Sleep-disordered breathing and stroke

This study demonstrates deep learning approaches with an aim to find the optimal method to automatically detect sleep apnea (SA) events from an electrocardiogram (ECG) signal.

Six deep learning approaches were designed and implemented for automatic detection of SA events including deep neural network (DNN), one-dimensional (1D) convolutional neural networks (CNN), two-dimensional (2D) CNN, recurrent neural networks (RNN), long short-term memory, and gated-recurrent unit (GRU). Designed deep learning models were analyzed and compared in the performances. The ECG signal was pre-processed, normalized, and segmented into 10 s intervals. Subsequently, the signal was converted into a 2D form for analysis in the 2D CNN model. A dataset collected from 86 patients with SA was used. The training set comprised data from 69 of the patients, while the test set contained data from the remaining 17 patients.

The accuracy of the best-performing model was 99.0%, and the 1D CNN and GRU models had 99.0% recall rates.

The designed deep learning approaches performed better than those developed and tested in previous studies in terms of detecting SA events, and they could distinguish between apnea and hypopnea events using an ECG signal. The deep learning approaches such as 1D CNN and GRU can be helpful tools to automatically detect SA in sleep apnea screening and related studies.

Obstructive Sleep Apnea (OSA) is a syndrome of cyclic upper airway collapse during sleep, leading to intermittent hypoxia and sleep fragmentation. OSA leads to daytime neurocognitive impairment symptoms and is a risk factor for the development of cardio-/cerebrovascular diseases including hypertension, stroke, heart failure, and arrhythmias. In addition, OSA may be independently linked with proinflammatory conditions including asthma and the metabolic syndrome. The mechanisms underlying the daytime impairment of OSA include increased homeostatic sleep pressure resulting from chronic partial sleep deprivation, as well as increased systemic inflammation induced by chronic intermittent hypoxia. The proposed mechanisms underlying the increased cardiovascular risk seen with OSA include activation of the sympathetic nervous system, physical vibratory trauma (from snoring) to structures of the head and neck, elaboration of oxidative stress and reactive oxygen species, and a systemic proinflammatory response. Systemic markers of inflammation associated with OSA include tumor necrosis factor α, leukotriene B4, leukotriene E4, cysteinyl leukotrienes, Calprotectin, C-reactive protein, circulating microparticles, fractalkine, interleukin-6, intercellular adhesion molecule-1, nuclear factor κB, prostaglandin D2, S100A12, selectins, vascular cell adhesion molecule-1 and vascular endothelial growth factor. Factors which influence an individual’s susceptibility to the development of an inflammatory response to OSA may include genetics (Apolipoprotein E deficiency, transcription-mediated hypoxia inducible factor activation, expression of interleukin-6 gene, C-reactive protein gene, tumor necrosis factor α gene, MCP-1 gene), and the presence of obesity, which is, itself, a proinflammatory state. The adipokine leptin and its counterregulatory hormone, ghrelin, are improperly regulated in OSA, and likely also play a role in the development of a systemic proinflammatory state.

Obstructive sleep apnea (OSA) is a disorder characterized by instability of the upper airway, resulting in periodic alternation between functional obstructions to airflow during sleep and relative restoration of breathing, typically in the setting of an arousal or awakening. OSA leads to daytime neurocognitive impairment symptoms and is a risk factor for the development of cardiovascular disease including hypertension, stroke, heart failure, and arrhythmias. In addition, OSA may be independently linked with proinflammatory conditions including asthma and the metabolic syndrome. The mechanisms underlying the daytime impairment of OSA include increased homeostatic sleep pressure resulting from chronic partial sleep deprivation, as well as increased systemic inflammation induced by chronic intermittent hypoxia. The proposed mechanisms underlying the increased cardiovascular risk seen with OSA include activation of the sympathetic nervous system, physical vibratory trauma to structures of the head and neck, elaboration of oxidative stress and reactive oxygen species, and a systemic proinflammatory response. Systemic markers of inflammation associated with OSA include tumor necrosis factor a, leukotriene E4, C-reactive protein, interleukin 6, nuclear factor kB, and prostaglandin D2. Factors which influence an individual's susceptibility to the development of an inflammatory response to OSA may include genetics and the presence of obesity, which is, itself, a proinflammatory state.

This chapter discusses the cardiovascular and cerebrovascular physiology in sleep. The cardiovascular responses to rapid eye movement (REM) and nonrapid eye movement (NREM) sleep are described. The incidence of cardiovascular and cerebrovascular adverse events is highest in the early-morning hours after awakening. The chapter reviews the principles of cerebral blood flow regulation during normal sleep and the changes observed during sleep-disordered breathing. Widespread recognition of the important interactions between sleep, maintenance of health, and prevention of disease has resulted in increased attention to sleep related changes in physiologic regulation of the cardiovascular and cerebrovascular systems. These complex control mechanisms differ significantly from circulatory control during wakefulness and may be altered by disease conditions. Disturbed cardiac and neurovascular regulation may have pathophysiologic implications. Some examples include the association between REM sleep and nocturnal angina, the preponderance of cardiovascular and cerebrovascular events in the early-morning hours after waking from sleep, and the suggestion that sleep apnea-related circulatory changes may be linked to a high likelihood of sudden cardiac death occurring during sleep in patients with obstructive sleep apnea (OSA).