Abstract Motor memory retention is impaired in Parkinson’s disease (PD), affecting long-term rehabilitation outcomes. It appears that NREM sleep could be beneficial for consolidation processes in PD, and could be leveraged with non-invasive sleep interventions. This study examined the effect of auditory targeted memory reactivation (TMR) during NREM sleep on the retention of a motor sequence learning finger tapping task in 20 PD and 20 healthy older adults (HOA). TMR was applied during a 2- hour nap and its effect on motor retention was tested post-nap, after 24-hours and with a dual-task. The impact of TMR on sleep electrophysiology was also evaluated. Results showed no effect of TMR on motor retention or dual-tasking, with no difference between the groups. However, the TMR intervention did increase slow-wave density and decreased spindle density in both groups, and slow-wave amplitude during the presentation of the auditory cues was positively associated with performance in HOA. In conclusion, TMR applied during a 2-hour nap did not enhance motor retention, but the changes in sleep physiological features could be linked to a possible underlying effect on memory processing that warrants further investigation.

Motor memory consolidation is a process by which newly acquired skills become stable over time in the absence of practice. Sleep facilitates consolidation, yet it remains unknown whether sleep-dependent consolidation is intact in people with Parkinson's disease. Here, we investigated whether a post-learning nap-as compared to wakefulness-improves motor memory consolidation in Parkinson. Thirty-two people with Parkinson's disease and 32 healthy older adults learnt a finger-tapping sequence task before a nap or wake intervention (pseudo-randomised assignment). Consolidation was measured as the change in performance between pre- and post-intervention and at 24-h retention. Automaticity was measured with dual-task cost, assessed at post-intervention and at post-night. Sleep architecture and electrophysiological markers of plasticity were extracted from the post-learning nap, to assess their association with performance change. The behavioural results suggest similar consolidation effects after sleep and wakefulness in both populations. Moreover, there was no effect of napping automaticity. Results also suggest positive associations between performance improvement and slow wave amplitude and slope in people with Parkinson's disease, and inconclusive associations between cross-frequency coupling and performance change in both populations. To conclude, napping did not have a beneficial effect on the consolidation of a finger-tapping task as compared to wakefulness in either people with Parkinson's disease or healthy older adults. Finally, in patients, sleep markers of plasticity were associated with performance improvements, implying that equivalent memory consolidation may be differently associated to sleep-related processes in Parkinson's and healthy ageing. Trial Registration: NCT04144283.

BACKGROUND:Sleep apnea is a common disorder characterized by recurrent episodes of upper airway obstruction or impaired respiratory drive, leading to disrupted sleep and significant cardiopulmonary consequences. While anatomical and neuromuscular factors are well-established contributors to obstructive sleep apnea (OSA), and central sleep apnea (CSA) is often linked to cardiac or neurological conditions, the impact of endocrine disorders, particularly hypothyroidism, is frequently overlooked. CLINICAL PRESENTATION:We describe a case of severe sleep apnea that exhibited persistent sleep apnea (including obstructive, but also central and mixed events) under continuous positive airway pressure (CPAP) therapy. Clinical and biochemical findings confirmed profound hypothyroidism with myxedema. Thyroid hormone replacement therapy led to substantial clinical improvement, including weight loss, normalization of thyroid function, and a marked reduction in residual AHI after eight months. CONCLUSION:This case highlights the need for increased awareness of hypothyroidism as a potential and reversible cause of treatment-resistant sleep apnea (TRSA). Thyroid hormone replacement therapy can lead to significant improvement, emphasizing the need for routine thyroid function screening in patients with sleep apnea.

