Towards ASSR-based hearing assessment using natural sounds.

Objective. The auditory steady-state response (ASSR) allows estimation of hearing thresholds. The ASSR can be estimated from electroencephalography (EEG) recordings from electrodes positioned on both the scalp and within the ear (ear-EEG). Ear-EEG can potentially be integrated into hearing aids, which would enable automatic fitting of the hearing device in daily life. The conventional stimuli for ASSR-based hearing assessment, such as pure tones and chirps, are monotonous and tiresome, making them inconvenient for repeated use in everyday situations. In this study we investigate the use of natural speech sounds for ASSR estimation.Approach.EEG was recorded from 22 normal hearing subjects from both scalp and ear electrodes. Subjects were stimulated monaurally with 180 min of speech stimulus modified by applying a 40 Hz amplitude modulation (AM) to an octave frequency sub-band centered at 1 kHz. Each 50 ms sub-interval in the AM sub-band was scaled to match one of 10 pre-defined levels (0-45 dB sensation level, 5 dB steps). The apparent latency for the ASSR was estimated as the maximum average cross-correlation between the envelope of the AM sub-band and the recorded EEG and was used to align the EEG signal with the audio signal. The EEG was then split up into sub-epochs of 50 ms length and sorted according to the stimulation level. ASSR was estimated for each level for both scalp- and ear-EEG.Main results. Significant ASSRs with increasing amplitude as a function of presentation level were recorded from both scalp and ear electrode configurations.Significance. Utilizing natural sounds in ASSR estimation offers the potential for electrophysiological hearing assessment that are more comfortable and less fatiguing compared to existing ASSR methods. Combined with ear-EEG, this approach may allow convenient hearing threshold estimation in everyday life, utilizing ambient sounds. Additionally, it may facilitate both initial fitting and subsequent adjustments of hearing aids outside of clinical settings.

Subclinical epileptiform discharges in Alzheimer's disease are associated with increased hippocampal blood flow.

BACKGROUND: In epilepsy, the ictal phase leads to cerebral hyperperfusion while hypoperfusion is present in the interictal phases. Patients with Alzheimer's disease (AD) have an increased prevalence of epileptiform discharges and a study using intracranial electrodes have shown that these are very frequent in the hippocampus. However, it is not known whether there is an association between hippocampal hyperexcitability and regional cerebral blood flow (rCBF). The objective of the study was to investigate the association between rCBF in hippocampus and epileptiform discharges as measured with ear-EEG in patients with Alzheimer's disease. Our hypothesis was that increased spike frequency may be associated with increased rCBF in hippocampus. METHODS: A total of 24 patients with AD, and 15 HC were included in the analysis. Using linear regression, we investigated the association between rCBF as measured with arterial spin-labelling MRI (ASL-MRI) in the hippocampus and the number of spikes/sharp waves per 24 h as assessed by ear-EEG. RESULTS: No significant difference in hippocampal rCBF was found between AD and HC (p-value = 0.367). A significant linear association between spike frequency and normalized rCBF in the hippocampus was found for patients with AD (estimate: 0.109, t-value = 4.03, p-value < 0.001). Changes in areas that typically show group differences (temporal-parietal cortex) were found in patients with AD, compared to HC. CONCLUSIONS: Increased spike frequency was accompanied by a hemodynamic response of increased blood flow in the hippocampus in patients with AD. This phenomenon has also been shown in patients with epilepsy and supports the hypothesis of hyperexcitability in patients with AD. The lack of a significant difference in hippocampal rCBF may be due to an increased frequency of epileptiform discharges in patients with AD. TRIAL REGISTRATION: The study is registered at clinicaltrials.gov (NCT04436341).

Effect of Stimulus Bandwidth on the Auditory Steady-State Response in Scalp- and Ear-EEG.

