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.

Abstract 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.

Human experts scoring sleep according to the American Academy of Sleep Medicine (AASM) rules are forced to select, for every 30-second epoch, one out of five stages, even if the characteristics of the neurological signals are ambiguous, a very common occurrence in clinical studies. Moreover, experts cannot score sleep in studies where these signals have not been recorded, such as in home sleep apnea testing (HSAT). In this topic review we describe how artificial intelligence can provide consistent and reliable scoring of sleep stages based on neurological signals recorded in polysomnography (PSG) and on cardiorespiratory signals recorded in HSAT. We also show how estimates of sleep stage probabilities, usually displayed as hypnodensity graph, can be used to quantify sleep stage ambiguity and stability. As an example of the application of hypnodensity in the characterization of sleep disordered breathing (SDB), we compared 49 patients with sleep apnea to healthy controls and revealed a severity-depending increase in ambiguity and decrease in stability during non-rapid eye movement (NREM) sleep. Moreover, using autoscoring of cardiorespiratory signals, we show how HSAT-derived apnea-hypopnea index and hypoxic burden are well correlated with the PSG indices in 80 patients, showing how using this technology can truly enable HSATs as alternatives to PSG to diagnose SDB.

Abstract Introduction In a recent analysis of PSG studies with six, nine and twelve human scorers, we showed that sleep stage ambiguity is the rule rather than the exception, and that sleep stage probabilities (SSPs) calculated with artificial intelligence provide an excellent estimate of this ambiguity. Here we investigate clinical and demographic factors driving this ambiguity and evaluate potential benefits of using hypnodensity in addition to the traditional hypnogram for sleep assessment. Methods SSPs were determined in 195 healthy subjects aged 20–95 years and in 49 apnea patients aged 29–73 years (AHI: 5.8–105.5 events/hour). In addition to the recommended sleep parameters, we derived the percentage of ambiguous sleep stages (SSP ≤ 0.95), the mean amount of ambiguity per sleep stage (1-SSP), sleep stage continuity (absolute difference in SSP between two epochs) and sleep stage stability (two adjacent epochs belonging to the same sleep stage with SSP > 0.95 each) as well as NREM sleep depth (weighted average of NREM SSPs). Results The percentages of ambiguous NREM epochs (±SD) increased significantly with age (Pearson’s r=0.72; p< 0.01) from 40±9% in young healthy subjects (20-39 years, n=61) to 50±9% in middle-aged healthy subjects (40-59 years, n=59) and to 62±11% in older healthy subjects (≥ 60 years, n=75). The percentages of ambiguous REM epochs did not change significantly across age (r=0.1). Apnea patients showed an increased NREM ambiguity (77±15% compared to 53±10% in age- and sex-matched healthy controls; p< 0.01), while REM ambiguity was only slightly increased (p< 0.05). Furthermore, sleep stage continuity, stability, and NREM sleep depth decrease significantly with age and are significantly lower in apnea patients than in healthy controls (p< 0.01). Conclusion Artificial intelligence-based autoscoring shows ambiguity in 40% of NREM epochs in young healthy subjects, increasing to 77% in apnea patients. Assigning a single sleep stage to each epoch and presenting sleep architecture as a traditional hypnogram may be misleading, especially for older subjects and patients with sleep-disordered breathing. A hypnodensity chart representing sleep stage probabilities reflects this sleep staging ambiguity, provides all the information contained in a hypnogram, and offers insights into sleep ambiguity, continuity, stability, and sleep depth. Support (if any)