The recent emergence of wearable devices will enable large scale remote brain monitoring. This study investigated whether multimodal wearable sleep recordings could help screening for Alzheimer’s disease (AD). Measurements were acquired simultaneously from polysomnography and a wearable device, measuring electroencephalography (EEG) and accelerometry (ACM) in 67 elderly without cognitive symptoms and 35 AD patients. Sleep staging was performed using an AI model (SeqSleepNet), followed by feature extraction from hypnograms and physiological signals. Using these features, a multi-layer perceptron was trained for AD detection, with elastic net identifying key features. The wearable AD detection model achieved an accuracy of 0.90 (0.76 for prodromal AD). Single-channel EEG and ACM physiological features captured sufficient information for AD detection and outperformed the hypnogram features, highlighting these physiological features as promising discriminative markers for AD. We conclude that wearable sleep monitoring augmented by AI shows promise towards non-invasive screening for AD in the older population.

Wearable electroencephalography devices emerge as a cost-effective and ergonomic alternative to gold-standard polysomnography, paving the way for better health monitoring and sleep disorder screening. Machine learning allows to automate sleep stage classification, but trust and reliability issues have hampered its adoption in clinical applications. Estimating uncertainty is a crucial factor in enhancing reliability by identifying regions of heightened and diminished confidence. In this study, we used an uncertainty-centred machine learning pipeline, U-PASS, to automate sleep staging in a challenging real-world dataset of single-channel electroencephalography and accelerometry collected with a wearable device from an elderly population. We were able to effectively limit the uncertainty of our machine learning model and to reliably inform clinical experts of which predictions were uncertain to improve the machine learning model's reliability. This increased the five-stage sleep-scoring accuracy of a state-of-the-art machine learning model from 63.9% to 71.2% on our dataset. Remarkably, the machine learning approach outperformed the human expert in interpreting these wearable data. Manual review by sleep specialists, without specific training for sleep staging on wearable electroencephalography, proved ineffective. The clinical utility of this automated remote monitoring system was also demonstrated, establishing a strong correlation between the predicted sleep parameters and the reference polysomnography parameters, and reproducing known correlations with the apnea-hypopnea index. In essence, this work presents a promising avenue to revolutionize remote patient care through the power of machine learning by the use of an automated data-processing pipeline enhanced with uncertainty estimation.

Abstract Wearable electroencephalography (EEG) devices emerge as a cost-effective and ergonomic alternative to gold standard polysomnography, paving the way for better health monitoring and sleep disorder screening. Machine learning allows to automate sleep stage classification, but trust and reliability issues have hampered its adoption in clinical applications. Estimating uncertainty is a crucial factor in enhancing reliability by identifying regions of heightened and diminished confidence. In this study, we investigated the utility of an uncertainty-centered machine learning pipeline, U-PASS, on sleep staging in a challenging real-world dataset of single-channel EEG and accelerometry collected with a wearable device from elderly sleep apnea patients. We demonstrated that U-PASS effectively limited the uncertainty at training time and communicated uncertainty to clinical experts at deployment time to improve the machine learning model's reliability. This effectively increased the 5-stage sleep scoring accuracy of a state-of-the-art machine learning model from 63.9% to 71.2% on our dataset. Remarkably, the machine learning approach outperformed the human expert in interpreting these wearable data. Manual review by sleep specialists, without specific training for sleep staging on wearable EEG, proved ineffective. The diagnostic capabilities of this automated remote monitoring system were also demonstrated, establishing a strong correlation between the predicted sleep features and the most important clinical marker for sleep apnea. In essence, an automated data processing pipeline enhanced with uncertainty estimation presents a promising avenue to unlock the full potential of machine learning in revolutionizing remote patient care.

