Machine Learning-Based Automatic Detection of Central Sleep Apnea Events From a Pressure Sensitive Mat

Treatment of Central Sleep Apnea in Heart Failure Patients

RATIONALE: Opioid-related central sleep apnea (CSA) is increasingly common, but its clinical implications are poorly understood. Without clear evidence of adverse outcomes, sleep physicians find it difficult to make treatment decisions regarding opiod-related CSA. We analysed the “OpSafe” (Op ioid Safe ty Program in Pain Clinics) cohort, a large prospective multicentre study of chronic opioid users, to investigate whether opioid-related CSA worsens key respiratory and sleep outcomes. METHODS: Participants on a stable opioid dose for chronic pain were recruited from five pain clinics. Measurements included resting daytime oxygen saturation (SpO2), Epworth Sleepiness Scale (ESS), and overnight in-lab polysomnography (PSG). PSGs were analysed for sleep-disordered breathing, oxygenation parameters, sleep architecture and quantitative electroencephalography (qEEG). RESULTS: A total of 160 participants were divided into three groups: 21 CSA, 66 obstructive sleep apnea (OSA), and 73 no-apnea. CSA participants had ∼4 times higher opioid dose and exhibited a ∼3% lower daytime SpO2 than OSA and no apnea participants (all p<0.001). However, during sleep, oxygenation measures were similar between CSA and OSA groups (all p>0.2). Comparing daytime SpO2 to sleep mean SpO2, OSA group decreased significantly (95.1±1.9 vs 93.9±2.1%, p=0.001), no-apnea group moderately dropped (95.9±1.9 vs 95.1±2%, p=0.05), whereas CSA group had no change in oxygen saturation (92.9±3.4 vs 93.5±2%, p=0.66).(Figure 1) CSA event duration was significantly shorter than that of OSA (15.6±4.1 vs 19.4±6.8 seconds, p=0.005). CSAs primarily occurred during non-rapid eye movement (NREM) sleep, with the REM CSA index being a third less than the NREM index [7.9(1.7-13.9) vs 27.7(10-50.1)/hr, p<0.001]. Sleep architecture and arousal indices in CSA patients were normal except for a reduced REM sleep linked to higher opioid doses. During REM sleep, while CSA was rare, the CSA group exhibited significantly higher Sigma, Alpha and Theta power than the OSA and no-apnea groups. Conversely, during NREM sleep, where CSA predominantly occurred, none of those qEEG band powers significantly differed among the three groups. Furthermore, CSA was not a significant predictor of daytime sleepiness, explaining only 1.5% of the variance of ESS. CONCLUSIONS: Our novel findings showed that opioid-related CSA did not worsen key respiratory and sleep outcomes. Instead, it may represent a compensatory mechanism through an augmented hypoxic ventilatory responses/loop gain to counterbalance opioids’ central depressant effects. Opioid-related CSA would diminish itself if the respiratory depression were resolved, usually through reducing the opioid dose. While it is essential to alleviate respiratory depression, targeted therapies to reduce opioid-related CSA may be unnecessary.

Central sleep apnea (CSA) and continuous positive airway pressure (CPAP) emergent CSA are common in patients for whom opioids have been prescribed for chronic pain management. It is not known if opioids are the potential cause of CSA. We report the case of a patient who underwent multiple full nights of polysomnography testing while on opioids, off opioids, and with various positive airway pressure devices. While on opioids, the patient had severe CSA that persisted during both CPAP and bilevel titration but was eliminated with adaptive servoventilation therapy. Some time later, opioid use was discontinued by the patient. Repeat polysomnography showed resolution of the sleep-disordered breathing. Later-while the patient was still off opioids-she had gained weight and become symptomatic; polysomnography showed obstructive sleep apnea without CSA. This time, therapy with CPAP showed elimination of sleep apnea without emergent CSA. These data collectively indicate that opioids were the cause of CSA as well as emergent CSA.

