Ventilatory Burden as a Measure of Obstructive Sleep Apnea Severity Is Predictive of Cardiovascular and All-Cause Mortality.

Rationale: The apnea-hypopnea index (AHI), used for the diagnosis of obstructive sleep apnea, captures only the frequency of respiratory events and has demonstrable limitations. Objectives: We propose a novel automated measure, termed "ventilatory burden" (VB), that represents the proportion of overnight breaths with less than 50% normalized amplitude, and we show its ability to overcome limitations of AHI. Methods: Data from two epidemiological cohorts (EPISONO [Sao Paolo Epidemiological Study] and SHHS [Sleep Heart Health Study]) and two retrospective clinical cohorts (DAYFUN; New York University Center for Brain Health) were used in this study to 1) derive the normative range of VB, 2) assess the relationship between degree of upper airway obstruction and VB, and 3) assess the relationship between VB and all-cause and cardiovascular disease (CVD) mortality with and without hypoxic burden that was derived using an in-house automated algorithm. Measurements and Main Results: The 95th percentiles of VB in asymptomatic healthy subjects across the EPISONO and the DAYFUN cohorts were 25.2% and 26.7%, respectively (median [interquartile range], VBEPISONO, 5.5 [3.5-9.7]%; VBDAYFUN, 9.8 [6.4-15.6]%). VB was associated with the degree of upper airway obstruction in a dose-response manner (VBuntreated, 31.6 [27.1]%; VBtreated, 7.2 [4.7]%; VBsuboptimally treated, 17.6 [18.7]%; VBoff-treatment, 41.6 [18.1]%) and exhibited low night-to-night variability (intraclass correlation coefficient [2,1], 0.89). VB was predictive of all-cause and CVD mortality in the SHHS cohort before and after adjusting for covariates including hypoxic burden. Although AHI was predictive of all-cause mortality, it was not associated with CVD mortality in the SHHS cohort. Conclusions: Automated VB can effectively assess obstructive sleep apnea severity, is predictive of all-cause and CVD mortality, and may be a viable alternative to the AHI.

Night-to-night reliability and agreement of obstructive sleep apnea pathophysiologic mechanisms estimated with phenotyping using polysomnography in cognitively normal elderly participants.

STUDY OBJECTIVES: Phenotyping using polysomnography (PUP) is an algorithmic method to quantify physiologic mechanisms underlying obstructive sleep apnea (OSA): loop gain (LG1), arousal threshold (ArTH), and upper airway collapsibility (Vpassive) and muscular compensation (Vcomp). The consecutive-night test-retest reliability and agreement of PUP-derived estimates are unknown. From a cohort of elderly (age ≥55 years), largely non-sleepy, community-dwelling volunteers who underwent in-lab polysomnography (PSG) on 2 consecutive nights, we determined the test-retest reliability and agreement of PUP-estimated physiologic factors. METHODS: Participants who had an apnea-hypopnea index (AHI3A) of at least 15 events per hour on the first night were included. PUP analyses were performed on each of the two PSGs from each participant. Physiologic factor estimates were derived from NREM sleep and compared across nights using intraclass correlation coefficients for reliability and smallest real differences (SRD) for agreement. RESULTS: Two PSGs from each of 43 participants (86 total) were analyzed. A first-night effect was evident with increased sleep time and stability and decreased OSA severity on the second night. LG1, ArTH, and Vpassive demonstrated good reliability (ICC > 0.80). Vcomp had modest reliability (ICC = 0.67). For all physiologic factors, SRD values were approximately 20% or more of the observed ranges, suggesting limited agreement of longitudinal measurements for a given individual. CONCLUSIONS: For NREM sleep in cognitively normal elderly individuals with OSA, PUP-estimated LG1, ArTH, and Vpassive demonstrated consistent relative ranking of individuals (good reliability) on short-term repeat measurement. For all physiologic factors, longitudinal measurements demonstrated substantial intraindividual variability across nights (limited agreement).

International Consensus Statement on Obstructive Sleep Apnea.

