N1-N2, N3 and REM. AHI estimation achieved an intraclass correlation coefficient of 0.91, and high diagnostic performance for different OSA severity thresholds. CONCLUSIONS: this study highlights the potential of using cardiorespiratory signals to estimate OSA severity, even without the need for airflow or oxygen saturation (SpO2), traditionally used for assessing OSA. SIGNIFICANCE: while further research is required to translate these findings to practical and unobtrusive sensors, this study demonstrates how existing, large datasets can serve as a foundation for wearable systems for OSA monitoring. Ultimately, this approach could enable long-term assessment of sleep disordered breathing, facilitating new avenues for clinical research in this field.

Performance of cardiorespiratory-based sleep staging in patients using beta blockers.

STUDY OBJECTIVES: Automatic sleep staging based on cardiorespiratory signals from home sleep monitoring devices holds great clinical potential. Using state-of-the-art machine learning, promising performance has been reached in patients with sleep disorders. However, it is unknown whether performance would hold in individuals with potentially altered autonomic physiology, for example under the influence of medication. Here, we assess an existing sleep staging algorithm in patients with sleep disorders with and without the use of beta blockers. METHODS: We analyzed a retrospective dataset of sleep recordings of 57 patients with sleep disorders using beta blockers and 57 age-matched patients with sleep disorders not using beta blockers. Sleep stages were automatically scored based on electrocardiography and respiratory effort from a thoracic belt, using a previously developed machine-learning algorithm (CReSS algorithm). For both patient groups, sleep stages classified by the model were compared to gold standard manual polysomnography scoring using epoch-by-epoch agreement. Additionally, for both groups, overall sleep parameters were calculated and compared between the two scoring methods. RESULTS: Substantial agreement was achieved for four-class sleep staging in both patient groups (beta blockers: kappa = 0.635, accuracy = 78.1%; controls: kappa = 0.660, accuracy = 78.8%). No statistical difference in epoch-by-epoch agreement was found between the two groups. Additionally, the groups did not differ on agreement of derived sleep parameters. CONCLUSIONS: We showed that the performance of the CReSS algorithm is not deteriorated in patients using beta blockers. Results do not indicate a fundamental limitation in leveraging autonomic characteristics to obtain a surrogate measure of sleep in this clinically relevant population. CITATION: Hermans L, van Meulen F, Anderer P, et al. Performance of cardiorespiratory-based sleep staging in patients using beta blockers. J Clin Sleep Med. 2024;20(4):575-581.

Guidelines for the recording and evaluation of pharmaco-sleep studies in man: the International Pharmaco-EEG Society (IPEG).

The International Pharmaco-EEG Society (IPEG) presents guidelines summarising the requirements for the recording and computerised evaluation of pharmaco-sleep data in man. Over the past years, technical and data-processing methods have advanced steadily, thus enhancing data quality and expanding the palette of sleep assessment tools that can be used to investigate the activity of drugs on the central nervous system (CNS), determine the time course of effects and pharmacodynamic properties of novel therapeutics, hence enabling the study of the pharmacokinetic/pharmacodynamic relationship, and evaluate the CNS penetration or toxicity of compounds. However, despite the presence of robust guidelines on the scoring of polysomnography -recordings, a review of the literature reveals inconsistent -aspects in the operating procedures from one study to another. While this fact does not invalidate results, the lack of standardisation constitutes a regrettable shortcoming, especially in the context of drug development programmes. The present guidelines are intended to assist investigators, who are using pharmaco-sleep measures in clinical research, in an effort to provide clear and concise recommendations and thereby to standardise methodology and facilitate comparability of data across laboratories.

Recent advances in sleep research.

The past two decades have witnessed substantial progress in methodology and knowledge in sleep research all over the world. The paper at hand will present some recent local contributions to this field. The first is a European project (SIESTA) focusing on the creation of an automatic sleep classification system and a normative database, including polysomnographic (PSG) and psychometric measures, in order to make it possible to diagnose sleep-disordered patients as compared with and age- and sex-matched healthy controls between 20 and 95 years of age. Subsequently, two trials on nonorganic sleep disorders in generalized anxiety disorder (GAD) and bruxism, as well as two trials on organic sleep disorders, i.e. snoring/sleep-disordered breathing treated with a mandibular advancement device (I.S.T.) and restless legs syndrome treated with ropinirole and gabapentin, will be discussed.

[Sleep disorders in psychiatry and their treatment]. / Schlafstörungen In Der Psychiatrieund Therapeutische Maßnahmen.