Abstract Introduction There have been significant advances in machine learning in recent years. This means that powerful methods are now available for classification problems, such as scoring sleep stages from neurological or cardiorespiratory signals. In the present work, validation studies for both applications are presented. Methods To determine the 5 sleep stages from the neurological signals, 54 sleep-wake-related features were calculated and classified by a bidirectional long short-term memory (LSTM) network which had been trained on 1956 manual scorings of 588 PSGs from 294 subjects (supervised deep learning). To determine the 4 stages (wake, light sleep, deep sleep, REM) from cardiorespiratory signals, a convolutional neural network combined with LSTM layers was used for feature extraction and classification. This network had been trained on 685 PSGs from 391 subjects (Bakker et al. JCSM 2021). The networks obtained were validated in 428 PSGs with one and 10 PSGs with 12 manual scorings (neurological staging) as well as in 2 two datasets, each containing 296 ambulatory recordings (cardiorespiratory staging). Results Cohen’s kappa between autoscoring based on neurological signals and manual scoring was 0.74 (95%-confidence interval: 0.74-0.74) for the 428 PSGs. The intraclass correlation coefficient (ICC) for absolute agreement between autoscoring and manual scoring was for the AHI 0.97 (0.96-0.98), for the arousal index 0.79 (0.67-0.86) and for the PLMSI 0.91 (0.88-0.93). The ICC between the sleep stage probabilities derived from the 12 manual scorings and the artificial intelligence (AI) derived hypnodensity was 0.91 (0.91-0.91). Cohen’s kappa values for the cardiorespiratory sleep staging were 0.68 (0.68-0.68) and 0.64 (0.63-0.64) for the 2 datasets with 296 ambulatory recordings each. Conclusion All metrics from the PSG validation studies show substantial (Cohen’s kappa > 0.6) as well as good to excellent agreement (ICC > 0.75 or > 0.90) compared to manual scorings. As an added value of the AI-supported PSG evaluation, the probabilities of the sleep stages per epoch are determined (hypnodensity graph). The valid estimation of the sleep stages from cardiorespiratory signals by means of AI may result in improved clinical interpretation of home sleep apnea tests, which are increasingly used in the sleep-disordered breathing diagnostic pathway. Support (If Any)

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.

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.

Many studies have shown only modest differences between insomnia sufferers and matched, non-complaining normal controls in regard to their levels of daytime sleepiness and diurnal performances. The current study was conducted to determine whether such daytime comparisons might be affected by the setting (home vs. sleep lab) in which study participants sleep on the nights before such testing. The study used a counter-balanced, matched-group design in which participants underwent three consecutive nocturnal polysomnographs (PSG) conducted either in the sleep lab or in their homes prior to undergoing daytime multiple sleep latency test (MSLT) and computer-administered performance testing. The study participants were 35 (18 women and 17 men) middle-aged (40-59 years) non-complaining normal sleepers and 33 middle-aged insomnia sufferers (17 women and 16 men) who met structured interview criteria for persistent primary insomnia. Use of a hierarchical linear statistical model showed only insomnia sufferers who underwent nocturnal home PSG were more alert on the MSLT than were normal sleepers who underwent lab PSG. However, these insomnia sufferers showed a greater propensity toward attention lapses on selected reaction time tests than did either of the two normal control groups (i.e. either those who slept in the lab or those who slept at home). The results suggest the nocturnal sleep setting (home vs. lab) may affect subsequent MSLT and performance test comparisons of insomnia sufferers and normal sleepers.

STUDY OBJECTIVESThe study compared adaptation responses and sleep pattern differences shown by normal sleepers and insomnia sufferers during lab (LPSG) and home (HPSG) polysomnography.DESIGNA counter-balanced, matched-group design was used. Participants underwent 3 consecutive nocturnal LPSG's and 3 consecutive nocturnal PSG's in their homes (HPSG's).SETTINGThe sleep disorders laboratories at affiliated VA and university medical centers.PARTICIPANTSThirty-five (18 women) middle-aged (40 to 59 years) noncomplaining normal sleepers and an age-matched sample of 33 (17 women) individuals who met structured interview criteria for persistent primary insomnia were the study participants.MEASUREMENTS AND RESULTSA series of multivariate and univariate analyses were conducted with 9 common sleep parameters to address study objectives. Bed partner influences were controlled by conducting separate sets of analyses for those with and without routine home bed partners. The interaction of participant type (normal vs. insomnia), sleep setting, and PSG sequence (HPSG 1st vs. LPSG 1st) affected first night values of sleep efficiency and stage 2 sleep among those without routine bed partners, and REM latency and sleep efficiency among those with routine bed partners. Analyses which controlled for first night and sequencing effects showed a significant participant type x sleep setting interaction among those with bed partners. These latter analyses suggested that LPSG's may underestimate the home sleep time of insomnia sufferers and overestimate the sleep continuity of normal sleepers, at least among those who routinely sleep with a bed partner.CONCLUSIONSThe nocturnal recording site may influence adaptation effects and sleep pattern differences noted between insomnia sufferers and normal sleepers.

