Self-Supervised Transformer Model Training for a Sleep-EEG Foundation Model.

The American Academy of Sleep Medicine (AASM) recognizes five sleep/wake states (Wake, N1, N2, N3, REM), yet this classification schema provides only a high-level summary of sleep and likely overlooks important neurological or health information. New, data-driven approaches are needed to more deeply probe the information content of sleep signals. Here we present a self-supervised approach that learns the structure embedded in large quantities of neurophysiological sleep data.

Laying the Foundation: Modern Transformers for Gold-Standard Sleep Analysis and Beyond.

Accurate sleep assessment is critical to the practice of sleep medicine and sleep research. The recent availability of large quantities of publicly available sleep data, alongside recent breakthroughs in AI like transformer architectures, present novel opportunities for data-driven discovery efforts. Transformers are flexible neural networks that not only excel at classification tasks, but also can enable data-driven discovery through un- or self-supervised learning, which requires no human annotations to the input data.

Suvorexant alters dynamics of the sleep-electroencephalography-power spectrum and depressive-symptom trajectories during inpatient opioid withdrawal.

Study Objectives: Opioid withdrawal is an aversive experience that often exacerbates depressive symptoms and poor sleep. The aims of the present study were to examine the effects of suvorexant on oscillatory sleep-electroencephalography (EEG) band power during medically managed opioid withdrawal, and to examine their association with withdrawal severity and depressive symptoms.

Methods: Participants with opioid use disorder (N = 38: age-range:21-63, 87% male, 45% white) underwent an 11-day buprenorphine taper, in which they were randomly assigned to suvorexant (20 mg [n = 14] or 40 mg [n = 12]), or placebo [n = 12], while ambulatory sleep-EEG data was collected.

Within-subject reaction time variability: Role of cortical networks and underlying neurophysiological mechanisms.

Variations in reaction time are a ubiquitous characteristic of human behavior. Extensively documented, they have been successfully modeled using parameters of the subject or the task, but the neural basis of behavioral reaction time that varies within the same subject and the same task has been minimally studied. In this paper, we investigate behavioral reaction time variance using 28 datasets of direct cortical recordings in humans who engaged in four different types of simple sensory-motor reaction time tasks.

Working memory load-dependent changes in cortical network connectivity estimated by machine learning.

Working memory engages multiple distributed brain networks to support goal-directed behavior and higher order cognition. Dysfunction in working memory has been associated with cognitive impairment in neuropsychiatric disorders. It is important to characterize the interactions among cortical networks that are sensitive to working memory load since such interactions can also hint at the impaired dynamics in patients with poor working memory performance.