Accuracy of Automatic Polysomnography Scoring Using Frontal Electrodes

Sex differences in the association of sleep spindle density and cognitive performance among community-dwelling middle-aged and older adults with obstructive sleep apnea

Recent studies have found associations between obstructive sleep apnea and cognitive decline. The underlying mechanisms are still unclear. Here, we investigate the associations between changes in micro-architecture, specifically sleep spindles, and cognitive function in community-dwelling middle-aged and older adults, some with obstructive sleep apnea, with a focus on sex differences. A total of 125 voluntary participants (mean age 66.0 ± 6.4 years, 64 females) from a larger cohort (participants of the Brain in Motion Studies I and II) underwent 1 night of in-home polysomnography and a neuropsychological battery (sleep and cognitive testing were conducted within 2 weeks of each other). A semi-automatic computerized algorithm was used to score polysomnography data and detect spindle characteristics in non-rapid eye movement Stages 2 and 3 in both frontal and central electrodes. Based on their apnea-hypopnea index, participants were divided into those with no obstructive sleep apnea (apnea-hypopnea index < 5 per hr, n = 21), mild obstructive sleep apnea (5 ≥ apnea-hypopnea index < 15, n = 47), moderate obstructive sleep apnea (15 ≥ apnea-hypopnea index < 30, n = 34) and severe obstructive sleep apnea (apnea-hypopnea index ≥ 30, n = 23). There were no significant differences in spindle characteristics between the four obstructive sleep apnea severity groups. Spindle density and percentage of fast spindles were positively associated with some verbal fluency measures on the cognitive testing. Sex might be linked with these associations. Biological sex could play a role in the associations between spindle characteristics and some verbal fluency measures. Obstructive sleep apnea severity was not found to be a contributing factor in this non-clinical community-dwelling cohort.

Performance Investigation of Somfit Sleep Staging Algorithm

Purpose

To investigate accuracy of the sleep staging algorithm in a new miniaturized home sleep monitoring device - Compumedics® Somfit. Somfit is attached to patient's forehead and combines channels specified for a pulse arterial tonometry (PAT)-based home sleep apnea testing (HSAT) device with the neurological signals. Somfit sleep staging deep learning algorithm is based on convolutional neural network architecture.

Patients and Methods

One hundred and ten participants referred for sleep investigation with suspected or preexisting obstructive sleep apnea (OSA) in need of a review were enrolled into the study involving simultaneous recording of full overnight polysomnography (PSG) and Somfit data. The recordings were conducted at three centers in Australia. The reported statistics include standard measures of agreement between Somfit automatic hypnogram and consensus PSG hypnogram.

Results

Overall percent agreement across five sleep stages (N1, N2, N3, REM, and wake) between Somfit automatic and consensus PSG hypnograms was 76.14 (SE: 0.79). The percent agreements between different pairs of sleep technologists' PSG hypnograms varied from 74.36 (1.93) to 85.50 (0.64), with interscorer agreement being greater for scorers from the same sleep laboratory. The estimate of kappa between Somfit and consensus PSG was 0.672 (0.002). Percent agreement for sleep/wake discrimination was 89.30 (0.37). The accuracy of Somfit sleep staging algorithm varied with increasing OSA severity - percent agreement was 79.67 (1.87) for the normal subjects, 77.38 (1.06) for mild OSA, 74.83 (1.79) for moderate OSA and 72.93 (1.68) for severe OSA.

Conclusion

Agreement between Somfit and PSG hypnograms was non-inferior to PSG interscorer agreement for a number of scorers, thus confirming acceptability of electrode placement at the center of the forehead. The directions for algorithm improvement include additional arousal detection, integration of motion and oximetry signals and separate inference models for individual sleep stages.

Research and application of deep learning-based sleep staging: Data, modeling, validation, and clinical practice

Over the past few decades, researchers have attempted to simplify and accelerate the process of sleep stage classification through various approaches; however, only a few such approaches have gained widespread acceptance. Artificial intelligence technology, particularly deep learning, is promising for earning the trust of the sleep medicine community in automated sleep-staging systems, thus facilitating its application in clinical practice and integration into daily life. We aimed to comprehensively review the latest methods that are applying deep learning for enhancing sleep staging efficiency and accuracy. Starting from the requisite "data" for constructing deep learning algorithms, we elucidated the current landscape of this domain and summarized the fundamental modeling process, encompassing signal selection, data pre-processing, model architecture, classification tasks, and performance metrics. Furthermore, we reviewed the applications of automated sleep staging in scenarios such as sleep-disorder screening, diagnostic procedures, and health monitoring and management. Finally, we conducted an in-depth analysis and discussion of the challenges and future in intelligent sleep staging, particularly focusing on large-scale sleep datasets, interdisciplinary collaborations, and human-computer interactions.

