Study objectives: The wake-sleep transition zone represents a poorly defined borderland, containing, for example, microsleep episodes (MSEs), which are of potential relevance for diagnosis and may have consequences while driving. Yet, the scoring guidelines of the American Academy of Sleep Medicine (AASM) completely neglect it. We aimed to explore the borderland between wakefulness and sleep by developing the Bern continuous and high-resolution wake-sleep (BERN) criteria for visual scoring, focusing on MSEs visible in the electroencephalography (EEG), as opposed to purely behavior- or performance-defined MSEs.Methods: Maintenance of Wakefulness Test (MWT) trials of 76 randomly selected patients were retrospectively scored according to both the AASM and the newly developed BERN scoring criteria. The visual scoring was compared with spectral analysis of the EEG. The quantitative EEG analysis enabled a reliable objectification of the visually scored MSEs. For less distinct episodes within the borderland, either ambiguous or no quantitative patterns were found.Results: As expected, the latency to the first MSE was significantly shorter in comparison to the sleep latency, defined according to the AASM criteria. In certain cases, a large difference between the two latencies was observed and a substantial number of MSEs occurred between the first MSE and sleep. Series of MSEs were more frequent in patients with shorter sleep latencies, while isolated MSEs were more frequent in patients who did not reach sleep.Conclusion: The BERN criteria extend the AASM criteria and represent a valuable tool for in-depth analysis of the wake-sleep transition zone, particularly important in the MWT.

Study Objectives: Microsleep episodes (MSEs) are brief episodes of sleep, mostly defined to be shorter than 15 s. In the electroencephalogram (EEG), MSEs are mainly characterized by a slowing in frequency. The identification of early signs of sleepiness and sleep (e.g. MSEs) is of considerable clinical and practical relevance. Under laboratory conditions, the maintenance of wakefulness test (MWT) is often used for assessing vigilance.Methods: We analyzed MWT recordings of 76 patients referred to the Sleep-Wake-Epilepsy-Center. MSEs were scored by experts defined by the occurrence of theta dominance on ≥1 occipital derivation lasting 1–15 s, whereas the eyes were at least 80% closed. We calculated spectrograms using an autoregressive model of order 16 of 1 s epochs moved in 200 ms steps in order to visualize oscillatory activity and derived seven features per derivation: power in delta, theta, alpha and beta bands, ratio theta/(alpha + beta), quantified eye movements, and median frequency. Three algorithms were used for MSE classification: support vector machine (SVM), random forest (RF), and an artificial neural network (long short-term memory [LSTM] network). Data of 53 patients were used for the training of the classifiers, and 23 for testing.Results: MSEs were identified with a high performance (sensitivity, specificity, precision, accuracy, and Cohen’s kappa coefficient). Training revealed that delta power and the ratio theta/(alpha + beta) were most relevant features for the RF classifier and eye movements for the LSTM network.Conclusions: The automatic detection of MSEs was successful for our EEG-based definition of MSEs, with good performance of all algorithms applied.

Study Objectives: Microsleep episodes (MSEs) are short fragments of sleep (1–15 s) that can cause dangerous situations with potentially fatal outcomes. In the diagnostic sleep-wake and fitness-to-drive assessment, accurate and early identification of sleepiness is essential. However, in the absence of a standardised definition and a time-efficient scoring method of MSEs, these short fragments are not assessed in clinical routine. Based on data of moderately sleepy patients, we recently developed the Bern continuous and high-resolution wake-sleep (BERN) criteria for visual scoring of MSEs and corresponding machine learning algorithms for automatic MSE detection, both mainly based on the electroencephalogram (EEG). The present study aimed to investigate the relationship between automatically detected MSEs and driving performance in a driving simulator, recorded in parallel with EEG, and to assess algorithm performance for MSE detection in severely sleepy participants. Methods: Maintenance of wakefulness test (MWT) and driving simulator recordings of 18 healthy participants, before and after a full night of sleep deprivation, were retrospectively analysed. Performance of automatic detection was compared with visual MSE scoring, following the BERN criteria, in MWT recordings of 10 participants. Driving performance was measured by the standard deviation of lateral position and the occurrence of off-road events. Results: In comparison to visual scoring, automatic detection of MSEs in participants with severe sleepiness showed good performance (Cohen’s kappa = 0.66). The MSE rate in the MWT correlated with the latency to the first MSE in the driving simulator (r_s = −0.54, p < 0.05) and with the cumulative MSE duration in the driving simulator (r_s = 0.62, p < 0.01). No correlations between MSE measures in the MWT and driving performance measures were found. In the driving simulator, multiple correlations between MSEs and driving performance variables were observed. Conclusion: Automatic MSE detection worked well, independent of the degree of sleepiness. The rate and the cumulative duration of MSEs could be promising sleepiness measures in both the MWT and the driving simulator. The correlations between MSEs in the driving simulator and driving performance might reflect a close and time-critical relationship between sleepiness and performance, potentially valuable for the fitness-to-drive assessment.