Sleep disturbances are common in people with Alzheimer’s disease (AD), and a reduction in slow-wave activity is the most striking underlying change. Acoustic stimulation has emerged as a promising approach to enhance slow-wave activity in healthy adults and people with amnestic mild cognitive impairment. In this phase 1 study we investigated, for the first time, the feasibility of acoustic stimulation in AD and piloted the effect on slow-wave sleep (SWS). Eleven adults with mild to moderate AD first wore the DREEM 2 headband for 2 nights to establish a baseline registration. Using machine learning, the DREEM 2 headband automatically scores sleep stages in real time. Subsequently, the participants wore the headband for 14 consecutive “stimulation nights” at home. During these nights, the device applied phase-locked acoustic stimulation of 40-dB pink noise delivered over 2 bone-conductance transducers targeted to the up-phase of the delta wave or SHAM, if it detected SWS in sufficiently high-quality data. Results of the DREEM 2 headband algorithm show a significant average increase in SWS (minutes) [t(3.17) = 33.57, P = .019] between the beginning and end of the intervention, almost twice as much time was spent in SWS. Consensus scoring of electroencephalography data confirmed this trend of more time spent in SWS [t(2.4) = 26.07, P = .053]. Our phase 1 study provided the first evidence that targeted acoustic stimuli is feasible and could increase SWS in AD significantly. Future studies should further test and optimize the effect of stimulation on SWS in AD in a large randomized controlled trial. Van den Bulcke L, Peeters A-M, Heremans E, et al. Acoustic stimulation as a promising technique to enhance slow-wave sleep in Alzheimer’s disease: results of a pilot study. J Clin Sleep Med. 2023;19(12):2107–2112.

Objective. The recent breakthrough of wearable sleep monitoring devices has resulted in large amounts of sleep data. However, as limited labels are available, interpreting these data requires automated sleep stage classification methods with a small need for labeled training data. Transfer learning and domain adaptation offer possible solutions by enabling models to learn on a source dataset and adapt to a target dataset. Approach. In this paper, we investigate adversarial domain adaptation applied to real use cases with wearable sleep datasets acquired from diseased patient populations. Different practical aspects of the adversarial domain adaptation framework are examined, including the added value of (pseudo-)labels from the target dataset and the influence of domain mismatch between the source and target data. The method is also implemented for personalization to specific patients. Main results. The results show that adversarial domain adaptation is effective in the application of sleep staging on wearable data. When compared to a model applied on a target dataset without any adaptation, the domain adaptation method in its simplest form achieves relative gains of 7%–27% in accuracy. The performance in the target domain is further boosted by adding pseudo-labels and real target domain labels when available, and by choosing an appropriate source dataset. Furthermore, unsupervised adversarial domain adaptation can also personalize a model, improving the performance by 1%–2% compared to a non-personalized model. Significance. In conclusion, adversarial domain adaptation provides a flexible framework for semi-supervised and unsupervised transfer learning. This is particularly useful in sleep staging and other wearable electroencephalography applications. (Clinical trial registration number: S64190.)

Summary The American Academy of Sleep Medicine (AASM) uses similar apnea–hypopnea index (AHI) cut‐off values to diagnose and define severity of sleep apnea independent of the technique used: in‐hospital polysomnography (PSG) or type 3 portable monitoring (PM). Taking into account that PM theoretically might underestimate the AHI, we explored whether a lower cut‐off would be more appropriate. We performed mathematical re‐calculations on the diagnostic PSG‐AHI (scored using AASM 1999 rules) of 865 consecutive patients with an AHI of ≥20 events/h who started continuous positive airway pressure (CPAP). For a PSG‐AHI of ≥15 events/h re‐scored using AASM 2012 rules (PSG‐AHI AASM2012 ), a PM‐respiratory event index (REI) AASM2012 cut‐off point of ≥15 events/h resulted in a post‐test probability of 100% of having the disease, but with negative tests in 57.1%. A PM‐REI AASM2012 cut‐off of 8 events/h, still resulted in a positive post‐test probability of 100% but with negative tests in only 34.3%. Combination of the cut‐off values with clinical estimation of being ‘at high risk’ based on Epworth Sleepiness Scale (ESS) and Berlin Questionnaire scores only resulted in a small reduction in the percentage of negative tests (respectively 52.7% and 32.7%). After 6 months, CPAP adherence was not lower using the PM‐REI AASM 2012 cut‐off ≥8 events/h in comparison to ≥15 events/h (median 5.7 vs. 5.8 h/night, p = 0.368) and the reduction in ESS was similar too (median –4 and –5 points, p = 0.083). Consequently, using a lower PM‐REI AASM2012 cut‐off could result in cost savings because of less negative studies and lesser need for a confirmatory PSG or a performance of a CPAP trial.