Sleep disturbances are frequent and multifaceted and have serious consequences. They play an important role within psychiatric symptoms and disorders. On the one hand they may appear as a symptom of a disorder, which may also be a diagnostic criterion, as for example in affective disorders, on the other hand they may be independent disorders or last but not least sequelae of psychiatric disorders or their pharmacological therapy, as with antidepressants or neuroleptics, which may cause or deteriorate nocturnal movement disorders. They may aggravate psychiatric disorders, perpetuate them or predict a disease onset, like in depressive or manic episodes. Also in organic sleep disorders, such as sleep-related breathing disorders or nocturnal movement disorders, increased anxiety or depression scores may be observed. Patients suffering from sleep disorders do not only experience impaired well-being, but also show deteriorations in cognition and performance, have a higher risk of accidents, are generally more prone to health problems, have a higher sickness absence rate, seek medical help more often and thus are also an important socioeconomic factor. This is why sleep disorders should be taken seriously and treated adequately.

Autonomic arousal detection and cardio-respiratory sleep staging improve the accuracy of home sleep apnea tests.

Introduction: The apnea-hypopnea index (AHI), defined as the number of apneas and hypopneas per hour of sleep, is still used as an important index to assess sleep disordered breathing (SDB) severity, where hypopneas are confirmed by the presence of an oxygen desaturation or an arousal. Ambulatory polygraphy without neurological signals, often referred to as home sleep apnea testing (HSAT), can potentially underestimate the severity of sleep disordered breathing (SDB) as sleep and arousals are not assessed. We aim to improve the diagnostic accuracy of HSATs by extracting surrogate sleep and arousal information derived from autonomic nervous system activity with artificial intelligence. Methods: We used polysomnographic (PSG) recordings from 245 subjects (148 with simultaneously recorded HSATs) to develop and validate a new algorithm to detect autonomic arousals using artificial intelligence. A clinically validated auto-scoring algorithm (Somnolyzer) scored respiratory events, cortical arousals, and sleep stages in PSGs, and provided respiratory events and sleep stages from cardio-respiratory signals in HSATs. In a four-fold cross validation of the newly developed algorithm, we evaluated the accuracy of the estimated arousal index and HSAT-derived surrogates for the AHI. Results: The agreement between the autonomic and cortical arousal index was moderate to good with an intraclass correlation coefficient of 0.73. When using thresholds of 5, 15, and 30 to categorize SDB into none, mild, moderate, and severe, the addition of sleep and arousal information significantly improved the classification accuracy from 70.2% (Cohen's κ = 0.58) to 80.4% (κ = 0.72), with a significant reduction of patients where the severity category was underestimated from 18.8% to 7.3%. Discussion: Extracting sleep and arousal information from autonomic nervous system activity can improve the diagnostic accuracy of HSATs by significantly reducing the probability of underestimating SDB severity without compromising specificity.

Scoring sleep with artificial intelligence enables quantification of sleep stage ambiguity: hypnodensity based on multiple expert scorers and auto-scoring.

STUDY OBJECTIVES: To quantify the amount of sleep stage ambiguity across expert scorers and to validate a new auto-scoring platform against sleep staging performed by multiple scorers. METHODS: We applied a new auto-scoring system to three datasets containing 95 PSGs scored by 6-12 scorers, to compare sleep stage probabilities (hypnodensity; i.e. the probability of each sleep stage being assigned to a given epoch) as the primary output, as well as a single sleep stage per epoch assigned by hierarchical majority rule. RESULTS: The percentage of epochs with 100% agreement across scorers was 46 ± 9%, 38 ± 10% and 32 ± 9% for the datasets with 6, 9, and 12 scorers, respectively. The mean intra-class correlation coefficient between sleep stage probabilities from auto- and manual-scoring was 0.91, representing excellent reliability. Within each dataset, agreement between auto-scoring and consensus manual-scoring was significantly higher than agreement between manual-scoring and consensus manual-scoring (0.78 vs. 0.69; 0.74 vs. 0.67; and 0.75 vs. 0.67; all p < 0.01). CONCLUSIONS: Analysis of scoring performed by multiple scorers reveals that sleep stage ambiguity is the rule rather than the exception. Probabilities of the sleep stages determined by artificial intelligence auto-scoring provide an excellent estimate of this ambiguity. Compared to consensus manual-scoring, sleep staging derived from auto-scoring is for each individual PSG noninferior to manual-scoring meaning that auto-scoring output is ready for interpretation without the need for manual adjustment.

A computationally efficient algorithm for wearable sleep staging in clinical populations.

