A Deep Transfer Learning Approach for Sleep Stage Classification and Sleep Apnea Detection Using Wrist-Worn Consumer Sleep Technologies.

Obstructive sleep apnea (OSA) is a common, underdiagnosed sleep-related breathing disorder with serious health implications Objective - We propose a deep transfer learning approach for sleep stage classification and sleep apnea (SA) detection using wrist-worn consumer sleep technologies (CST). Methods - Our model is based on a deep convolutional neural network (DNN) utilizing accelerometers and photo-plethysmography signals from nocturnal recordings. The DNN was trained and tested on internal datasets that include raw data from clinical and wrist-worn devices; external validation was performed on a hold-out test dataset containing raw data from a wrist-worn CST. Results - Training on clinical data improves performance significantly, and feature enrichment through a sleep stage stream gives only minor improvements. Raw data input outperforms feature-based input in CST datasets. The system generalizes well but performs slightly worse on wearable device data compared to clinical data. However, it excels in detecting events during REM sleep and is associated with arousal and oxygen desaturation. We found; cases that were significantly underestimated were characterized by fewer of such event associations. Conclusion - This study showcases the potential of using CSTs as alternate screening solution for undiagnosed cases of OSA. Significance - This work is significant for its development of a deep transfer learning approach using wrist-worn consumer sleep technologies, offering comprehensive validation for data utilization, and learning techniques, ultimately improving sleep apnea detection across diverse devices.

A Flexible Deep Learning Architecture for Temporal Sleep Stage Classification Using Accelerometry and Photoplethysmography.

Wrist-worn consumer sleep technologies (CST) that contain accelerometers (ACC) and photoplethysmography (PPG) are increasingly common and hold great potential to function as out-of-clinic (OOC) sleep monitoring systems. However, very few validation studies exist because raw data from CSTs are rarely made accessible for external use. We present a deep neural network (DNN) with a strong temporal core, inspired by U-Net, that can process multivariate time series inputs with different dimensionality to predict sleep stages (wake, light-, deep-, and REM sleep) using ACC and PPG signals from nocturnal recordings. The DNN was trained and tested on 3 internal datasets, comprising raw data both from clinical and wrist-worn devices from 301 recordings (PSG-PPG: 266, Wrist-worn PPG: 35). External validation was performed on a hold-out test dataset containing 35 recordings comprising only raw data from a wrist-worn CST. An accuracy = 0.71 ± 0.09, 0.76 ± 0.07, 0.73 ± 0.06, and κ = 0.58 ± 0.13, 0.64 ± 0.09, 0.59 ± 0.09 was achieved on the internal test sets. Our experiments show that spectral preprocessing yields superior performance when compared to surrogate-, feature-, raw data-based preparation. Combining both modalities produce the overall best performance, although PPG proved to be the most impactful and was the only modality capable of detecting REM sleep well. Including ACC improved model precision to wake and sleep metric estimation. Increasing input segment size improved performance consistently; the best performance was achieved using 1024 epochs (∼8.5 hrs.). An accuracy = 0.69 ± 0.13 and κ = 0.58 ± 0.18 was achieved on the hold-out test dataset, proving the generalizability and robustness of our approach to raw data collected with a wrist-worn CST.

The sonar beam of Macrophyllum macrophyllum implies ecological adaptation under phylogenetic constraint.

All animals are adapted to their ecology within the bounds of their evolutionary heritage. Echolocating bats clearly show such adaptations and boundaries through their biosonar call design. Adaptations include not only the overall time-frequency structure, but also the shape of the emitted echolocation beam. Macrophyllum macrophyllum is unique within the phyllostomid family, being the only species to predominantly hunt for insects in the open, on or above water, and as such it presents an interesting case for comparing the impact of phylogeny and ecology as it originates from a family of low-intensity, high-directionality gleaning bats, but occupies a niche dominated by very loud and substantially less-directional bats. Here, we examined the sonar beam pattern of M. macrophyllum in the field and in a flight room and compared it to closely related species with very different feeding ecology and to that of the niche-sharing but distantly related Myotis daubentonii Our results show that M. macrophyllum uses higher source levels and emits less-directional calls than other phyllostomids. In the field, its call directionality is comparable to M. daubentonii, but in the flight room, M. macrophyllum is substantially more directional. Hence our results indicate that ecology influences the emitted call, pushing the bats to emit a louder and broader beam than other phyllostomids, but that phylogeny does limit the emitted intensity and flexibility of the overall beam pattern.

