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 commonly available 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 large cohort of 653 participants with a wide range of OSA severity. RESULTS: four-class sleep staging achieved a κ of 0.69 with 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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

Sleep EEG characteristics associated with sleep onset misperception.

STUDY OBJECTIVE: To study sleep EEG characteristics associated with misperception of Sleep Onset Latency (SOL). METHODS: Data analysis was based on secondary analysis of standard in-lab polysomnographic recordings in 20 elderly people with insomnia and 21 elderly good sleepers. Parameters indicating sleep fragmentation, such as number of awakenings, wake after sleep onset (WASO) and percentage of NREM1 were extracted from the polsysomnogram, as well as spectral power, microarousals and sleep spindle index. The correlation between these parameters during the first sleep cycle and the amount of misperceived sleep was assessed in the insomnia group. Additionally, we made a model of the minimum duration that a sleep fragment at sleep onset should have in order to be perceived as sleep, and we fitted this model to subjective SOLs of both subject groups. RESULTS: Misperception of SOL was associated with increased percentage of NREM1 and more WASO during sleep cycle 1. For insomnia subjects, the best fit of modelled SOL with subjective SOL was found when assuming that sleep fragments shorter than 30 min at sleep onset were perceived as wake. The model indicated that healthy subjects are less sensitive to sleep interruptions and perceive fragments of 10 min or longer as sleep. CONCLUSIONS: Our findings suggest that sleep onset misperception is related to sleep fragmentation at the beginning of the night. Moreover, we show that people with insomnia needed a longer duration of continuous sleep for the perception as such compared to controls. Further expanding the model could provide more detailed information about the underlying mechanisms of sleep misperception.

Detection of Nocturnal Scratching Movements in Patients with Atopic Dermatitis Using Accelerometers and Recurrent Neural Networks.

Atopic dermatitis is a chronic inflammatory skin condition affecting both children and adults and is associated with pruritus. A method for objectively quantifying nocturnal scratching events could aid in the development of therapies for atopic dermatitis and other pruritic disorders. High-resolution wrist actigraphy (three-dimensional accelerometer sensors sampled at 20 Hz) is a noninvasive method to record movement. This paper presents an algorithm to detect nocturnal scratching events based on actigraphy data. The twofold process consists of segmenting the data into "no motion," "single handed motion," and "both handed motion" followed by discriminating motion segments into scratching and other motion using a bidirectional recurrent neural network classifier. The performance was compared against manually scored infrared video data collected from 24 subjects (6 healthy controls and 18 atopic dermatitis patients) demonstrating an score of 0.68 and a rank correlation of 0.945. The algorithm clearly outperformed a published reference method based on wrist actigraphy ( score of 0.09 and a rank correlation of 0.466). The results suggest that scratching movements can be discriminated from other nocturnal movements accurately.

A novel actigraphy data analysis tool and its application to identifying the optimal threshold value in three subject populations.

Most actigraphy devices use different analysis methods and a non-standardized threshold value to estimate sleep/wake status and identify rest intervals. To address limitations of these approaches, a new algorithm was developed that makes no assumptions about sleep/wake status, objectively selects an optimal threshold for different populations, and provides mathematical endpoints to more fully describe the activity patterns of subjects. The optimal threshold (cts min(-1)) is defined as the value that maximizes the duration of the rest period while minimizing the inclusion of epochs from the active period. This value is identified as the beginning of a plateau region of a rest duration versus threshold value graph. Application of this new algorithm to data from 56 healthy adults, 6 healthy children, and 14 children with autism spectrum disorder (ASD) showed that the three groups had different optimal threshold values (35, 40, and 45 cts min(-1) for adults, children and ASD respectively). The rest periods of healthy children was longer than that of adults (8.5 ± 0.5 versus 6.3 ± 0.9 h, p < 0.001). Healthy children also had less activity during the rest periods than adults (10.5 ± 1.8 versus 15.1 ± 11.8 cts min(-1)) and ASD children (12.0 ± 2.2 cts min(-1)) but these differences were not statistically significant. However, the distributions of their activity values during rest periods as measured by skewness and kurtosis were significantly greater than that of healthy adults (skewness: 7.3 ± 0.9 versus 6.2 ± 0.9, p < 0.01, kurtosis: 83.3 ± 16.5 versus 52.8 ± 14.4, p < 0.001) and of ASD children (skewness: 6.4 ± 0.6. p < 0.05, kurtosis: 57.7 ± 12.8, p < 0.001). These findings are consistent with more restful sleep patterns which would have mostly low levels of activity with few large values. The new analysis tool may be helpful in standardizing actigraphy data analyses while providing new insights into activity patterns.

Computer-assisted sleep classification according to the standard of the American Academy of Sleep Medicine: validation study of the AASM version of the Somnolyzer 24 × 7.

BACKGROUND: In 2007, the AASM Manual for the Scoring of Sleep and Associated Events was published by the American Academy of Sleep Medicine (AASM). Concerning the visual classification of sleep stages, these new rules are intended to replace the rules by Rechtschaffen and Kales (R&K). METHODS: We adapted the automatic R&K sleep scoring system Somnolyzer 24 × 7 to comply with the AASM rules and subsequently performed a validation study based on 72 polysomnographies from the Siesta database (56 healthy subjects, 16 patients, 38 females, 34 males, aged 21-86 years). Scorings according to the AASM rules were performed manually by experienced sleep scorers and semi-automatically by the AASM version of the Somnolyzer. Manual scorings and Somnolyzer reviews were performed independently by at least 2 out of 8 experts from 4 sleep centers. RESULTS: In the quality control process, sleep experts corrected 4.8 and 3.7% of the automatically assigned epochs, resulting in a reliability between 2 Somnolyzer-assisted scorings of 99% (Cohen's kappa: 0.99). In contrast, the reliability between the 2 manual scorings was 82% (kappa: 0.76). The agreement between the 2 Somnolyzer-assisted and the 2 visual scorings was between 81% (kappa: 0.75) and 82% (kappa: 0.76). CONCLUSION: The AASM version of the Somnolyzer revealed an agreement between semi-automated and human expert scoring comparable to that published for the R&K version with a validity comparable to that of human experts, but with a reliability close to 1, thereby reducing interrater variability as well as scoring time to a minimum.