BACKGROUND: Evaluation and interpretation of the literature on obstructive sleep apnea (OSA) allows for consolidation and determination of the key factors important for clinical management of the adult OSA patient. Toward this goal, an international collaborative of multidisciplinary experts in sleep apnea evaluation and treatment have produced the International Consensus statement on Obstructive Sleep Apnea (ICS:OSA). METHODS: Using previously defined methodology, focal topics in OSA were assigned as literature review (LR), evidence-based review (EBR), or evidence-based review with recommendations (EBR-R) formats. Each topic incorporated the available and relevant evidence which was summarized and graded on study quality. Each topic and section underwent iterative review and the ICS:OSA was created and reviewed by all authors for consensus. RESULTS: The ICS:OSA addresses OSA syndrome definitions, pathophysiology, epidemiology, risk factors for disease, screening methods, diagnostic testing types, multiple treatment modalities, and effects of OSA treatment on multiple OSA-associated comorbidities. Specific focus on outcomes with positive airway pressure (PAP) and surgical treatments were evaluated. CONCLUSION: This review of the literature consolidates the available knowledge and identifies the limitations of the current evidence on OSA. This effort aims to create a resource for OSA evidence-based practice and identify future research needs. Knowledge gaps and research opportunities include improving the metrics of OSA disease, determining the optimal OSA screening paradigms, developing strategies for PAP adherence and longitudinal care, enhancing selection of PAP alternatives and surgery, understanding health risk outcomes, and translating evidence into individualized approaches to therapy.

The Link between Obstructive Sleep Apnea and Neurocognitive Impairment: An Official American Thoracic Society Workshop Report.

There is emerging evidence that obstructive sleep apnea (OSA) is a risk factor for preclinical Alzheimer's disease (AD). An American Thoracic Society workshop was convened that included clinicians, basic scientists, and epidemiologists with expertise in OSA, cognition, and dementia, with the overall objectives of summarizing the state of knowledge in the field, identifying important research gaps, and identifying potential directions for future research. Although currently available cognitive screening tests may allow for identification of cognitive impairment in patients with OSA, they should be interpreted with caution. Neuroimaging in OSA can provide surrogate measures of disease chronicity, but it has methodological limitations. Most data on the impact of OSA treatment on cognition are for continuous positive airway pressure (CPAP), with limited data for other treatments. The cognitive domains improving with CPAP show considerable heterogeneity across studies. OSA can negatively influence risk, manifestations, and possibly progression of AD and other forms of dementia. Sleep-dependent memory tasks need greater incorporation into OSA testing, with better delineation of sleep fragmentation versus intermittent hypoxia effects. Plasma biomarkers may prove to be sensitive, feasible, and scalable biomarkers for use in clinical trials. There is strong biological plausibility, but insufficient data, to prove bidirectional causality of the associations between OSA and aging pathology. Engaging, recruiting, and retaining diverse populations in health care and research may help to decrease racial and ethnic disparities in OSA and AD. Key recommendations from the workshop include research aimed at underlying mechanisms; longer-term longitudinal studies with objective assessment of OSA, sensitive cognitive markers, and sleep-dependent cognitive tasks; and pragmatic study designs for interventional studies that control for other factors that may impact cognitive outcomes and use novel biomarkers.

Association between lower body temperature and increased tau pathology in cognitively normal older adults.

BACKGROUND: Preclinical studies suggest body temperature (Tb) and consequently brain temperature has the potential to bidirectionally interact with tau pathology in Alzheimer's Disease (AD). Tau phosphorylation is substantially increased by a small (<1 °C) decrease in temperature within the human physiological range, and thermoregulatory nuclei are affected by tau pathology early in the AD continuum. In this study we evaluated whether Tb (as a proxy for brain temperature) is cross-sectionally associated with clinically utilized markers of tau pathology in cognitively normal older adults. METHODS: Tb was continuously measured with ingestible telemetry sensors for 48 h. This period included two nights of nocturnal polysomnography to delineate whether Tb during waking vs sleep is differentially associated with tau pathology. Tau phosphorylation was assessed with plasma and cerebrospinal fluid (CSF) tau phosphorylated at threonine 181 (P-tau), sampled the day following Tb measurement. In addition, neurofibrillary tangle (NFT) burden in early Braak stage regions was imaged with PET-MR using the [18F]MK-6240 radiotracer on average one month later. RESULTS: Lower Tb was associated with increased NFT burden, as well as increased plasma and CSF P-tau levels (p < 0.05). NFT burden was associated with lower Tb during waking (p < 0.05) but not during sleep intervals. Plasma and CSF P-tau levels were highly correlated with each other (p < 0.05), and both variables were correlated with tau tangle radiotracer uptake (p < 0.05). CONCLUSIONS: These results, the first available for human, suggest that lower Tb in older adults may be associated with increased tau pathology. Our findings add to the substantial preclinical literature associating lower body and brain temperature with tau hyperphosphorylation. CLINICAL TRIAL NUMBER: NCT03053908.