Robust, ECG-based detection of Sleep-disordered breathing in large population-based cohorts.

STUDY OBJECTIVES: Up to 5% of adults in Western countries have undiagnosed sleep-disordered breathing (SDB). Studies have shown that electrocardiogram (ECG)-based algorithms can identify SDB and may provide alternative screening. Most studies, however, have limited generalizability as they have been conducted using the apnea-ECG database, a small sample database that lacks complex SDB cases. METHODS: Here, we developed a fully automatic, data-driven algorithm that classifies apnea and hypopnea events based on the ECG using almost 10 000 polysomnographic sleep recordings from two large population-based samples, the Sleep Heart Health Study (SHHS) and the Multi-Ethnic Study of Atherosclerosis (MESA), which contain subjects with a broad range of sleep and cardiovascular diseases (CVDs) to ensure heterogeneity. RESULTS: Performances on average were sensitivity(Se)=68.7%, precision (Pr)=69.1%, score (F1)=66.6% per subject, and accuracy of correctly classifying apnea-hypopnea index (AHI) severity score was Acc=84.9%. Target AHI and predicted AHI were highly correlated (R2 = 0.828) across subjects, indicating validity in predicting SDB severity. Our algorithm proved to be statistically robust between databases, between different periodic leg movement index (PLMI) severity groups, and for subjects with previous CVD incidents. Further, our algorithm achieved the state-of-the-art performance of Se=87.8%, Sp=91.1%, Acc=89.9% using independent comparisons and Se=90.7%, Sp=95.7%, Acc=93.8% using a transfer learning comparison on the apnea-ECG database. CONCLUSIONS: Our robust and automatic algorithm constitutes a minimally intrusive and inexpensive screening system for the detection of SDB events using the ECG to alleviate the current problems and costs associated with diagnosing SDB cases and to provide a system capable of identifying undiagnosed SDB cases.

Neural network analysis of sleep stages enables efficient diagnosis of narcolepsy.

Analysis of sleep for the diagnosis of sleep disorders such as Type-1 Narcolepsy (T1N) currently requires visual inspection of polysomnography records by trained scoring technicians. Here, we used neural networks in approximately 3,000 normal and abnormal sleep recordings to automate sleep stage scoring, producing a hypnodensity graph-a probability distribution conveying more information than classical hypnograms. Accuracy of sleep stage scoring was validated in 70 subjects assessed by six scorers. The best model performed better than any individual scorer (87% versus consensus). It also reliably scores sleep down to 5 s instead of 30 s scoring epochs. A T1N marker based on unusual sleep stage overlaps achieved a specificity of 96% and a sensitivity of 91%, validated in independent datasets. Addition of HLA-DQB1*06:02 typing increased specificity to 99%. Our method can reduce time spent in sleep clinics and automates T1N diagnosis. It also opens the possibility of diagnosing T1N using home sleep studies.

Automatic, electrocardiographic-based detection of autonomic arousals and their association with cortical arousals, leg movements, and respiratory events in sleep.