This study describes a computationally efficient algorithm for 4-class sleep staging based on cardiac activity and body movements. Using an accelerometer to calculate gross body movements and a reflective photoplethysmographic (PPG) sensor to determine interbeat intervals and a corresponding instantaneous heart rate signal, a neural network was trained to classify between wake, combined N1 and N2, N3 and REM sleep in epochs of 30 s. The classifier was validated on a hold-out set by comparing the output against manually scored sleep stages based on polysomnography (PSG). In addition, the execution time was compared with that of a previously developed heart rate variability (HRV) feature-based sleep staging algorithm. With a median epoch-per-epoch κ of 0.638 and accuracy of 77.8% the algorithm achieved an equivalent performance when compared to the previously developed HRV-based approach, but with a 50-times faster execution time. This shows how a neural network, without leveraging any a priori knowledge of the domain, can automatically "discover" a suitable mapping between cardiac activity and body movements, and sleep stages, even in patients with different sleep pathologies. In addition to the high performance, the reduced complexity of the algorithm makes practical implementation feasible, opening up new avenues in sleep diagnostics.

Effects of electromagnetic fields emitted by mobile phones (GSM 900 and WCDMA/UMTS) on the macrostructure of sleep.

In the present double-blind, randomized, sham-controlled cross-over study, possible effects of electromagnetic fields emitted by Global System for Mobile Communications (GSM) 900 and Wideband Code-Division Multiple Access (WCDMA)/Universal Mobile Telecommunications System (UMTS) cell-phones on the macrostructure of sleep were investigated in a laboratory environment. An adaptation night, which served as screening night for sleep disorders and as an adjustment night to the laboratory environment, was followed by 9 study nights (separated by a 2-week interval) in which subjects were exposed to three exposure conditions (sham, GSM 900 and WCDMA/UMTS). The sample comprised 30 healthy male subjects within the age range 18-30 years (mean ± standard deviation: 25.3 ± 2.6 years). A cell-phone usage at maximum radio frequency (RF) output power was simulated and the transmitted power was adjusted in order to approach, but not to exceed, the specific absorption rate (SAR) limits of the International Commission on Non-Ionizing Radiation Protection (ICNIRP) guidelines for general public exposure (SAR(10g) = 2.0 W kg(-1)). In this study, possible effects of long-term (8 h) continuous RF exposure on the central nervous system were analysed during sleep, because sleep is a state in which many confounding intrinsic and extrinsic factors (e.g. motivation, personality, attitude) are eliminated or controlled. Thirteen of 177 variables characterizing the initiation and maintenance of sleep in the GSM 900 and three in the WCDMA exposure condition differed from the sham condition. The few significant results are not indicative of a negative impact on sleep architecture. From the present results there is no evidence for a sleep-disturbing effect of GSM 900 and WCDMA exposure.

Dysfunctional pain modulation in somatoform pain disorder patients.

To date, pain perception is thought to be a creative process of modulation carried out by an interplay of pro- and anti-nociceptive mechanisms. Recent research demonstrates that pain experience constitutes the result of top-down processes represented in cortical descending pain modulation. Cortical, mainly medial and frontal areas, as well as subcortical structures such as the brain stem, medulla and thalamus seem to be key players in pain modulation. An imbalance of pro- and anti-nociceptive mechanisms are assumed to cause chronic pain disorders, which are associated with spontaneous pain perception without physiologic scaffolding or exaggerated cortical activation in response to pain exposure. In contrast to recent investigations, the aim of the present study was to elucidate cortical activation of somatoform pain disorder patients during baseline condition. Scalp EEG, quantitative Fourier-spectral analyses and LORETA were employed to compare patient group (N = 15) to age- and sex-matched controls (N = 15) at rest. SI, SII, ACC, SMA, PFC, PPC, insular, amygdale and hippocampus displayed significant spectral power reductions within the beta band range (12-30 Hz). These results suggest decreased cortical baseline arousal in somatoform pain disorder patients. We finally conclude that obtained results may point to an altered baseline activity, maybe characteristic for chronic somatoform pain disorder.

A deep transfer learning approach for wearable sleep stage classification with photoplethysmography.