Feasibility and Acceptability of Using Wireless Limited Polysomnography to Capture Sleep Before, During, and After Hospitalization for Patients With Planned Cardiothoracic Surgery

BACKGROUND

Sleep disruption, a common symptom among patients requiring cardiovascular surgery, is a potential risk factor for the development of postoperative delirium. Postoperative delirium is a disorder of acute disturbances in cognition associated with prolonged hospitalization, cognitive decline, and mortality.

OBJECTIVE

The aim of this study was to evaluate the feasibility and acceptability of using polysomnography (PSG) to capture sleep in patients with scheduled cardiothoracic surgery.

METHODS

Wireless limited PSG assessed sleep at baseline (presurgery at home), postoperatively in the intensive care unit, and at home post hospital discharge. Primary outcomes were quality and completeness of PSG signals, and acceptability by participants and nursing staff.

RESULTS

Among 15 patients, PSG data were of high quality, and mean percentage of unscorable data was 5.5% ± 11.1%, 3.7% ± 5.4%, and 3.7% ± 8.4% for baseline, intensive care unit, and posthospitalization measurements, respectively. Nurses and patients found the PSG monitor acceptable.

CONCLUSIONS

Wireless, limited PSG to capture sleep across the surgical continuum was feasible, and data were of high quality. Authors of future studies will evaluate associations of sleep indices and development of postoperative delirium in this high-risk population.

New insights and potential clinical implications of the odds ratio product

The odds ratio product (ORP) is a continuous metric of sleep depth that ranges from 0 (very deep sleep) to 2. 5 (full wakefulness). Its advantage over the conventional method recommended by AASM is that it discloses different levels of stage wake (sleep propensity) and different sleep depths within the same sleep stage. As such, it can be used to identify differences in sleep depth between subjects, and in the same subjects under different circumstances, when differences are not discernible by conventional staging. It also identifies different sleep depths within stage rapid-eye-movement sleep, with possible implications to disorders during this stage. Epoch-by-epoch ORP can be displayed graphically across the night or as average values in conventional sleep stages. In addition, ORP can be reported as % of recording time in specific ORP ranges (e.g., deciles of the total ORP range) where it produces distinct distribution patterns (ORP-architecture) that have been associated with different clinical disorders and outcomes. These patterns offer unique research opportunities to identify different mechanisms and potential therapy for various sleep complaints and disorders. In this review I will discuss how ORP is measured, its validation, differences from delta power, and the various phenotypes, and their postulated mechanisms, identified by ORP architecture and the opportunities for research to advance management of sleep-disordered breathing, insomnia and idiopathic hypersomnia.

Challenges of Applying Automated Polysomnography Scoring at Scale

Automatic polysomnography analysis can be leveraged to shorten scoring times, reduce associated costs, and ultimately improve the overall diagnosis of sleep disorders. Multiple and diverse strategies have been attempted for implementation of this technology at scale in the routine workflow of sleep centers. The field, however, is complex and presents unsolved challenges in a number of areas. Recent developments in computer science and artificial intelligence are nevertheless closing the gap. Technological advances are also opening new pathways for expanding our current understanding of the domain and its analysis.

Sleep calibrates atherosclerotic cardiovascular disease

Sleep modulates cardiovascular health, and recent studies have begun to uncover underlying mechanistic links. An integrated translational approach that combines animal models and human trials will enrich scientific discovery, improve therapy, and help to alleviate the global burden of insufficient sleep and cardiovascular disease.

A novel EEG marker predicts perceived sleepiness and poor sleep quality

STUDY OBJECTIVES

To determine if a novel EEG-derived continuous index of sleep depth/alertness, the odds ratio product (ORP), predicts self-reported daytime sleepiness and poor sleep quality in two large population-based cohorts.

METHODS

ORP values which range from 0 (deep sleep) to 2.5 (fully alert) were calculated in 3s intervals during awake periods (ORPwake) and NREM sleep (ORPNREM) determined from home sleep studies in the HypnoLaus (N = 2162: 1106 females, 1056 males) and men androgen inflammation lifestyle environment and stress (MAILES) cohorts (N = 754 males). Logistic regression was used to examine associations between ORPwake, ORPNREM, and traditional polysomnography measures (as comparators) with excessive sleepiness (Epworth sleepiness scale >10) and poor sleep quality (Pittsburgh sleep quality index >5) and insomnia symptoms.