The Quest for Stability in an Unstable World: Adaptive Servoventilation in Opioid Induced Complex Sleep Apnea Syndrome

Multimodal multitask deep learning model for Alzheimer’s disease progression detection based on time series data

SLEEP-DISORDERED BREATHING AND LONG-HAUL COVID-19: A CASE REPORT

Predicting remaining useful life (RUL) is crucial for tool condition monitoring (TCM) systems. Inaccurate predictions can lead to premature tool replacements or excessive usage, resulting in resource wastage and potential equipment failures. This study introduces a novel tool RUL prediction method that integrates the enhanced northern goshawk optimization (MSANGO) algorithm with a bidirectional long short-term memory (BiLSTM) network. Initially, key statistical features are extracted from collected signal data using multivariate variational mode decomposition. This is followed by effective feature reduction, facilitated by the uniform information coefficient and Mann–Kendall trend tests. The RUL predictions are subsequently refined through a BiLSTM network, with the MSANGO algorithm optimizing the network parameters. Comparative evaluations with BiLSTM, BiGRU, and NGO-BiLSTM models, as well as tests on real-world datasets, demonstrate this method’s superior accuracy and generalizability in RUL prediction, enhancing the efficacy of tool management systems.

Clinical Guidelines for the Use of Unattended Portable Monitors in the Diagnosis of Obstructive Sleep Apnea in Adult Patients

Efficacy of Adaptive Servoventilation in Treatment of Complex and Central Sleep Apnea Syndromes

Application of Deep Learning for Reservoir Porosity Prediction and Self Organizing Map for Lithofacies Prediction

A two-stage online remaining useful life prediction framework for supercapacitors based on the fusion of deep learning network and state estimation algorithm

Central sleep apnoea (CSA) - the temporary absence or diminution of ventilatory effort during sleep - is seen in a variety of forms including periodic breathing in infancy and healthy adults at altitude and Cheyne-Stokes respiration in heart failure. In most circumstances, the cyclic absence of effort is paradoxically a consequence of hypersensitive ventilatory chemoreflex responses to oppose changes in airflow, that is elevated loop gain, leading to overshoot/undershoot ventilatory oscillations. Considerable evidence illustrates overlap between CSA and obstructive sleep apnoea (OSA), including elevated loop gain in patients with OSA and the presence of pharyngeal narrowing during central apnoeas. Indeed, treatment of OSA, whether via continuous positive airway pressure (CPAP), tracheostomy or oral appliances, can reveal CSA, an occurrence referred to as complex sleep apnoea. Factors influencing loop gain include increased chemosensitivity (increased controller gain), reduced damping of blood gas levels (increased plant gain) and increased lung to chemoreceptor circulatory delay. Sleep-wake transitions and pharyngeal dilator muscle responses effectively raise the controller gain and therefore also contribute to total loop gain and overall instability. In some circumstances, for example apnoea of infancy and central congenital hypoventilation syndrome, central apnoeas are the consequence of ventilatory depression and defective ventilatory responses, that is low loop gain. The efficacy of available treatments for CSA can be explained in terms of their effects on loop gain, for example CPAP improves lung volume (plant gain), stimulants reduce the alveolar-inspired PCO2 difference and supplemental oxygen lowers chemosensitivity. Understanding the magnitude of loop gain and the mechanisms contributing to instability may facilitate personalized interventions for CSA.