OBJECTIVES: The auditory steady-state response (ASSR) enables hearing threshold estimation based on electroencephalography (EEG) recordings. The choice of stimulus type has an impact on both the detectability and the frequency specificity of the ASSR. Amplitude modulated pure tones provide the most frequency-specific ASSR, but responses to pure tones are weak. The ASSR can be enhanced by increasing the bandwidth of the stimulus, but this comes at the cost of a decrease in the frequency specificity of the measured response. The objective of the present study is to investigate the relationship between stimulus bandwidth and ASSR amplitude. DESIGN: The amplitude of ASSR was measured for five types of stimuli: 1 kHz pure tone and band-pass noise with 1/3, 1/2, 1, and 2 octave bandwidths centered at 1 kHz. All stimuli were amplitude modulated with a 40 Hz sinusoid. Responses to all stimulus types were measured at 30, 40, and 50 dB SL. ASSRs were measured concurrently using both conventional scalp-EEG and ear-EEG. RESULTS: Stimulus bandwidth and sound intensity were both found to have a significant effect on the ASSR amplitude for scalp- and ear-EEG recordings. In scalp-EEG ASSRs to all bandwidth stimuli were found to be significantly larger than ASSRs to pure tone at low sound intensity. At higher sound intensities, however, significantly larger responses were only obtained for 1- and 2-octave bandwidth stimuli. In ear-EEG, only the ASSR to 2 octave bandwidth stimulus was significantly larger than the ASSR to amplitude modulated pure tones. CONCLUSIONS: At low presentation levels, even small increases in stimulus bandwidth (1/3 and 1/2 octave) improve the detectability of ASSR in scalp-EEG with little or no impact on the frequency specificity. In comparison, a larger increase in stimulus bandwidth was needed to improve the ASSR detectability in the ear-EEG recordings.

Subclinical Epileptiform Activity in Dementia with Lewy Bodies.

BACKGROUND: Patients with dementia with Lewy bodies (DLB) have a higher probability of seizures than in normal aging and in other types of neurodegenerative disorders. Depositions of α-synuclein, a pathological hallmark of DLB, can induce network excitability, which can escalate into seizure activity. Indicator of seizures are epileptiform discharges as observed using electroencephalography (EEG). However, no studies have so far investigated the occurrence of interictal epileptiform discharges (IED) in patients with DLB. OBJECTIVES: To investigate if IED as measured with ear-EEG occurs with a higher frequency in patients with DLB compared to healthy controls (HC). METHODS: In this longitudinal observational exploratory study, 10 patients with DLB and 15 HC were included in the analysis. Patients with DLB underwent up to three ear-EEG recordings, each lasting up to 2 days, over a period of 6 months. RESULTS: At baseline, IED were detected in 80% of patients with DLB and in 46.7% of HC. The spike frequency (spikes or sharp waves/24 hours) was significantly higher in patients with DLB as compared to HC with a risk ratio of 2.52 (CI, 1.42-4.61; P-value = 0.001). Most IED occurred at night. CONCLUSIONS: Long-term outpatient ear-EEG monitoring detects IED in most patients with DLB with an increased spike frequency compared to HC. This study extends the spectrum of neurodegenerative disorders in which epileptiform discharges occurs at an elevated frequency. It is possible that epileptiform discharges are, therefore, a consequence of neurodegeneration. © 2023 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.

Detection of subclinical epileptiform discharges in Alzheimer's disease using long-term outpatient EEG monitoring.

BACKGROUND: In patients with Alzheimer's disease (AD) without clinical seizures, up to half have epileptiform discharges on long-term in-patient electroencephalography (EEG) recordings. Long-term in-patient monitoring is obtrusive, and expensive as compared to outpatient monitoring. No studies have so far investigated if long-term outpatient EEG monitoring is able to identify epileptiform discharges in AD. Our aim is to investigate if epileptiform discharges as measured with ear-EEG are more common in patients with AD compared to healthy elderly controls (HC). METHODS: In this longitudinal observational study, 24 patients with mild to moderate AD and 15 age-matched HC were included in the analysis. Patients with AD underwent up to three ear-EEG recordings, each lasting up to two days, within 6 months. RESULTS: The first recording was defined as the baseline recording. At baseline, epileptiform discharges were detected in 75.0% of patients with AD and in 46.7% of HC (p-value = 0.073). The spike frequency (spikes or sharp waves/24 h) was significantly higher in patients with AD as compared to HC with a risk ratio of 2.90 (CI: 1.77-5.01, p < 0.001). Most patients with AD (91.7%) showed epileptiform discharges when combining all ear-EEG recordings. CONCLUSIONS: Long-term ear-EEG monitoring detects epileptiform discharges in most patients with AD with a three-fold increased spike frequency compared to HC, which most likely originates from the temporal lobes. Since most patients showed epileptiform discharges with multiple recordings, elevated spike frequency should be considered a marker of hyperexcitability in AD.

Long-term ear-EEG monitoring of sleep - A case study during shift work.