RESULTS

High ORPwake was associated with a ~30% increase in poor sleep quality in both HypnoLaus (odds ratio, OR, and 95% CI) 1.28 (1.09, 1.51), and MAILES 1.36 (1.10, 1.68). High ORPwake was also associated with a ~28% decrease in excessive daytime sleepiness in the MAILES dataset. ORPNREM was associated with a ~30% increase in poor sleep quality in HypnoLaus but not in MAILES. No consistent associations across cohorts were detected using traditional polysomnography markers.

CONCLUSIONS

ORP, a novel EEG-derived metric, measured during wake periods predicts poor sleep quality in two independent cohorts. Consistent with insomnia symptomatology of poor perceived sleep in the absence of excessive daytime sleepiness, ORPwake may provide valuable objective mechanistic insight into physiological hyperarousal.

Traffic noise-induced changes in wake-propensity measured with the Odds-Ratio Product (ORP)

Nocturnal traffic noise can disrupt sleep and impair physical and mental restoration, but classical sleep scoring techniques may not fully capture subtle yet clinically relevant alterations of sleep induced by noise. We used a validated continuous measure of sleep depth and quality based on automatic analysis of physiologic sleep data, termed Wake Propensity (WP), to investigate temporal changes of sleep in response to nocturnal noise events in 3-s epochs. Seventy-two healthy participants (mean age 40.3 years, range 18-71 years, 40 females, 32 males) slept for 11 nights in a laboratory, during which we measured sleep with polysomnography. In 8 nights, participants were exposed to 40, 80 or 120 road, rail and/or aircraft noise events with maximum noise levels of 45-65 dB L_AS,max during 8-h sleep opportunities. We analyzed sleep macrostructure and event-related change of WP during noise exposure with linear mixed models. Nocturnal traffic noise led to event-related shifts towards wakefulness and less deep, more unstable sleep (increase in WP relative to pre-noise baseline ranging from +29.5% at 45 dB to +38.3% at 65 dB; type III effect p < 0.0001). Sleep depth decreased dynamically with increasing noise level, peaking when L_AS,max was highest. This change in WP was stronger and occurred more quickly for events where the noise onset was more rapid (road and rail) compared to more gradually time-varying noise (aircraft). Sleep depth did not immediately recover to pre-noise WP, leading to decreased sleep stability across the night compared to quiet nights, which was greater with an increasing number of noise events (standardized β = 0.053, p = 0.003). Further, WP was more sensitive to noise than classical arousals. Results demonstrate the usefulness of WP as a measure of the effects of external stimuli on sleep, and show WP is a more sensitive measure of noise-induced sleep disruption than traditional methods of sleep analysis.

Statistical uncertainty quantification to augment clinical decision support: a first implementation in sleep medicine

Machine learning has the potential to change the practice of medicine, particularly in areas that require pattern recognition (e.g. radiology). Although automated classification is unlikely to be perfect, few modern machine learning tools have the ability to assess their own classification confidence to recognize uncertainty that might need human review. Using automated single-channel sleep staging as a first implementation, we demonstrated that uncertainty information (as quantified using Shannon entropy) can be utilized in a "human in the loop" methodology to promote targeted review of uncertain sleep stage classifications on an epoch-by-epoch basis. Across 20 sleep studies, this feedback methodology proved capable of improving scoring agreement with the gold standard over automated scoring alone (average improvement in Cohen's Kappa of 0.28), in a fraction of the scoring time compared to full manual review (60% reduction). In summary, our uncertainty-based clinician-in-the-loop framework promotes the improvement of medical classification accuracy/confidence in a cost-effective and economically resourceful manner.

Automatic analysis of single-channel sleep EEG in a large spectrum of sleep disorders

STUDY OBJECTIVES

To assess the performance of the single-channel automatic sleep staging (AS) software ASEEGA in adult patients diagnosed with various sleep disorders.

METHODS

Sleep recordings were included of 95 patients (38 women, 40.5 ± 13.7 years) diagnosed with insomnia (n = 23), idiopathic hypersomnia (n = 24), narcolepsy (n = 24), and obstructive sleep apnea (n = 24). Visual staging (VS) was performed by two experts (VS1 and VS2) according to the American Academy of Sleep Medicine rules. AS was based on the analysis of a single electroencephalogram channel (Cz-Pz), without any information from electro-oculography nor electromyography. The epoch-by-epoch agreement (concordance and Conger's coefficient [κ]) was compared pairwise (VS1-VS2, AS-VS1, AS-VS2) and between AS and consensual VS. Sleep parameters were also compared.