Characterizing sleep-wake patterns in mothers and children in an agrarian community: results from the Ghana Randomized Air Pollution and Health Study.

STUDY OBJECTIVES: Several studies have examined sleep patterns in rural/indigenous communities, however little is known about sleep characteristics in women of reproductive age, and children within these populations. We investigate sleep-wake patterns in mothers and children (ages 3-5 years) leveraging data from the Ghana Randomized Air Pollution and Health Study (GRAPHS). METHODS: The GRAPHS cohort comprises of rural/agrarian communities in Ghana and collected multiday actigraphy in a subset of women and children to assess objective sleep-wake patterns. Data were scored using the Cole-Kripke and Sadeh algorithms for mothers/children. We report descriptive, baseline characteristics and objective sleep measures, compared by access to electricity/poverty status. RESULTS: We analyzed data for 58 mothers (mean age 33 ± 6.6) and 64 children (mean age 4 ± 0.4). For mothers, mean bedtime was 9:40 pm ± 56 min, risetime 5:46 am ± 40 min, and total sleep time (TST) was 6.3 h ± 46 min. For children, median bedtime was 8:07 pm (interquartile range [IQR]: 7:50,8:43), risetime 6:09 am (IQR: 5:50,6:37), and mean 24-h TST 10.44 h ± 78 min. Children with access to electricity had a reduced TST compared to those without electricity (p = 0.02). Mean bedtime was later for both mothers (p = 0.05) and children (p = 0.08) classified as poor. CONCLUSIONS: Mothers in our cohort demonstrated a shorter TST, and earlier bed/risetimes compared to adults in postindustrialized nations. In contrast, children had a higher TST compared to children in postindustrialized nations, also with earlier sleep-onset and offset times. Investigating objective sleep-wake patterns in rural/indigenous communities can highlight important differences in sleep health related to sex, race/ethnicity, and socioeconomic status, and help estimate the impact of industrialization on sleep in developed countries.

Immediate Physiological Responses to Inspiratory Flow Limited Events in Mild Obstructive Sleep Apnea.

Rationale: Inspiratory flow limitation (IFL), characterized by flattening of individual breaths on the airflow/time tracing, is a noninvasive indicator of elevated upper airway resistance. An IFL "event" in isolation has not been defined, nor has the ability to reproducibly identify event occurrence been tested. IFL events and their association with immediate physiological responses-as well as the impact of characteristics such as age, sex, sleep stage, sleepiness, and event duration on their association with such outcomes-have not been studied. Symptomatic patients with a normal to mildly abnormal apnea-hypopnea index who have predominant IFL on their polysomnography may benefit from treatment. Objectives: To test the reproducibility of identifying IFL events and their termination and to determine the frequency of the immediate physiological response to their occurrence, including desaturation, electroencephalography (EEG) arousal, and increased heart rate (HR). Methods: Fifty-eight patients with obstructive sleep apnea (OSA) underwent full diagnostic polysomnography. IFL events and their termination were identified manually using predefined rules from the unscored nasal cannula flow channel alone and were evaluated for responses such as EEG arousal, oxygen desaturation of ⩾3%, and HR increase. Results: Interscorer reliability was acceptable, with an average percent agreement for occurrence of 82% ± 3%. Of all IFL events, 24% (regardless of the definition) were not associated with an EEG arousal, an increase in HR, or O2 desaturation. Of all IFL events scored, 25% caused O2 desaturation, 40% were associated with an EEG arousal, and 55% were associated with an increase in HR; 67% caused either an EEG arousal and/or an increase in HR. Responses were observed to occur either in isolation or in combination. IFL events that terminated with at least two non-IFL breaths, one of which had a 200% increase in amplitude, were significantly associated with O2 desaturation, EEG arousal, and increase in HR compared with events that ended in one non-IFL breath. IFL events that had a >50% reduction in flow amplitude compared with baseline were significantly associated with O2 desaturation compared with events that had a 30% reduction or less. Conclusions: Most IFL events resulted in immediate physiological responses, and no single consequence reliably occurred after every event. We propose a framework that can incorporate the scoring of IFL events into assessing the diagnosis and severity of OSA and suggest that no single consequence be used to define IFL as a respiratory event. The relationship of IFL events to OSA outcomes remains to be tested.