The interest in sleep as a potential clinical biomarker is growing, but the standard method of sleep assessment, polysomnography, is expensive, time consuming, and requires a lot of expert assistance for both set-up and interpretation. To make sleep analysis more available both in research and in the clinic, there is a need for a reliable wearable device for sleep staging. In this case study, we test ear-electroencephalography. A wearable, where electrodes are placed in the outer ear, as a platform for longitudinal at-home recording of sleep. We explore the usability of the ear-electroencephalography in a shift work case with alternating sleep conditions. We find the ear-electroencephalography platform to be reliable both in terms of showing substantial agreement to polysomnography after long-time use (with an overall agreement, using Cohen's kappa, of 0.72) and by being unobtrusive enough to wear during night shift conditions. We find that fractions of non-rapid eye movement sleep and transition probability between sleep stages show great potential as sleep metrics when exploring quantitative differences in sleep architecture between shifting sleep conditions. This study shows that the ear-electroencephalography platform holds great potential as a reliable wearable for quantifying sleep "in the wild", pushing this technology further towards clinical adaptation.

At-home sleep monitoring using generic ear-EEG.

Introduction: A device comprising two generic earpieces with embedded dry electrodes for ear-centered electroencephalography (ear-EEG) was developed. The objective was to provide ear-EEG based sleep monitoring to a wide range of the population without tailoring the device to the individual. Methods: To validate the device ten healthy subjects were recruited for a 12-night sleep study. The study was divided into two parts; part A comprised two nights with both ear-EEG and polysomnography (PSG), and part B comprised 10 nights using only ear-EEG. In addition to the electrophysiological measurements, subjects filled out a questionnaire after each night of sleep. Results: The subjects reported that the ear-EEG system was easy to use, and that the comfort was better in part B. The performance of the system was validated by comparing automatic sleep scoring based on ear-EEG with PSG-based sleep scoring performed by a professional trained sleep scorer. Cohen's kappa was used to assess the agreement between the manual and automatic sleep scorings, and the study showed an average kappa value of 0.71. The majority of the 20 recordings from part A yielded a kappa value above 0.7. The study was compared to a companioned study conducted with individualized earpieces. To compare the sleep across the two studies and two parts, 7 different sleeps metrics were calculated based on the automatic sleep scorings. The ear-EEG nights were validated through linear mixed model analysis in which the effects of equipment (individualized vs. generic earpieces), part (PSG and ear-EEG vs. only ear-EEG) and subject were investigated. We found that the subject effect was significant for all computed sleep metrics. Furthermore, the equipment did not show any statistical significant effect on any of the sleep metrics. Discussion: These results corroborate that generic ear-EEG is a promising alternative to the gold standard PSG for sleep stage monitoring. This will allow sleep stage monitoring to be performed in a less obtrusive way and over longer periods of time, thereby enabling diagnosis and treatment of diseases with associated sleep disorders.

Long-Term EEG Monitoring in Patients with Alzheimer's Disease Using Ear-EEG: A Feasibility Study.

BACKGROUND: Previous studies have reported that epileptiform activity may be detectible in nearly half of patients with Alzheimer's disease (AD) on long-term electroencephalographic (EEG) recordings. However, such recordings can be uncomfortable, expensive, and difficult. Ear-EEG has shown promising results for long-term EEG monitoring, but it has not been used in patients with AD. OBJECTIVE: To investigate if ear-EEG is a feasible method for long-term EEG monitoring in patients with AD. METHODS: In this longitudinal, single-group feasibility study, ten patients with mild to moderate AD were recruited. A total of three ear-EEG recordings of up to 48 hours three months apart for six months were planned. RESULTS: All patients managed to wear the ear-EEG for at least 24 hours and at least one full night. A total of 19 ear-EEG recordings were performed (self-reported recording, mean: 37.15 hours (SD: 8.96 hours)). After automatic pre-processing, a mean of 27.37 hours (SD: 7.19 hours) of data with acceptable quality in at least one electrode in each ear was found. Seven out of ten participants experienced mild adverse events. Six of the patients did not complete the study with three patients not wanting to wear the ear-EEG anymore due to adverse events. CONCLUSION: It is feasible and safe to use ear-EEG for long-term EEG monitoring in patients with AD. Minor adjustments to the equipment may improve the comfort for the participants.

Self-applied ear-EEG for sleep monitoring at home.