RESULTS

The pairwise agreements were: between AS and VS1, 78.6% (κ = 0.70); AS and VS2, 75.0% (0.65); and VS1 and VS2, 79.5% (0.72). Agreement between AS and consensual VS was 85.6% (0.80), with the following distribution: insomnia 85.5% (0.80), narcolepsy 83.8% (0.78), idiopathic hypersomnia 86.1% (0.68), and obstructive sleep disorder 87.2% (0.82). A significant low-amplitude scorer effect was observed for most sleep parameters, not always driven by the same scorer. Hypnograms obtained with AS and VS exhibited very close sleep organization, except for 80% of rapid eye movement sleep onset in the group diagnosed with narcolepsy missed by AS.

CONCLUSIONS

Agreement between AS and VS in sleep disorders is comparable to that reported in healthy individuals and to interexpert agreement in patients. ASEEGA could therefore be considered as a complementary sleep stage scoring tool in clinical practice, after improvement of rapid eye movement sleep onset detection.

Expert-level automated sleep staging of long-term scalp electroencephalography recordings using deep learning

STUDY OBJECTIVES

Develop a high-performing, automated sleep scoring algorithm that can be applied to long-term scalp electroencephalography (EEG) recordings.

METHODS

Using a clinical dataset of polysomnograms from 6,431 patients (MGH-PSG dataset), we trained a deep neural network to classify sleep stages based on scalp EEG data. The algorithm consists of a convolutional neural network for feature extraction, followed by a recurrent neural network that extracts temporal dependencies of sleep stages. The algorithm's inputs are four scalp EEG bipolar channels (F3-C3, C3-O1, F4-C4, and C4-O2), which can be derived from any standard PSG or scalp EEG recording. We initially trained the algorithm on the MGH-PSG dataset and used transfer learning to fine-tune it on a dataset of long-term (24-72 h) scalp EEG recordings from 112 patients (scalpEEG dataset).

RESULTS

The algorithm achieved a Cohen's kappa of 0.74 on the MGH-PSG holdout testing set and cross-validated Cohen's kappa of 0.78 after optimization on the scalpEEG dataset. The algorithm also performed well on two publicly available PSG datasets, demonstrating high generalizability. Performance on all datasets was comparable to the inter-rater agreement of human sleep staging experts (Cohen's kappa ~ 0.75 ± 0.11). The algorithm's performance on long-term scalp EEGs was robust over a wide age range and across common EEG background abnormalities.

CONCLUSION

We developed a deep learning algorithm that achieves human expert level sleep staging performance on long-term scalp EEG recordings. This algorithm, which we have made publicly available, greatly facilitates the use of large long-term EEG clinical datasets for sleep-related research.

HIV Increases Sleep-based Brain Age Despite Antiretroviral Therapy

STUDY OBJECTIVES

Age-related comorbidities and immune activation raise concern for advanced brain aging in people living with HIV (PLWH). The brain age index (BAI) is a machine learning model that quantifies deviations in brain activity during sleep relative to healthy individuals of the same age. High BAI was previously found to be associated with neurological, psychiatric, cardiometabolic diseases, and reduced life expectancy among people without HIV. Here, we estimated the effect of HIV infection on BAI by comparing PLWH and HIV-controls.

METHODS

Clinical data and sleep EEGs from 43 PLWH on antiretroviral therapy (HIV+) and 3,155 controls (HIV-) were collected from Massachusetts General Hospital. The effect of HIV infection on BAI, and on individual EEG features, was estimated using causal inference.

RESULTS

The average effect of HIV on BAI was estimated to be +3.35 years (p < 0.01, 95% CI = [0.67, 5.92]) using doubly robust estimation. Compared to HIV- controls, HIV+ participants exhibited a reduction in delta band power during deep sleep and rapid eye movement sleep.

CONCLUSION

We provide causal evidence that HIV contributes to advanced brain aging reflected in sleep EEG. A better understanding is greatly needed of potential therapeutic targets to mitigate the effect of HIV on brain health, potentially including sleep disorders and cardiovascular disease.

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.

Comparing two measures of sleep depth/intensity

Study Objectives

To compare delta spectral power (delta) and odds ratio product (ORP) as measures of sleep depth during sleep restriction with placebo or a drug that increases delta.

Methods

This is a secondary analysis of data from a study of 41 healthy participants randomized to receive placebo or gaboxadol 15 mg during sleep restriction. Participants underwent in-laboratory sleep studies on two baseline, four sleep restriction (5-h), and two recovery nights. Relation between delta or ORP and sleep depth was operationally defined as the degree of association of each metric to the probability of arousal or awakening occurring during the next 30 s (arousability).