Objective: With the rapid rise of wearable sleep monitoring devices with non-conventional electrode configurations, there is a need for automated algorithms that can perform sleep staging on configurations with small amounts of labeled data. Transfer learning has the ability to adapt neural network weights from a source modality (e.g. standard electrode configuration) to a new target modality (e.g. non-conventional electrode configuration). Methods: We propose feature matching, a new transfer learning strategy as an alternative to the commonly used finetuning approach. This method consists of training a model with larger amounts of data from the source modality and few paired samples of source and target modality. For those paired samples, the model extracts features of the target modality, matching these to the features from the corresponding samples of the source modality. Results: We compare feature matching to finetuning for three different target domains, with two different neural network architectures, and with varying amounts of training data. Particularly on small cohorts (i.e. 2 - 5 labeled recordings in the non-conventional recording setting), feature matching systematically outperforms finetuning with mean relative differences in accuracy ranging from 0.4% to 4.7% for the different scenarios and datasets. Conclusion: Our findings suggest that feature matching outperforms finetuning as a transfer learning approach, especially in very low data regimes. Significance: As such, we conclude that feature matching is a promising new method for wearable sleep staging with novel devices.

Objectives: Sleep time information is essential for monitoring of obstructive sleep apnea (OSA), as the severity assessment depends on the number of breathing disturbances per hour of sleep. However, clinical procedures for sleep monitoring rely on numerous uncomfortable sensors, which could affect sleeping patterns. Therefore, an automated method to identify sleep intervals from unobtrusive data is required. However, most unobtrusive sensors suffer from data loss and sensitivity to movement artifacts. Thus, current sleep detection methods are inadequate, as these require long intervals of good quality. Moreover, sleep monitoring of OSA patients is often less reliable due to heart rate disturbances, movement and sleep fragmentation. The primary aim was to develop a sleep-wake classifier for sleep time estimation of suspected OSA patients, based on single short-term segments of their cardiac and respiratory signals. The secondary aim was to define metrics to detect OSA patients directly from their predicted sleep-wake pattern and prioritize them for clinical diagnosis.Methods: This study used a dataset of 183 suspected OSA patients, of which 36 test subjects. First, a convolutional neural network was designed for sleep-wake classification based on healthier patients (AHI < 10). It employed single 30 s epochs of electrocardiograms and respiratory inductance plethysmograms. Sleep information and Total Sleep Time (TST) was derived for all patients using the short-term segments. Next, OSA patients were detected based on the average confidence of sleep predictions and the percentage of sleep-wake transitions in the predicted sleep architecture.Results: Sleep-wake classification on healthy, mild and moderate patients resulted in moderate κ scores of 0.51, 0.49, and 0.48, respectively. However, TST estimates decreased in accuracy with increasing AHI. Nevertheless, severe patients were detected with a sensitivity of 78% and specificity of 89%, and prioritized for clinical diagnosis. As such, their inaccurate TST estimate becomes irrelevant. Excluding detected OSA patients resulted in an overall estimated TST with a mean bias error of 21.9 (± 55.7) min and Pearson correlation of 0.74 to the reference.Conclusion: The presented framework offered a realistic tool for unobtrusive sleep monitoring of suspected OSA patients. Moreover, it enabled fast prioritization of severe patients for clinical diagnosis.