High quality sleep monitoring is done using EEG electrodes placed on the skin. This has traditionally required assistance by an expert when the equipment needed to mounted. However, this creates a limitation in how cheap and easy it can be to record sleep in the subject's own home. Here we present a data set of 120 home recordings of sleep, in which subjects use self-applied ear-EEG monitoring equipment. We compare this data set to a previously recorded data set with both ear-EEG and polysomnography, which was applied by an expert. Clinical relevance - On all tested metrics, self applied sleep recordings behaved the same as expert applied. This indicates that ear-EEG can reliably be used as a home sleep monitor, even when subjects apply the equipment themselves.

Characterization of Dry-Contact EEG Electrodes and an Empirical Comparison of Ag/AgCl and IrO2 Electrodes.

Dry-contact electrodes are increasingly being used for EEG recordings in both research studies and consumer products. They are more user-friendly and better suited for long-term recordings. However, dry-contact electrodes also bring challenges with respect to the stability and impedance of the electrode-skin interface. We propose a methodology to characterize and compare dry-contact electrodes. The characterization is based on measuring the electrode-skin impedance spectrum, fit a parametric model of the electrode-skin interface to the measured spectrum, and calculate the resulting thermal noise spectrum. Thereby it is possible to relate the noise of an EEG recording to the theoretical noise contribution from the electrode-skin interface. To demonstrate the methodology, we performed an empirical study comparing two types of dry-contact electrodes in an ear-EEG setup. The electrodes were IrO2, previously used for ear-EEG, and a new design based on Ag/AgCl. Here, we related the noise floor of an auditory steady-state response (ASSR) to the thermal noise spectrum of the electrode-skin interface. The study showed similar impedance and EEG recording quality for the two electrode types, and the thermal noise of the electrode-skin interface was below the noise floor of the EEG recordings for both electrode types. Dry-contact EEG is an enabling technology for long-term brain monitoring of patients. This may be relevant for example for monitoring of neurodegenerative diseases, stroke patients, patients with traumatic brain injuries, and psychiatric patients.

Investigation of the Effect of Spatial Filtering for Detecting Auditory Steady-State Responses Recorded from Ear-EEG.

Auditory steady-state responses (ASSRs) enable hearing threshold estimation based on electrophysiological measurements and are widely used in clinical practice. Traditionally, ASSRs are recorded from a few electroencephalography (EEG) electrodes placed on the scalp. Ear-EEG is a method in which the EEG is recorded from electrodes placed within or around the ear and is thus more suitable for use in everyday life. Ear-EEG is typically recorded from multiple electrodes in order to enhance redundancy and robustness, but a pair of electrodes (so-called "best pair") is usually chosen for the further analysis. Spatial filtering uses an optimized weighted combination of the electrodes, and is thus in general a better method for analysis of multichannel EEG. In this study we propose a new spatial filtering method based on solving a constrained optimization problem. Empirical evaluation based on ear-EEG recorded from nine subjects shows that the proposed spatial filtering method provides a significant increase in ASSR SNR as compared to the conventional "best pair" method. Clinical Relevance - ASSR can be estimated from ear-EEG recordings. Integrating ear-EEG into hearing aids would allow hearing aids to characterize hearing loss and thereby adjust the audio processing accordingly.

Chirp-Evoked Auditory Steady-State Response: The Effect of Repetition Rate.

OBJECTIVE: The auditory steady-state response (ASSR) is commonly used in clinical pediatric audiology in order to provide an electrophysiological estimate of hearing threshold, and has the potential to be used in unsupervised mobile EEG applications. Enhancement of the ASSR amplitude through optimization of the stimulation and recording methods shortens the required testing time or reduce the offset between the electrophysiological and behavioral thresholds. Here, we investigate the spatial distribution of the ASSR to broadband chirp stimuli across a wide range of repetition rates on the scalp and in the ears. Moreover, the ASSR amplitude is compared across repetition rates for commonly used electrode configurations. METHODS: ASSR to chirp stimuli with repetition rates from 6-198 Hz was recorded using scalp EEG and high-density ear-EEG. RESULTS: The distributions of the ASSR amplitude and phase were found to be dependent on the chirp repetition rate across the scalp, but independent of repetition rate in the ears. The normal drop in ASSR SNR for high repetition rates seen for click and pure tone stimuli was not found for chirp stimuli. Instead, the ASSR SNRs for chirp stimuli at high repetition rates (95-198 Hz) were found to be comparable to that found at 40 Hz for scalp EEG and even higher than 40 Hz ASSR for ear-EEG. CONCLUSION: Based on the results, use of chirp stimuli with high repetition rates (95-198 Hz) is advantageous for multiple stimulus ASSR recording in both clinical practice and mobile real-life applications.

