Our neural network can score sleep using a single lead of ECG data at an equivalent performance to expert human-scored PSG. It was trained and evaluated on 4,000 recordings from subjects 5 to 90 years old. What was the approach or how does the tool work? The neural network was designed with the intention of testing if cardiosomnography (an ECG-only sleep study) could complement or replace polysomnography (PSG). Keep reading
The goal of the study was to see if children’s treatment response to early adenotonsillectomy (eAT) could be predicted using the sleep quality index (SQI), which is based on cardiopulmonary coupling (CPC). We were specifically interested in changes in metabolic health. Keep reading
Four key obstructive sleep apnea (OSA) endotypic traits have been identified, namely: collapsibility, upper airway muscle compensation, arousal threshold and loop gain. However, most methods for extracting these traits require specialized training and equipment not available in a standard sleep clinic, which has hampered the ability to assess the full impact of these traits on OSA outcomes. Keep reading
Random forest machine learning is a popular predictive tool in medical research. However, when attempting to determine why the random forest model is predictive, applied researchers continue to rely on ‘out of bag’ (OOB) variable importance metrics (VIMPs) that are known to have considerable limitations within the statistics community, including a bias towards highly correlated features. Keep reading
It remains to be determined whether and in which individuals weekend catch-up sleep (CUS) promotes health. The health effects of weekend CUS could differ depending on both the ability to obtain sufficient sleep during weekdays and amount of weekend CUS required to compensate for sleep lost during the week. We examined the longitudinal association of these two aspects of sleep with all-cause mortality. Keep reading
AASM guidelines are the result of decades of efforts aimed at standardizing sleep scoring procedures, with the final goal of sharing a worldwide common methodology. The guidelines cover several aspects from the technical/digital specifications, e.g., recommended EEG derivations, to detailed sleep scoring rules according to age. Automated sleep scoring systems - e.g. highly performing deep learning (DL) algorithms - have always largely exploited the standards as fundamental guidelines. Keep reading
The Greifswald Sleep Stage Classifier (GSSC) is a highly accurate, deep learning-based automatic sleep stage classifier that priortises ease of use as well as accessibility for a broad range of potential applications and recording environments. Sleep staging can be performed within a simple GUI, the command-line, or integrated directly into the user's own Python code. Keep reading
Textbook depictions of aging suggest a linear, almost deterministic, worsening of sleep architecture and sleep physiology in older adulthood. However, such conceptualizations of aging arise from group-averaged cross-sectional polysomnography data. What was the approach to solving the problem? We used a large-sample, longitudinal dataset to investigate individual trajectories in spectral power. Keep reading
Obstructive sleep apnea (OSA) affects more than 20% of the global adult population, with approximately 80% of cases remaining undiagnosed. Although home sleep test solutions have existed for almost two decades, they suffer from significant limitations. A recent review reported a misdiagnosis rate of 39% for home sleep tests. Keep reading
Due to adverse social and environmental factors, Black children and/or those living in lower socioeconomic status (SES) contexts are more likely to experience sleep disorders, including obstructive sleep apnea syndrome (OSAS), as well as short and irregular sleep duration. Children with OSAS also often have behavioral difficulties, but little is known about whether these challenges are worse when children also experience poor sleep, which is linked to similar child outcomes. Keep reading