Respiratory sinus arrhythmia (RSA) is a form of cardiorespiratory coupling. It is observed as changes in the heart rate in synchrony with the respiration. RSA has been hypothesized to be due to a combination of linear and nonlinear effects. The quantification of the latter, in turn, has been suggested as a biomarker to improve the assessment of several conditions and diseases. In this study, a framework to quantify RSA using support vector machines is presented. The methods are based on multivariate autoregressive models, in which the present samples of the heart rate variability are predicted as combinations of past samples of the respiration. The selection and tuning of a kernel in these models allows to solve the regression problem taking into account only the linear components, or both the linear and the nonlinear ones. The methods are tested in simulated data as well as in a dataset of polysomnographic studies taken from 110 obstructive sleep apnea patients. In the simulation, the methods were able to capture the nonlinear components when a weak cardiorespiratory coupling occurs. When the coupling increases, the nonlinear part of the coupling is not detected and the interaction is found to be of linear nature. The trends observed in the application in real data show that, in the studied dataset, the proposed methods captured a more prominent linear interaction than the nonlinear one.

Transfer entropy (TE) has been used to identify and quantify interactions between physiological systems. Different methods exist to estimate TE, but there is no consensus about which one performs best in specific applications. In this study, five methods (linear, k-nearest neighbors, fixed-binning with ranking, kernel density estimation and adaptive partitioning) were compared. The comparison was made on three simulation models (linear, nonlinear and linear + nonlinear dynamics). From the simulations, it was found that the best method to quantify the different interactions was adaptive partitioning. This method was then applied on data from a polysomnography study, specifically on the ECG and the respiratory signals (nasal airflow and respiratory effort around the thorax). The hypothesis that the linear and nonlinear components of cardio-respiratory interactions during light and deep sleep change with the sleep stage, was tested. Significant differences, after performing surrogate analysis, indicate an increased TE during deep sleep. However, these differences were found to be dependent on the type of respiratory signal and sampling frequency. These results highlight the importance of selecting the appropriate signals, estimation method and surrogate analysis for the study of linear and nonlinear cardio-respiratory interactions.

Obstructive sleep apnea is often associated with cardiovascular diseases (CVD). Early CVD detection would enhance patient selection for diagnosis and treatment prioritization, to avert development of aggravating CVD. Therefore, the aim of this study is to find markers of CVD risk factors in the pulse photoplethysmography signal, as this enables wearable assessment. To avoid the influence of apneic events on the PPG signal and the requirement to retain the correct sensor positioning for a full night, a method based on wakefulness was investigated. From the PPG, the wake period in the evening before falling asleep and the wake period after waking up in the morning were extracted. A set of 148 features characterized the PPG waveform, using window sizes of 5s to 85s in steps of 5s. A stratified 10-fold cross validation was repeated 100 times for feature selection and CVD classification of 78 subjects. The mean diastolic width at 10% of pulse amplitude (mean DT 10%) was overall the most distinctive feature for CVD risk detection as it showed a significant decrease for CVD patients. Pre-sleep pulse width features extracted over 45s resulted in k = 0.46, a sensitivity of 72.1% and specificity of 74.3%. Overall, mean DT 10% contained CVD risk information, but the result requires further validation on larger datasets and wearable sensors.

Aim: Sleep apnea is often associated with different cardiovascular diseases (CVD). The aim of this study is to find markers of CVD risk factors in the pulse photoplethysmography (PPG) signal as this enables wearable assessment. To avoid the influence of apneic events on the PPG signal and the requirement to retain the correct sensor positioning for a full night, a method based on wakefulness was investigated. Methods: The dataset comprised finger PPG recordings from polysomnography and information on hypertension, hyperlipidemia and diabetes of 78 patients with suspected sleep apnea. Patients with absence of risk factors for CVD were grouped as Class 1, with one as Class 2 and Class 3 otherwise. From the PPG, the wake period in the evening before falling asleep and the wake period after waking up in the morning were extracted. A set of 148 features derived time and frequency information and characterized the PPG waveform. Feature extraction was performed in non-overlapping windows of 5s. Features with a low correlation to age and BMI were ranked by the ‘Minimum Redundancy Maximum Relevance’ algorithm. The top three features were applied in a 5fold cross validation using Naïve Bayes classification. Feature extraction and classification was done separately for the evening and morning wake period. Results and Conclusions: The selected features for the evening wake period were the mean diastolic width at 10% of the pulse amplitude, the standard deviation (SD) of pulse slope transit time and SD of the pulse slope. The classification reached a Kappa score (κ) of 0.47 (Figure 1). The classification with morning period features resulted in a lower κ of 0.32. The evening-based CVD risk prediction could aid to prioritize patients for sleep apnea diagnosis and treatment, in order to avert development of aggravating CVD. Investigation of longer feature windows and improved feature selection could boost CVD risk classification.