Interactive Associations of Neuropsychiatry Inventory-Questionnaire Assessed Sleep Disturbance and Vascular Risk on Alzheimer's Disease Stage Progression in Clinically Normal Older Adults.

Background: To determine whether sleep disturbance (SD) and vascular-risk interact to promote Alzheimer's disease (AD) stage-progression in normal, community-dwelling older adults and evaluate their combined risk beyond that of established AD biomarkers. Methods: Longitudinal data from the National Alzheimer's Coordinating Center Uniform-Dataset. SD data (i.e., SD+ vs. SD-), as characterized by the Neuropsychiatric Inventory-Questionnaire, were derived from 10,600 participants at baseline, with at-least one follow-up visit. A subset (n = 361) had baseline cerebrospinal fluid (CSF) biomarkers and MRI data. The Framingham heart study general cardiovascular disease (FHS-CVD) risk-score was used to quantify vascular risk. Amnestic mild cognitive impairment (aMCI) diagnosis during follow-up characterized AD stage-progression. Logistic mixed-effects models with random intercept and slope examined the interaction of SD and vascular risk on prospective aMCI diagnosis. Results: Of the 10,600 participants, 1,017 (9.6%) reported SD and 6,572 (62%) were female. The overall mean (SD) age was 70.5 (6.5), and follow-up time was 5.1 (2.7) years. SD and the FHS-CVD risk-score were each associated with incident aMCI (aOR: 1.42 and aOR: 2.11, p < 0.01 for both). The interaction of SD and FHS-CVD risk-score with time was significant (aOR: 2.87, p < 0.01), suggesting a synergistic effect. SD and FHS-CVD risk-score estimates remained significantly associated with incident aMCI even after adjusting for CSF (Aß, T-tau, P-tau) and hippocampal volume (n = 361) (aOR: 2.55, p < 0.01), and approximated risk-estimates of each biomarker in the sample where data was available. Conclusions: Clinical measures of sleep and vascular risk may complement current AD biomarkers in assessing risk of cognitive decline in older adults.

Selective Continuous Positive Airway Pressure Withdrawal With Supplemental Oxygen During Slow-Wave Sleep as a Method of Dissociating Sleep Fragmentation and Intermittent Hypoxemia-Related Sleep Disruption in Obstructive Sleep Apnea.

Obstructive sleep apnea (OSA) is considered to impair memory processing and increase the expression of amyloid-ß (Aß) and risk for Alzheimer's disease (AD). Given the evidence that slow-wave sleep (SWS) is important in both memory and Aß metabolism, a better understanding of the mechanisms by which OSA impacts memory and risk for AD can stem from evaluating the role of disruption of SWS specifically and, when such disruption occurs through OSA, from evaluating the individual contributions of sleep fragmentation (SF) and intermittent hypoxemia (IH). In this study, we used continuous positive airway pressure (CPAP) withdrawal to recapitulate SWS-specific OSA during polysomnography (PSG), creating conditions of both SF and IH in SWS only. During separate PSGs, we created the conditions of SWS fragmentation but used oxygen to attenuate IH. We studied 24 patients (average age of 55 years, 29% female) with moderate-to-severe OSA [Apnea-Hypopnea Index (AHI); AHI4% > 20/h], who were treated and adherent to CPAP. Participants spent three separate nights in the laboratory under three conditions as follows: (1) consolidated sleep with CPAP held at therapeutic pressure (CPAP); (2) CPAP withdrawn exclusively in SWS (OSA SWS ) breathing room air; and (3) CPAP withdrawn exclusively in SWS with the addition of oxygen during pressure withdrawal (OSA SWS + O 2). Multiple measures of SF (e.g., arousal index) and IH (e.g., hypoxic burden), during SWS, were compared according to condition. Arousal index in SWS during CPAP withdrawal was significantly greater compared to CPAP but not significantly different with and without oxygen (CPAP = 1.1/h, OSA SWS + O2 = 10.7/h, OSA SWS = 10.6/h). However, hypoxic burden during SWS was significantly reduced with oxygen compared to without oxygen [OSA SWS + O 2 = 23 (%min)/h, OSA SWS = 37 (%min)/h]. No significant OSA was observed in non-rapid eye movement (REM) stage 1 (NREM 1), non-REM stage 2 (NREM 2), or REM sleep (e.g., non-SWS) in any condition. The SWS-specific CPAP withdrawal induces OSA with SF and IH. The addition of oxygen during CPAP withdrawal results in SF with significantly less severe hypoxemia during the induced respiratory events in SWS. This model of SWS-specific CPAP withdrawal disrupts SWS with a physiologically relevant stimulus and facilitates the differentiation of SF and IH in OSA.