Introduction It has been well documented that opiate use is a risk factor for developing sleep apnea. We suspect that buprenorphine being a partial-opioid-agonist to also be a risk factor for developing sleep apnea. Study by Farney et al showed an association between Buprenorphine use and sleep apnea. But the literature also has contradictory findings in which a publication by Grunstein et al showed that by switching from methadone to buprenorphine pre-existing sleep apnea was eliminated, although this study only observed the effects of only short-term buprenorphine use. There is a gap in understanding the prevalence and specific risk factors associated with sleep apnea in chronic buprenorphine. Report of case(s) Patient 1: 46-year-old male. Medical History: Obesity, hypertension, coronary artery disease. Former smoker (15 pack year smoking history) Buprenorphine Use: 6 years for opioid dependence. Sleep Study: Central sleep apnea- hypopnea index of 10.3, unresponsive to CPAP titration. Patient 2: 66-year-old male Medical history: Chronic back pain, smoker Buprenorphine Use: 6 years for chronic back pain. Sleep Study: Central sleep apnea- hypopnea index of 4.5, unresponsive to CPAP titration. Patient 3: 47-year-old female. Medical History: Obesity, narcolepsy. Buprenorphine Use: 6 years. Sleep Study: No evidence of central sleep apnea on initial and subsequent studies. Patient 4: 28-year-old male. Medical History: Obesity. Buprenorphine Use: 8 years for chronic pain or opioid dependence. Sleep Study: No central sleep apnea on initial study. Subsequent study revealed central sleep apnea with central apnea- hypopnea index (AHI) of 2.9. Patient 5: 68-year-old male. Medical History: Atrial fibrillation, hyperlipidemia, chronic kidney disease, cigarette smoker, obesity. Buprenorphine Use: 8 years for chronic pain or opioid dependence. Sleep Study: Initial study showed central AHI of 0.5. Subsequent study revealed an increase in central AHI to 13.1. Conclusion The presented cases raise awareness of a possible link between long- term buprenorphine use and sleep apnea. This case series underscores the importance of monitoring individuals on long-term buprenorphine therapy for the potential development of sleep apnea. Further research is needed to elucidate the underlying mechanisms and explore management strategies for individuals facing this complication of buprenorphine therapy. Support (if any)

Maglev is a developing transportation mode in the recent years, and its safety and stability are required to be ensured by structural health monitoring system. However, the data measured by some sensors may be partially or totally unavailable due to the external electromagnetic interference or sensor failure. While, in some cases, those missing data are important to identify and analyze damage of maglev bridges. Since the structural dynamic characteristics of maglev bridge are complicated, the data reconstruction of those sensors becomes challenging. Therefore, this study proposes a bidirectional long short-term memory (BiLSTM) network to accurately reconstruct the maglev bridge acceleration data. The design of long short-term memory helps to sufficiently exploit the time series data and learn the hidden features of maglev bridge acceleration data between sensors. The bidirectional architecture enables the network to simultaneously learn the time series data from past and future, which is beneficial to extract more hidden features. A dataset collected from an in-site experiment for maglev bridge is used to verify the feasibility of the proposed method. The lost acceleration data from abnormal sensors is predicted by the acceleration data recorded from normally operating sensors. The results shows that the difference between predicted and true acceleration data is at a very low magnitude. Consequently, the proposed method can be applied for the high-performance reconstruction of maglev bridge acceleration data.

Sleep disordered breathing (SDB) is a common co-morbidity in patients with heart failure (HF). Both its forms - central and obstructive sleep apnea - are highly prevalent in this population. SDB fragments sleep, impairs life quality, worsens exercise tolerance, worsens HF and is an independent predictor of poor prognosis. Still, SDB remains largely undiagnosed. Therefore, early detection of SDB seems to be of primary importance, especially in the presence of new diagnostic and therapeutic methods. Treatment with continuous positive airway pressure (CPAP) increases left ventricular ejection fraction and stroke volume in virtually all HF patients with obstructive and in 50% with central sleep apnea. For those in whom central sleep apnea is not suppressed by CPAP, a trial of adaptive servoventilation is recommended. Although no randomized, controlled trials have shown improvement in mortality, several observational studies have shown that effective treatment of both forms of sleep apnea with various positive airway pressure devices improves survival of HF patients. Currently, 2 large trials with newer masked based therapies with adaptive servoventilation are in progress. This article is a brief overview of present knowledge, the pathophysiology, diagnostic approach and therapy of SDB.