Results

ORP values in wake, N1, N2, N3, and REM were significantly different. Delta differed between both N2 and N3 and other sleep stages but not between wake and N1 or N1 and REM. Epoch-by-epoch and individual correlations between ORP and delta power were modest or insignificant. The relation between ORP and arousability was linear across the entire ORP range. Delta also changed with arousability but only when delta values were less than 300 μV2. Receiver-operating-characteristic analysis found the ability to predict imminent arousal to be significantly greater with ORP than with log delta power for all experimental conditions. Changes in ORP, but not log delta, across the night correlated with next-day physiologic sleep tendency.

Conclusions

Compared to delta power, ORP is more discriminating among sleep stages, more sensitive to sleep restriction, and more closely associated with arousability. This evidence supports ORP as a measure of sleep depth/intensity.

Automated sleep stage scoring of the Sleep Heart Health Study using deep neural networks

STUDY OBJECTIVES

Polysomnography (PSG) scoring is labor intensive and suffers from variability in inter- and intra-rater reliability. Automated PSG scoring has the potential to reduce the human labor costs and the variability inherent to this task. Deep learning is a form of machine learning that uses neural networks to recognize data patterns by inspecting many examples rather than by following explicit programming.

METHODS

A sleep staging classifier trained using deep learning methods scored PSG data from the Sleep Heart Health Study (SHHS). The training set was composed of 42 560 hours of PSG data from 5213 patients. To capture higher-order data, spectrograms were generated from electroencephalography, electrooculography, and electromyography data and then passed to the neural network. A holdout set of 580 PSGs not included in the training set was used to assess model accuracy and discrimination via weighted F1-score, per-stage accuracy, and Cohen's kappa (K).

RESULTS

The optimal neural network model was composed of spectrograms in the input layer feeding into convolutional neural network layers and a long short-term memory layer to achieve a weighted F1-score of 0.87 and K = 0.82.

CONCLUSIONS

The deep learning sleep stage classifier demonstrates excellent accuracy and agreement with expert sleep stage scoring, outperforming human agreement on sleep staging. It achieves comparable or better F1-scores, accuracy, and Cohen's kappa compared to literature for automated sleep stage scoring of PSG epochs. Accurate automated scoring of other PSG events may eventually allow for fully automated PSG scoring.

Mechanism of excessive wake time when associated with obstructive sleep apnea or periodic limb movements

STUDY OBJECTIVES

It is uncertain whether obstructive apnea (OSA) or periodic limb movements (PLMs) contribute to excessive wake time (EWT) when EWT and these disorders coexist. We hypothesized that such EWT is an independent disorder related to central regulation of sleep depth. Accordingly, we compared sleep depth in patients with EWT and OSA/PLMs (EWT+P) with patients with EWT and no OSA/PLMs (EWT-NP) and patients with a normal wake time.

METHODS

A total of 267 participants were divided into five groups: (1) EWT+P: n = 100 (wake time > 20% total recording time; TRT) with OSA (apnea-hypopnea index 5-110 events/h) and/or PLMs (PLM index 10-151 events/h); (2) EWT-NP: n = 49 (wake time > 20%TRT), no associated pathology; (3) normal wake time (NWT)+P: n = 54 (wake time < 20%TRT, with OSA/PLMs); (4) NWT-NP: n = 26; (5) Healthy participants: n = 38 (no sleep complaints, NWT and no OSA/PLMs). Sleep depth was evaluated by the odds ratio product (ORP; 0 = deep sleep, 2.5 = fully alert). We also measured ORP in the 9 seconds immediately following arousals (ORP-9) to distinguish between peripheral and central mechanisms of light sleep.

RESULTS

ORP during sleep was higher (lighter sleep) in both EWT groups than in the three NWT groups (P < 1E-11) with no difference between those with and those without OSA/PLMs. ORP-9 was also significantly higher in the EWT groups than in the NWT groups (P < 1E-19), also with no difference between those with and without OSA/PLMs, indicating that the lighter sleep was of central origin. There were highly significant correlations between wake time and ORP-9 across all groups (P < 1E-35).

CONCLUSIONS

EWT associated with OSA/PLMs is independent of OSA/PLMs and related to abnormal central regulation of sleep depth.

Expert-level sleep scoring with deep neural networks

Objectives

Scoring laboratory polysomnography (PSG) data remains a manual task of visually annotating 3 primary categories: sleep stages, sleep disordered breathing, and limb movements. Attempts to automate this process have been hampered by the complexity of PSG signals and physiological heterogeneity between patients. Deep neural networks, which have recently achieved expert-level performance for other complex medical tasks, are ideally suited to PSG scoring, given sufficient training data.