Study Objectives: The current definition of sleep arousals neglects to address the diversity of arousals and their systemic cohesion. Autonomic arousals (AA) are autonomic activations often associated with cortical arousals (CA), but they may also occur in relation to a respiratory event, a leg movement event or spontaneously, without any other physiological associations. AA should be acknowledged as essential events to understand and explore the systemic implications of arousals. Methods: We developed an automatic AA detection algorithm based on intelligent feature selection and advanced machine learning using the electrocardiogram. The model was trained and tested with respect to CA systematically scored in 258 (181 training size/77 test size) polysomnographic recordings from the Wisconsin Sleep Cohort. Results: A precision value of 0.72 and a sensitivity of 0.63 were achieved when evaluated with respect to CA. Further analysis indicated that 81% of the non-CA-associated AAs were associated with leg movement (38%) or respiratory (43%) events. Conclusions: The presented algorithm shows good performance when considering that more than 80% of the false positives (FP) found by the detection algorithm appeared in relation to either leg movement or respiratory events. This indicates that most FP constitute autonomic activations that are indistinguishable from those with cortical cohesion. The proposed algorithm provides an automatic system trained in a clinical environment, which can be utilized to analyze the systemic and clinical impacts of arousals.

Dynamics of the echolocation beam during prey pursuit in aerial hawking bats.

In the evolutionary arms race between prey and predator, measures and countermeasures continuously evolve to increase survival on both sides. Bats and moths are prime examples. When exposed to intense ultrasound, eared moths perform dramatic escape behaviors. Vespertilionid and rhinolophid bats broaden their echolocation beam in the final stage of pursuit, presumably as a countermeasure to keep evading moths within their "acoustic field of view." In this study, we investigated if dynamic beam broadening is a general property of echolocation when catching moving prey. We recorded three species of emballonurid bats, Saccopteryx bilineata, Saccopteryx leptura, and Rhynchonycteris naso, catching airborne insects in the field. The study shows that S. bilineata and S. leptura maintain a constant beam shape during the entire prey pursuit, whereas R. naso broadens the beam by lowering the peak call frequency from 100 kHz during search and approach to 67 kHz in the buzz. Surprisingly, both Saccopteryx bats emit calls with very high energy throughout the pursuit, up to 60 times more than R. naso and Myotis daubentonii (a similar sized vespertilionid), providing them with as much, or more, peripheral "vision" than the vespertilionids, but ensonifying objects far ahead suggesting more clutter. Thus, beam broadening is not a fundamental property of the echolocation system. However, based on the results, we hypothesize that increased peripheral detection is crucial to all aerial hawking bats in the final stages of prey pursuit and speculate that beam broadening is a feature characterizing more advanced echolocation.

Effect of hyperosmotic conditions on the expression of the betaine-GABA-transporter (BGT-1) in cultured mouse astrocytes.

The adaptation of cells to hyperosmotic conditions involves accumulation of organic osmolytes to achieve osmotic equilibrium and maintenance of cell volume. The Na+ and Cl(-)-coupled betaine/GABA transporter, designated BGT-1, is responsible for the cellular accumulation of betaine and has been proposed to play a role in osmoregulation in the brain. BGT-1 is also called GAT2 (GABA transporter 2) when referring to the mouse transporter homologue. Using Western Blotting the expression of the mouse GAT2 protein was investigated in astrocyte primary cultures exposed to a growth medium made hyperosmotic (353+/-2.5 mosmol/kg) by adding sodium chloride. A polyclonal anti-BGT-1 antibody revealed the presence of two characteristic bands at 69 and 138 kDa. When astrocytes were grown for 24 h under hyperosmotic conditions GAT2 protein was up-regulated 2-4-fold compared to the level of the isotonic control. Furthermore, the expected dimer of GAT2 was also up-regulated after 24 h under the hyperosmotic conditions. The [3H]GABA uptake was examined in the hyperosmotic treated astrocytes, and characterized using different selective GABA transport inhibitors. The up-regulation of GAT2 protein was not affecting total GABA uptake but the hyperosmotic condition did change total GABA uptake possibly involving GAT1. Immunocytochemical studies revealed cell membrane localization of GAT2 throughout astroglial processes. Taken together, these results indicate that astroglial GAT2 expression and function may be regulated by hyperosmolarity in cultured mouse astrocytes, suggesting a role of GAT2 in osmoregulation in neural cells.