Sleep duration and vascular inflammation using hybrid positron emission tomography/magnetic resonance imaging: results from the Multi-Ethnic Study of Atherosclerosis.

STUDY OBJECTIVES: Short sleep duration (SD) is associated with cardiovascular disease. We investigated the relationship between objective SD and subclinical atherosclerosis employing hybrid positron emission tomography/magnetic resonance imaging with 18F-FDG tracer in the MESA cohort. METHODS: We utilized data from Multi-Ethnic Study of Atherosclerosis-SLEEP and Multi-Ethnic Study of Atherosclerosis-PET ancillary studies. SD and sleep fragmentation index (SFI) were assessed using 7-day actigraphy. The primary and secondary outcomes were carotid inflammation, defined using target-to-background ratios, and measures of carotid wall remodeling (carotid wall thickness), summarized by SD category. Multivariable linear regression was performed to assess the association between SD and SFI with the primary/secondary outcomes, adjusting for several covariates including apnea-hypopnea index, and cardiovascular disease risk. RESULTS: Our analytical sample (n = 58) was 62% female (mean age 68 ± 8.4 years). Average SD was 5.1 ± 0.9 hours in the short SD group (≤ 6 h/night, 31%), and 7.1 ± 0.8 hours in the normal SD group (69%). Prevalence of pathologic vascular inflammation (maximal target-to-background ratio > 1.6) was higher in the short SD group (89% vs 53%, P = .01). Those with short SD had a higher maximal target-to-background ratio (1.77 vs 1.71), although this was not statistically significant (P = .39). Carotid wall thickness was positively associated with SFI even after adjusting for covariates (Beta [standard error] = 0.073 ± [0.032], P = .03). CONCLUSIONS: Prevalence of pathologic vascular inflammation was higher among those who slept ≤ 6 hours, and vascular inflammation was higher among those with a SD of ≤ 6 hours. Interestingly, SFI was positively associated with carotid wall thickness even after adjustment for covariates. Our results are hypothesis generating but suggest that both habitual SD and SFI should be investigated in future studies as potential risk factors for subclinical atherosclerosis. CITATION: Kundel V, Reid M, Fayad Z, et al. Sleep duration and vascular inflammation using hybrid positron emission tomography/magnetic resonance imaging: results from the Multi-Ethnic Study of Atherosclerosis. J Clin Sleep Med. 2021;17(10):2009-2018.

Quantification of airway conductance from noninvasive ventilatory drive in patients with sleep apnea.

Upper airway conductance, the ratio of inspiratory airflow to inspiratory effort, quantifies the degree of airway obstruction in hypopneas observed in sleep apnea. We evaluated the ratio of ventilation to noninvasive ventilatory drive as a surrogate of conductance. Furthermore, we developed and tested a refinement of noninvasive drive to incorporate the interactions of inspiratory flow, pressure, and drive to better estimate conductance. Hypopneas were compiled from existing polysomnography studies with esophageal catheterization in 18 patients with known or suspected sleep apnea, totaling 1,517 hypopneas during NREM sleep. For each hypopnea, reference standard conductance was calculated as the ratio of peak inspiratory flow to esophageal pressure change during inspiration. Ventilatory drive was calculated using the algorithm developed by Terrill et al. and then mathematically modified according to the presence or absence of flow limitation to noninvasively estimate esophageal pressure. The ratio of ventilation to ventilatory drive and the ratio of peak inspiratory flow to estimated esophageal pressure were each compared with the reference standard for all hypopneas and for median values from individual patients. Hypopnea ventilation to drive ratios were of limited correlation with the reference standard (R2 = 0.17, individual hypopneas; R2 = 0.03, median patient values). Modification of drive to estimated pressure yielded estimated conductance, which strongly correlated with reference standard conductance (R2 = 0.49, individual hypopneas; R2 = 0.77, median patient values). We conclude that the severity of airway obstruction during hypopneas may be estimated from noninvasive drive by accounting for mechanical effects of flow on pressure. NEW & NOTEWORTHY Classification of hypopneas as obstructive (decreased upper airway conductance) or central (decreased inspiratory flow commensurate with decreased effort) is complicated by the requirement of invasive methods, such as esophageal manometry. Here, we demonstrate that using a few esophageal pressure measurements to account for the interactions between inspiratory flow, pressure, and noninvasive ventilatory drive allows estimation of upper airway conductance. Further studies may use these findings to quantify airway obstruction completely noninvasively.