Methods

We used a combination of deep recurrent and convolutional neural networks (RCNN) for supervised learning of clinical labels designating sleep stages, sleep apnea events, and limb movements. The data for testing and training were derived from 10 000 clinical PSGs and 5804 research PSGs.

Results

When trained on the clinical dataset, the RCNN reproduces PSG diagnostic scoring for sleep staging, sleep apnea, and limb movements with accuracies of 87.6%, 88.2% and 84.7% on held-out test data, a level of performance comparable to human experts. The RCNN model performs equally well when tested on the independent research PSG database. Only small reductions in accuracy were noted when training on limited channels to mimic at-home monitoring devices: frontal leads only for sleep staging, and thoracic belt signals only for the apnea-hypopnea index.

Conclusions

By creating accurate deep learning models for sleep scoring, our work opens the path toward broader and more timely access to sleep diagnostics. Accurate scoring automation can improve the utility and efficiency of in-lab and at-home approaches to sleep diagnostics, potentially extending the reach of sleep expertise beyond specialty clinics.

Automatic Sleep Staging in Patients With Obstructive Sleep Apnea Using Single-Channel Frontal EEG

STUDY OBJECTIVES

Reliable sleep staging is difficult to obtain from home sleep testing for diagnosis of obstructive sleep apnea (OSA), especially when it is self-applied. Hence, the current study aimed to develop a single frontal electroencephalography-based automatic sleep staging system (ASSS).

METHODS

The ASSS system was developed on a clinical dataset, with a high percentage of participants with OSA. The F4-M1 signal extracted from 62 participants (62.9% having OSA) was used to build a four-stage classifier. Performance of the ASSS was tested in a holdout set of 58 patients (60.3% having OSA) with epoch-by-epoch and whole-night agreement for sleep staging compared with expert scoring of polysomnography.

RESULTS

Mean all-stage percentage agreement was 75.52% (95% confidence interval, 72.90 to 78.13) (kappa 0.62; 95% confidence interval, 0.58 to 0.65), with mean percentage agreement for wake, light sleep, deep sleep (DS), and rapid eye movement of 78.04%, 70.97%, 83.65%, and 75.00%, respectively. The whole-night agreement was good-excellent (intraclass correlation coefficient, 0.74 to 0.88) for sleep onset latency, wake after sleep onset, total sleep time, and sleep efficiency. Compared to the non-OSA subset, the OSA subset had lower agreement for DS.

CONCLUSIONS

Our results indicate that a single-channel F4-M1 based ASSS was sufficient for sleep staging in a population with a high percentage of participants with OSA.

Portable PSG for sleep stage monitoring in sports: Assessment of SOMNOwatch plus EEG

Current sport-scientific studies mostly neglect the assessment of sleep architecture, although the distribution of different sleep stages is considered an essential component influencing an athlete's recovery and performance capabilities. A mobile, self-applied tool like the SOMNOwatch plus EEG might serve as an economical and time-friendly alternative to activity-based devices. However, self-application of SOMNOwatch plus EEG has not been validated against conventional polysomnography (PSG) yet. For evaluation purposes, 25 participants (15 female, 10 male; M _age = 22.92 ± 2.03 years) slept in a sleep laboratory on two consecutive nights wearing both, conventional PSG and SOMNOwatch plus EEG electrodes. Sleep parameters and sleep stages were compared using paired t-tests and Bland-Altman plots. No significant differences were found between the recordings for Sleep Onset Latency, stages N1 to N3 as well as Rapid Eye Movement stage. Significant differences (Bias [95%-confidence interval]) were present between Total Sleep Time (9.95 min [-29.18, 49.08], d = 0.14), Total Wake Time (-13.12 min [-47.25, 23.85], d = -0.28), Wake after Sleep Onset (-11.70 min [-47.25, 23.85], d = -0.34) and Sleep Efficiency (2.18% [-7.98, 12.34], d = 0.02) with small effect sizes. Overall, SOMNOwatch plus EEG can be considered a valid and practical self-applied method for the examination of sleep. In sport-scientific research, it is a promising tool to assess sleep architecture in athletes; nonetheless, it cannot replace in-lab PSG for all clinical or scientific purposes.