Background.Respiratory sinus arrhythmia (RSA) is a form of cardiorespiratory coupling. Its quantification has been suggested as a biomarker to diagnose different diseases. Two state-of-the-art methods, based on subspace projections and entropy, are used to estimate the RSA strength and are evaluated in this paper. Their computation requires the selection of a model order, and their performance is strongly related to the temporal and spectral characteristics of the cardiorespiratory signals.Objective.To evaluate the robustness of the RSA estimates to the selection of model order, delays, changes of phase and irregular heartbeats as well as to give recommendations for their interpretation on each case.Approach.Simulations were used to evaluate the model order selection when calculating the RSA estimates introduced before, as well as three different scenarios that can occur in signals acquired in non-controlled environments and/or from patient populations: the presence of irregular heartbeats; the occurrence of delays between heart rate variability (HRV) and respiratory signals; and the changes over time of the phase between HRV and respiratory signals.Main results.It was found that using a single model order for all the calculations suffices to characterize RSA correctly. In addition, the RSA estimation in signals containing more than 5 irregular heartbeats in a period of 5 min might be misleading. Regarding the delays between HRV and respiratory signals, both estimates are robust. For the last scenario, the two approaches tolerate phase changes up to 54°, as long as this lasts less than one fifth of the recording duration.Significance.Guidelines are given to compute the RSA estimates in non-controlled environments and patient populations.

Obstructive sleep apnea (OSA) patients would strongly benefit from comfortable home diagnosis, during which detection of wakefulness is essential. Therefore, capacitively-coupled electrocardiogram (ccECG) and bioimpedance (ccBioZ) sensors were used to record the sleep of suspected OSA patients, in parallel with polysomnography (PSG). The three objectives were quality assessment of the unobtrusive signals during sleep, prediction of sleep–wake using ccECG and ccBioZ, and detection of high-risk OSA patients. First, signal quality indicators (SQIs) determined the data coverage of ccECG and ccBioZ. Then, a multimodal convolutional neural network (CNN) for sleep–wake prediction was tested on these preprocessed ccECG and ccBioZ data. Finally, two indices derived from this prediction detected patients at risk. The data included 187 PSG recordings of suspected OSA patients, 36 (dataset “Test”) of which were recorded simultaneously with PSG, ccECG, and ccBioZ. As a result, two improvements were made compared to prior studies. First, the ccBioZ signal coverage increased significantly due to adaptation of the acquisition system. Secondly, the utility of the sleep–wake classifier increased as it became a unimodal network only requiring respiratory input. This was achieved by using data augmentation during training. Sleep–wake prediction on “Test” using PSG respiration resulted in a Cohen’s kappa (κ) of 0.39 and using ccBioZ in κ = 0.23. The OSA risk model identified severe OSA patients with a κ of 0.61 for PSG respiration and κ of 0.39 using ccBioZ (accuracy of 80.6% and 69.4%, respectively). This study is one of the first to perform sleep–wake staging on capacitively-coupled respiratory signals in suspected OSA patients and to detect high risk OSA patients based on ccBioZ. The technology and the proposed framework could be applied in multi-night follow-up of OSA patients.