Unobtrusive home sleep monitoring using wrist-worn wearable photoplethysmography (PPG) could open the way for better sleep disorder screening and health monitoring. However, PPG is rarely included in large sleep studies with gold-standard sleep annotation from polysomnography. Therefore, training data-intensive state-of-the-art deep neural networks is challenging. In this work a deep recurrent neural network is first trained using a large sleep data set with electrocardiogram (ECG) data (292 participants, 584 recordings) to perform 4-class sleep stage classification (wake, rapid-eye-movement, N1/N2, and N3). A small part of its weights is adapted to a smaller, newer PPG data set (60 healthy participants, 101 recordings) through three variations of transfer learning. Best results (Cohen's kappa of 0.65 ± 0.11, accuracy of 76.36 ± 7.57%) were achieved with the domain and decision combined transfer learning strategy, significantly outperforming the PPG-trained and ECG-trained baselines. This performance for PPG-based 4-class sleep stage classification is unprecedented in literature, bringing home sleep stage monitoring closer to clinical use. The work demonstrates the merit of transfer learning in developing reliable methods for new sensor technologies by reusing similar, older non-wearable data sets. Further study should evaluate our approach in patients with sleep disorders such as insomnia and sleep apnoea.

Estimating sleep stages using cardiorespiratory signals: validation of a novel algorithm across a wide range of sleep-disordered breathing severity.

STUDY OBJECTIVES: We have developed the CardioRespiratory Sleep Staging (CReSS) algorithm for estimating sleep stages using heart rate variability and respiration, allowing for estimation of sleep staging during home sleep apnea tests. Our objective was to undertake an epoch-by-epoch validation of algorithm performance against the gold standard of manual polysomnography sleep staging. METHODS: Using 296 polysomnographs, we created a limited montage of airflow and heart rate and deployed CReSS to identify each 30-second epoch as wake, light sleep (N1 + N2), deep sleep (N3), or rapid eye movement (REM) sleep. We calculated Cohen's kappa and the percentage of accurately identified epochs. We repeated our analyses after stratification by sleep-disordered breathing (SDB) severity, and after adding thoracic respiratory effort as a backup signal for periods of invalid airflow. RESULTS: CReSS discriminated wake/light sleep/deep sleep/REM sleep with 78% accuracy; the kappa value was 0.643 (95% confidence interval, 0.641-0.645). Discrimination of wake/sleep demonstrated a kappa value of 0.711 and accuracy of 89%, non-REM sleep/REM sleep demonstrated a kappa of 0.790 and accuracy of 94%, and light sleep/deep sleep demonstrated a kappa of 0.469 and accuracy of 87%. Kappa values did not vary by more than 0.07 across subgroups of no SDB, mild SDB, moderate SDB, and severe SDB. Accuracy increased to 80%, with a kappa value of 0.680 (95% confidence interval, 0.678-0.682), when CReSS additionally utilized the thoracic respiratory effort signal. CONCLUSIONS: We observed substantial agreement between CReSS and the gold-standard comparator of manual sleep staging of polysomnographic signals, which was consistent across the full range of SDB severity. Future research should focus on the extent to which CReSS reduces the discrepancy between the apnea-hypopnea index and the respiratory event index, and the ability of CReSS to identify REM sleep-related obstructive sleep apnea.

It is All in the Wrist: Wearable Sleep Staging in a Clinical Population versus Reference Polysomnography.

PURPOSE: There is great interest in unobtrusive long-term sleep measurements using wearable devices based on reflective photoplethysmography (PPG). Unfortunately, consumer devices are not validated in patient populations and therefore not suitable for clinical use. Several sleep staging algorithms have been developed and validated based on ECG-signals. However, translation from these techniques to data derived by wearable PPG is not trivial, and requires the differences between sensing modalities to be integrated in the algorithm, or having the model trained directly with data obtained with the target sensor. Either way, validation of PPG-based sleep staging algorithms requires a large dataset containing both gold standard measurements and PPG-sensor in the applicable clinical population. Here, we take these important steps towards unobtrusive, long-term sleep monitoring. METHODS: We developed and trained an algorithm based on wrist-worn PPG and accelerometry. The method was validated against reference polysomnography in an independent clinical population comprising 244 adults and 48 children (age: 3 to 82 years) with a wide variety of sleep disorders. RESULTS: The classifier achieved substantial agreement on four-class sleep staging with an average Cohen's kappa of 0.62 and accuracy of 76.4%. For children/adolescents, it achieved even higher agreement with an average kappa of 0.66 and accuracy of 77.9%. Performance was significantly higher in non-REM parasomnias (kappa = 0.69, accuracy = 80.1%) and significantly lower in REM parasomnias (kappa = 0.55, accuracy = 72.3%). A weak correlation was found between age and kappa (ρ = -0.30, p<0.001) and age and accuracy (ρ = -0.22, p<0.001). CONCLUSION: This study shows the feasibility of automatic wearable sleep staging in patients with a broad variety of sleep disorders and a wide age range. Results demonstrate the potential for ambulatory long-term monitoring of clinical populations, which may improve diagnosis, estimation of severity and follow up in both sleep medicine and research.