Opportunities for utilizing polysomnography signals to characterize obstructive sleep apnea subtypes and severity

BACKGROUND

Obstructive sleep apnea (OSA) is a heterogeneous sleep disorder with many pathophysiological pathways to disease. Currently, the diagnosis and classification of OSA is based on the apnea-hypopnea index, which poorly correlates to underlying pathology and clinical consequences. A large number of in-laboratory sleep studies are performed around the world every year, already collecting an enormous amount of physiological data within an individual. Clinically, we have not yet fully taken advantage of this data, but combined with existing analytical approaches, we have the potential to transform the way OSA is managed within an individual patient. Currently, respiratory signals are used to count apneas and hypopneas, but patterns such as inspiratory flow signals can be used to predict optimal OSA treatment. Electrocardiographic data can reveal arrhythmias, but patterns such as heart rate variability can also be used to detect and classify OSA. Electroencephalography is used to score sleep stages and arousals, but specific patterns such as the odds-ratio product can be used to classify how OSA patients responds differently to arousals.

OBJECTIVE

In this review, we examine these and many other existing computer-aided polysomnography signal processing algorithms and how they can reflect an individual's manifestation of OSA.

SIGNIFICANCE

Together with current technological advance, it is only a matter of time before advanced automatic signal processing and analysis is widely applied to precision medicine of OSA in the clinical setting.

Reliability of the American Academy of Sleep Medicine Rules for Assessing Sleep Depth in Clinical Practice

STUDY OBJECTIVES

The American Academy of Sleep Medicine has published manuals for scoring polysomnograms that recommend time spent in non-rapid eye movement sleep stages (stage N1, N2, and N3 sleep) be reported. Given the well-established large interrater variability in scoring stage N1 and N3 sleep, we determined the range of time in stage N1 and N3 sleep scored by a large number of technologists when compared to reasonably estimated true values.

METHODS

Polysomnograms of 70 females were scored by 10 highly trained sleep technologists, two each from five different academic sleep laboratories. Range and confidence interval (CI = difference between the 5th and 95th percentiles) of the 10 times spent in stage N1 and N3 sleep assigned in each polysomnogram were determined. Average values of times spent in stage N1 and N3 sleep generated by the 10 technologists in each polysomnogram were considered representative of the true values for the individual polysomnogram. Accuracy of different technologists in estimating delta wave duration was determined by comparing their scores to digitally determined durations.

RESULTS

The CI range of the ten N1 scores was 4 to 39 percent of total sleep time (% TST) in different polysomnograms (mean CI ± standard deviation = 11.1 ± 7.1 % TST). Corresponding range for N3 was 1 to 28 % TST (14.4 ± 6.1 % TST). For stage N1 and N3 sleep, very low or very high values were reported for virtually all polysomnograms by different technologists. Technologists varied widely in their assignment of stage N3 sleep, scoring that stage when the digitally determined time of delta waves ranged from 3 to 17 seconds.

CONCLUSIONS

Manual scoring of non-rapid eye movement sleep stages is highly unreliable among highly trained, experienced technologists. Measures of sleep continuity and depth that are reliable and clinically relevant should be a focus of clinical research.

Large-Scale Automated Sleep Staging

Study Objectives

Automated sleep staging has been previously limited by a combination of clinical and physiological heterogeneity. Both factors are in principle addressable with large data sets that enable robust calibration. However, the impact of sample size remains uncertain. The objectives are to investigate the extent to which machine learning methods can approximate the performance of human scorers when supplied with sufficient training cases and to investigate how staging performance depends on the number of training patients, contextual information, model complexity, and imbalance between sleep stage proportions.

Methods

A total of 102 features were extracted from six electroencephalography (EEG) channels in routine polysomnography. Two thousand nights were partitioned into equal (n = 1000) training and testing sets for validation. We used epoch-by-epoch Cohen's kappa statistics to measure the agreement between classifier output and human scorer according to American Academy of Sleep Medicine scoring criteria.

Results

Epoch-by-epoch Cohen's kappa improved with increasing training EEG recordings until saturation occurred (n = ~300). The kappa value was further improved by accounting for contextual (temporal) information, increasing model complexity, and adjusting the model training procedure to account for the imbalance of stage proportions. The final kappa on the testing set was 0.68. Testing on more EEG recordings leads to kappa estimates with lower variance.

Conclusion

Training with a large data set enables automated sleep staging that compares favorably with human scorers. Because testing was performed on a large and heterogeneous data set, the performance estimate has low variance and is likely to generalize broadly.

A State Space and Density Estimation Framework for Sleep Staging in Obstructive Sleep Apnea

OBJECTIVE

Although the importance of sleep is increasingly recognized, the lack of robust and efficient algorithms hinders scalable sleep assessment in healthy persons and those with sleep disorders. Polysomnography (PSG) and visual/manual scoring remain the gold standard in sleep evaluation, but more efficient/automated systems are needed. Most previous works have demonstrated algorithms in high agreement with the gold standard in healthy/normal (HN) individuals-not those with sleep disorders.