Sleep Monitoring Using Ear-Centered Setups: Investigating the Influence From Electrode Configurations.

Modern sleep monitoring development is shifting towards the use of unobtrusive sensors combined with algorithms for automatic sleep scoring. Many different combinations of wet and dry electrodes, ear-centered, forehead-mounted or headband-inspired designs have been proposed, alongside an ever growing variety of machine learning algorithms for automatic sleep scoring. OBJECTIVE: Among candidate positions, those in the facial area and around the ears have the benefit of being relatively hairless, and in our view deserve extra attention. In this paper, we seek to determine the limits to sleep monitoring quality within this spatial constraint. METHODS: We compare 13 different, realistic sensor setups derived from the same data set and analysed with the same pipeline. RESULTS: All setups which include both a lateral and an EOG derivation show similar, state-of-the-art performance, with average Cohen's kappa values of at least 0.80. CONCLUSION: If large electrode distances are used, positioning is not critical for achieving large sleep-related signal-to-noise-ratio, and hence accurate sleep scoring. SIGNIFICANCE: We argue that with the current competitive performance of automated staging approaches, there is a need for establishing an improved benchmark beyond current single human rater scoring.

Repeated automatic sleep scoring based on ear-EEG is a valuable alternative to manually scored polysomnography.

While polysomnography (PSG) is the gold standard to quantify sleep, modern technology allows for new alternatives. PSG is obtrusive, affects the sleep it is set out to measure and requires technical assistance for mounting. A number of less obtrusive solutions based on alternative methods have been introduced, but few have been clinically validated. Here we validate one of these solutions, the ear-EEG method, against concurrently recorded PSG in twenty healthy subjects each measured for four nights. Two trained technicians scored the 80 nights of PSG independently, while an automatic algorithm scored the ear-EEG. The sleep stages and eight sleep metrics (Total Sleep Time (TST), Sleep Onset Latency, Sleep Efficiency, Wake After Sleep Onset, REM latency, REM fraction of TST, N2 fraction of TST, and N3 fraction of TST) were used in the further analysis. We found the sleep metrics: Total Sleep Time, Sleep Onset Latency, Sleep Efficiency, Wake After Sleep Onset were estimated with high accuracy and precision between automatic sleep scoring and manual sleep scoring. However, the REM latency and REM fraction of sleep showed high accuracy but low precision. Further, the automatic sleep scoring systematically overestimated the N2 fraction of sleep and slightly underestimated the N3 fraction of sleep. We demonstrate that sleep metrics estimated from automatic sleep scoring based on repeated ear-EEG in some cases are more reliably estimated with repeated nights of automatically scored ear-EEG than with a single night of manually scored PSG. Thus, given the obtrusiveness and cost of PSG, ear-EEG seems to be a useful alternative for sleep staging for the single night recording and an advantageous choice for several nights of sleep monitoring.

Investigation of low dimensional feature spaces for automatic sleep staging.

BACKGROUND: Automatic sleep stage classification depends crucially on the selection of a good set of descriptive features. However, the selection of a feature set with an appropriate low computational cost without compromising classification performance is still a challenge. This study attempts to represent sleep EEG patterns using a minimum number of features, without significant performance loss. METHODS: Three feature selection algorithms were applied to a high dimensional feature space comprising 84 features. These methods were based on a bootstrapping approach guided by Gini ranking and mutual information between the features. The algorithms were tested on three scalp electroencephalography (EEG) and one ear-EEG datasets. The relationship between the information carried by different features was investigated using mutual information and illustrated by a graphical clustering tool. RESULTS: The minimum number of features that can represent the whole feature set without performance loss was found to range between 5 and 11 for different datasets. In ear-EEG, 7 features based on Continuous Wavelet Transform (CWT) resulted in similar performance as the whole set whereas in two scalp EEG datasets, the difference between minimal CWT set and the whole set was statistically significant (0.008 and 0.017 difference in average kappa). Features were divided into groups according to the type of information they carry. The group containing relative power features was identified as the most informative feature group in sleep stage classification, whereas the group containing non-linear features was found to be the least informative. CONCLUSIONS: This study showed that EEG sleep staging can be performed based on a low dimensional feature space without significant decrease in sleep staging performance. This is especially important in the case of wearable devices like ear-EEG where low computational complexity is needed. The division of the feature space into groups of features, and the analysis of the distribution of feature groups for different feature set sizes, is helpful in the selection of an appropriate feature set.