Brief fragments of sleep shorter than 15 s are defined as microsleep episodes (MSEs), often subjectively perceived as sleepiness. Their main characteristic is a slowing in frequency in the electroencephalogram (EEG), similar to stage N1 sleep according to standard criteria. The maintenance of wakefulness test (MWT) is often used in a clinical setting to assess vigilance. Scoring of the MWT in most sleep-wake centers is limited to classical definition of sleep (30 s epochs), and MSEs are mostly not considered in the absence of established scoring criteria defining MSEs but also because of the laborious work. We aimed for automatic detection of MSEs with machine learning, i.e., with deep learning based on raw EEG and EOG data as input. We analyzed MWT data of 76 patients. Experts visually scored wakefulness, and according to recently developed scoring criteria MSEs, microsleep episode candidates (MSEc), and episodes of drowsiness (ED). We implemented segmentation algorithms based on convolutional neural networks (CNNs) and a combination of a CNN with a long-short term memory (LSTM) network. A LSTM network is a type of a recurrent neural network which has a memory for past events and takes them into account. Data of 53 patients were used for training of the classifiers, 12 for validation and 11 for testing. Our algorithms showed a good performance close to human experts. The detection was very good for wakefulness and MSEs and poor for MSEc and ED, similar to the low inter-expert reliability for these borderline segments. We performed a visualization of the internal representation of the data by the artificial neuronal network performing best using t-distributed stochastic neighbor embedding (t-SNE). Visualization revealed that MSEs and wakefulness were mostly separable, though not entirely, and MSEc and ED largely intersected with the two main classes. We provide a proof of principle that it is feasible to reliably detect MSEs with deep neuronal networks based on raw EEG and EOG data with a performance close to that of human experts. The code of the algorithms (https://github.com/alexander-malafeev/microsleep-detection) and data (https://zenodo.org/record/3251716) are available.

Objective: To identify the availability and unmet need of home adaptations (HAs) among the Swiss population with spinal cord injury (SCI). Design: Cross-sectional study. Setting: Swiss Spinal Cord Injury Community Survey 2012. Participants: Individuals aged 16 or older with chronic SCI living in Switzerland. Interventions: Not applicable. Outcome measures: The availability of ten HAs (self-report) was analyzed by sex, age, living situation, indoor mobility, SCI severity, SCI etiology and time since SCI. The unmet need (self-report of not having a HA but needing it) of HAs was analyzed by financial hardship. Results: Among the 482 study participants (mean age 55.2 years, standard deviation 15.0 years, 71.6% males), 85.1% had at least one HA. The most frequent HA was a wheelchair accessible shower (62.7%). Availability of HAs markedly varied with indoor mobility (e.g. 38.4% of participants using a wheelchair had a stair lift compared to 17.4% of those walking) and with SCI severity (e.g. 54.8% of those with complete paraplegia had a wheelchair accessible kitchen worktop compared to 26.0% of those with incomplete paraplegia). Unmet need was highest for adjustable kitchen worktops (78.7% of those with a need) and adjustable kitchen cabinets (75.7%) and lowest for wheelchair accessible showers (9.4%) and grab bars next to the toilet (8.5%). No significant differences in unmet need were found when stratifying for financial hardship. Conclusion: Availability of HAs is dependent on indoor mobility and SCI severity. There is a considerable degree of unmet need for selected HAs, which couldn't be explained by financial hardship.

Optimizing nutritional intake and timing helps athletes to improve performance and long-term health. Different training phases can require varying nutritional needs. In this study, we conducted a descriptive assessment of dietary intake, energy availability (EA), and blood biochemical parameters in elite wheelchair athletes during distinct training phases. Data analyzed in this study were collected as part of a randomized controlled crossover trial exploring the feasibility of probiotics and prebiotic supplementation. Data were obtained from consecutive three-day diaries and blood samples, both collected at four different time points across four consecutive months. We included 14 athletes (mean (standard deviation) age 34 (9) years, eight females, and six males) active in different wheelchair sports. The mean daily nutritional intake (g/kg body mass) for females and males was 2.7 (0.9) and 4.0 (0.7) for carbohydrates, 1.1 (0.3) and 1.5 (0.3) for protein, and 0.8 (0.3) and 1.4 (0.2) for fat. EA did not change across the four time points in either female (p = 0.30) or male (p = 0.05) athletes. The mean EA was lower in female athletes compared to male athletes (p = 0.03). Low EA (≤30 kcal/ kg fat-free mass/day) was observed in female (58 (29) % of days) and male (34 (23) % of days) athletes. Iron deficiency with anemia was observed in two female athletes. Mean vitamin D levels were insufficient (<75 nmol/L). Macronutrient intake, EA, and blood biochemical parameters were suboptimal in this cohort of elite wheelchair athletes, especially in female athletes.