METHODS

This paper presents a statistical framework that automatically estimates whole-night sleep architecture in patients with obstructive sleep apnea (OSA)-the most common sleep disorder. Single-channel frontal electroencephalography was extracted from 65 HN/OSA sleep studies, and decomposed into 11 spectral features in 60 903 30 s sleep epochs. The algorithm leveraged kernel density estimation to generate stage-specific likelihoods, and a 5-state hidden Markov model to estimate per-night sleep architecture.

RESULTS

Comparisons to full PSG expert scoring revealed the algorithm was in fair agreement with the gold standard (median Cohen's kappa = 0.53). Further, analysis revealed modest decreases in median scoring agreement as OSA severity increased from HN (kappa = 0.63) to severe (kappa = 0.47). A separate implementation on HN data from the Physionet Sleep-EDF Database resulted in a median kappa = 0.65, further indicating the algorithm's broad applicability.

CONCLUSION

Results of this work indicate the proposed single-channel framework can emulate expert-level scoring of sleep architecture in OSA.

SIGNIFICANCE

Algorithms constructed to more accurately model physiological variability during sleep may help advance automated sleep assessment, for practical and general use in sleep medicine.

Performance of a New Portable Wireless Sleep Monitor

STUDY OBJECTIVES

To determine if signals generated by a new sleep monitor (Prodigy) are comparable to signals generated during in-laboratory polysomnography (PSG).

METHODS

Fifty-nine patients with various sleep disorders (25 with moderate/severe sleep apnea) were studied. Full PSG was performed using standard acquisition systems. Prodigy was attached to the forehead with four disposable snap electrodes. Four additional electrodes were attached to monitor eye movements and muscle activity, and to serve as reference (mastoid). One frontal EEG signal was outputted in real time from the monitor and stored in the PSG record along with the other PSG signals. PSG was scored for sleep variables manually, and monitor records were scored by a validated automatic system (MSS) (MSS-Prodigy). MSS-Prodigy was briefly edited following suggestions of an Editing Helper feature of MSS.

RESULTS

Technical failures resulted in one study being unusable and another with data for only 3 hours. Prodigy EEG signal stored in the PSG record was visually indistinguishable from the PSG-derived EEG signals. Important differences between manual scores and unedited MSS-Prodigy were seen in a few patients in some sleep variables (notably onset latencies and REM time). Editing Helper issued 2.1 ± 0.8 suggestions/file. Only these suggestions were pursued during editing. Intraclass correlation coefficients for manual vs. edited MSS-Prodigy were > 0.83 for all sleep variables except for stages N1 and N3 (0.57 and 0.58).

CONCLUSIONS

When scored with MSS, and with only very minor editing, the monitor's results show excellent agreement with manual scoring of polysomnography data, even in patients with severe sleep disorders.

Enhancements to the multiple sleep latency test

INTRODUCTION

The utility of multiple sleep latency tests (MSLTs) is limited to determining sleep onset latency (SOL) and rapid eye movement sleep latency. The odds ratio product (ORP) is a continuous index of sleep depth with values of 0, 1.0, and 2.5 reflecting very deep sleep, light sleep, and full wakefulness, respectively. We determined the time course of sleep depth during MSLT naps expecting that this would enhance the test's clinical utility.

METHODS

Thirty MSLTs (150 naps) were performed for excessive somnolence. Patients indicated whether they slept (yes/no) after each nap. SOL was scored by two experienced technologists. Time course of ORP was determined with a commercial system. We determined ORP at SOL (ORPSOL), times ORP decreased <2.0, <1.5, <1.0 and <0.5 during the entire nap duration, and the integral of decrease in ORP over nap duration (ΔORPINT).

RESULTS

SOL occurred almost invariably when ORP was between 1.0 and 2.0. Of 47 naps (21 patients) with SOL <5 minutes, ORP decreased <1.0 (light sleep) in <5 minutes in only 13 naps (nine patients) and <0.5 (deep sleep) in only two naps in one patient. The relation between ORPINT and frequency of sleep perception was well defined, allowing determination of a threshold for sleep perception. This threshold ranged widely (5-50 ΔORP*epoch).

CONCLUSION

As currently identified, SOL reflects transition into a highly unstable state between wakefulness and sleep. Reporting the times of attaining different sleep depths may help better identify patients at high risk of vigilance loss. Furthermore, an ORPSOL outside the range 1.0-2.0 can help identify scoring errors.