EEGs Vary Less Between Lab and Home Locations Than They Do Between People.

Given the rapid development of light weight EEG devices which we have witnessed the past decade, it is reasonable to ask to which extent neuroscience could now be taken outside the lab. In this study, we have designed an EEG paradigm well suited for deployment "in the wild." The paradigm is tested in repeated recordings on 20 subjects, on eight different occasions (4 in the laboratory, 4 in the subject's own home). By calculating the inter subject, intra subject and inter location variance, we find that the inter location variation for this paradigm is considerably less than the inter subject variation. We believe the paradigm is representative of a large group of other relevant paradigms. This means that given the positive results in this study, we find that if a research paradigm would benefit from being performed in less controlled environments, we expect limited problems in doing so.

Droplet-Based Techniques for Printing of Functional Inks for Flexible Physical Sensors.

Printed electronics (PE) is an emerging technology that uses functional inks to print electrical components and circuits on variety of substrates. This technology has opened up new possibilities to fabricate flexible, bendable, and form-fitting devices at low-cost and fast speed. There are different printing technologies in use, among which droplet-based techniques are of great interest as they provide the possibility of printing computer-controlled design patterns with high resolution, and greater production flexibility. Nanomaterial inks form the heart of this technology, enabling different functionalities. To this end, intensive research has been carried out on formulating inks with conductive, semiconductive, magnetic, piezoresistive, and piezoelectric properties. Here, a detailed landscape view on different droplet-based printing technologies (inkjet, aerosol jet, and electrohydrodynamic jet) is provided, with comprehensive discussion on their working principals. This is followed by a detailed research overview of different functional inks (metal, carbon, polymer, and ceramic). Different sintering methods and common substrates being used in printed electronics are also discussed, followed by an in-depth review of different physical sensors fabricated by droplet-based techniques. Finally, the challenges facing the field are considered and a perspective on possible ways to overcome them is provided.

Ear-EEG for sleep assessment: a comparison with actigraphy and PSG.

PURPOSE: To assess automatic sleep staging of three ear-EEG setups with different electrode configurations and compare performance with concurrent polysomnography and wrist-worn actigraphy recordings. METHODS: Automatic sleep staging was performed for single-ear, single-ear with ipsilateral mastoid, and cross-ear electrode configurations, and for actigraphy data. The polysomnography data were manually scored and used as the gold standard. The automatic sleep staging was tested on 80 full-night recordings from 20 healthy subjects. The scoring performance and sleep metrics were determined for all ear-EEG setups and the actigraphy device. RESULTS: The single-ear, the single-ear with ipsilateral mastoid setup, and the cross-ear setup performed five class sleep staging with kappa values 0.36, 0.63, and 0.72, respectively. For the single-ear with mastoid electrode and the cross-ear setup, the performance of the sleep metrics, in terms of mean absolute error, was better than the sleep metrics estimated from the actigraphy device in the current study, and also better than current state-of-the-art actigraphy studies. CONCLUSION: A statistically significant improvement in both accuracy and kappa was observed from single-ear to single-ear with ipsilateral mastoid, and from single-ear with ipsilateral mastoid to cross-ear configurations for both two and five-sleep stage classification. In terms of sleep metrics, the results were more heterogeneous, but in general, actigraphy and single-ear with ipsilateral mastoid configuration were better than the single-ear configuration; and the cross-ear configuration was consistently better than both the actigraphy device and the single-ear configuration.

Predicting Sleep Classification Performance without Labels.

When generating automatic sleep reports with mobile sleep monitoring devices, it is crucial to have a good grasp of the reliability of the result. In this paper, we feed features derived from the output of a sleep scoring algorithm to a 'regression ensemble' to estimate the quality of the automatic sleep scoring. We compare this estimate to the actual quality, calculated using a manual scoring of a concurrent polysomnography recording. We find that it is generally possible to estimate the quality of a sleep scoring, but with some uncertainty ('root mean squared error' between estimated and true Cohen's kappa is 0.078). We expect that this method could be useful in situations with many scored nights from the same subject, where an overall picture of scoring quality is needed, but where uncertainty on single nights is less of an issue.