Endotyping Sleep Apnea One Breath at a Time: An Automated Approach for Separating Obstructive from Central Sleep-disordered Breathing.

Rationale: Determining whether an individual has obstructive or central sleep apnea is fundamental to selecting the appropriate treatment. Objectives: Here we derive an automated breath-by-breath probability of obstruction, as a surrogate of gold-standard upper airway resistance, using hallmarks of upper airway obstruction visible on clinical sleep studies. Methods: From five nocturnal polysomnography signals (airflow, thoracic and abdominal effort, oxygen saturation, and snore), nine features were extracted and weighted to derive the breath-by-breath probability of obstruction (Pobs). A development and initial test set of 29 subjects (development = 6, test = 23) (New York, NY) and a second test set of 39 subjects (Solingen, Germany), both with esophageal manometry, were used to develop Pobs and validate it against gold-standard upper airway resistance. A separate dataset of 114 subjects with 2 consecutive nocturnal polysomnographies (New York, NY) without esophageal manometry was used to assess the night-to-night variability of Pobs. Measurements and Main Results: A total of 1,962,229 breaths were analyzed. On a breath-by-breath level, Pobs was strongly correlated with normalized upper airway resistance in both test sets (set 1: cubic adjusted [adj.] R2 = 0.87, P < 0.001, area under the receiver operating characteristic curve = 0.74; set 2: cubic adj. R2 = 0.83, P < 0.001, area under the receiver operating characteristic curve = 0.7). On a subject level, median Pobs was associated with the median normalized upper airway resistance (set 1: linear adj. R2 = 0.59, P < 0.001; set 2: linear adj. R2 = 0.45, P < 0.001). Median Pobs exhibited low night-to-night variability [intraclass correlation(2, 1) = 0.93]. Conclusions: Using nearly 2 million breaths from 182 subjects, we show that breath-by-breath probability of obstruction can reliably predict the overall burden of obstructed breaths in individual subjects and can aid in determining the type of sleep apnea.

WaveSleepNet: An interpretable deep convolutional neural network for the continuous classification of mouse sleep and wake.

BACKGROUND: Recent advancement in deep learning provides a pivotal opportunity to potentially supplement or supplant the limiting step of manual sleep scoring. NEW METHOD: In this paper, we characterize the WaveSleepNet (WSN), a deep convolutional neural network (CNN) that uses wavelet transformed images of mouse EEG/EMG signals to autoscore sleep and wake. RESULTS: WSN achieves an epoch by epoch mean accuracy of 0.86 and mean F1 score of 0.82 compared to manual scoring by a human expert. In mice experiencing mechanically induced sleep fragmentation, an overall epoch by epoch mean accuracy of 0.80 is achieved by WSN and classification of non-REM (NREM) sleep is not compromised, but the high level of sleep fragmentation results in WSN having greater difficulty differentiating REM from NREM sleep. We also find that WSN achieves similar levels of accuracy on an independent dataset of externally acquired EEG/EMG recordings with an overall epoch by epoch accuracy of 0.91. We also compared conventional summary sleep metrics in mice sleeping ad libitum. WSN systematically biases sleep fragmentation metrics of bout number and bout length leading to an overestimated degree of sleep fragmentation. COMPARISON WITH EXISTING METHODS: In a cross-validation, WSN has a greater macro and stage-specific accuracy compared to a conventional random forest classifier. Examining the WSN, we find that it automatically learns spectral features consistent with manual scoring criteria that are used to define each class. CONCLUSION: These results suggest to us that WSN is capable of learning visually agreeable features and may be useful as a supplement to human manual scoring.