Previous findings suggest that some who report insomnia sleep well, whereas some noncomplaining individuals sleep rather poorly. This study was conducted to determine if mood, anxiety, and sleep-related beliefs might relate to perceived sleep disturbance. Thirty-two women and 32 men (aged 40-79 years) with primary insomnia and an aged-matched sample of 61 normal sleepers (31 women, 30 men) completed 6 nocturnal sleep recordings, as well as the Beck Depression Inventory (BDI), the Trait portion of the State-Trait Anxiety Inventory (STAI-2), and the Dysfunctional Beliefs and Attitudes About Sleep Questionnaire. Sleep and interview data were used to subdivide the majority of the sample (n = 108) into objective normal sleepers and subjective insomnia sufferers who seemingly slept well and subjective normal sleepers and objective insomnia sufferers who slept poorly. The 2 subjective subgroups showed the most marked differences on most of the psychometric measures. The findings suggest that the psychological factors scrutinized in this study may mediate sleep satisfaction and/or predict objective sleep difficulties.

Many laboratory polysomnographic (LPSG) studies have shown only modest sleep differences between insomniacs and matched, noncomplaining normal controls. However, the extent to which LPSG methodology affects the outcome of such comparisons has yet to be tested. In the current investigation, 32 (16 females, 16 males) older (age > or = 60 years) insomniacs and an age-matched and gender-matched sample of 32 noncomplaining normal sleepers underwent three consecutive nights of LPSG monitoring and another three consecutive nights of PSG monitoring in their homes (HPSG). By random assignment, one-half of the subjects in each group underwent LPSG first, whereas the remaining subjects underwent HPSG first. Each PSG recording was blindly scored using conventional scoring criteria, and resulting measures of total sleep period, total sleep time, sleep efficiency percent, stage 1 time, slow-wave sleep time, and rapid eye movement latency were used to compare the two subject groups within each PSG recording site (i.e. lab and home). Statistical analyses showed the normals sleepers and insomniacs evidenced similar pronounced first night effects (FNEs) when undergoing LPSG. However, neither mean values of the selected sleep parameters nor measures reflecting their night-to-night variability differentiated the insomniacs from the normal sleepers when such measures were derived from LPSG. In contrast, FNEs were generally absent for both subject groups when they underwent HPSG. Moreover, the insomniacs displayed significantly greater variability in several of their sleep measures during HPSG than did the normal sleepers. Overall, results suggest FNEs are a concern mainly when using LPSG, and HPSG may be more sensitive than LPSG for documenting sleep differences between normal sleepers and insomniacs. Additional studies are needed to determine if the findings reported herein are similar for young and middle-aged adults.

Complaints of daytime dysfunction are common among chronic insomniacs, but laboratory comparisons of insomniacs and age-matched and gender-matched normal controls have generally failed to document these complaints. However, a few studies, which allowed subjects to sleep in their homes on the nights before daytime testing, have shown some relative diurnal deficits among insomniacs. The current study compared the effects of nocturnal laboratory and home polysomnogram (PSG) studies on subsequent daytime test results among older insomniacs and normal sleepers. Insomniacs (n = 32) and normal sleepers (n = 32) were randomly assigned to first undergo three nights of nocturnal PSG monitoring either in the sleep laboratory (16 insomniacs, 16 normal sleepers) or in their homes (16 insomniacs, 16 normal sleepers). Following the third night of PSG monitoring, subjects spent 1 day in the sleep laboratory, where they completed a four-trial multiple sleep latency test along with four trials of a computer-administered performance test battery. Results showed that insomniacs, as a group, were slightly, albeit consistently, sleepier than were normal sleepers following nights of home sleep monitoring, but a reverse of this trend was found among subjects who underwent nocturnal laboratory PSG before daytime testing. Furthermore, normal sleepers showed faster reaction times on a signal detection task than did insomniacs within the subgroup who underwent home PSGs prior to such testing. However, within the subgroup that underwent nocturnal laboratory PSGs, insomniacs' signal detection reaction times were significantly faster than those shown by normal sleepers. Results provide some support for the speculation that the nocturnal PSG monitoring site, used as a precursor to daytime testing, may systematically affect daytime comparisons between insomniacs and matched controls. Moreover, these results suggest that the use of home-based nocturnal PSG monitoring prior to daytime testing may provide an enhanced understanding of insomniacs' diurnal complaints.