Diagnosis Of Sleep Apnea Research Articles

Morning headache caused by obstructive sleep apnea misdiagnosed as temporomandibular disorders-related headache: A case report.

A 67-year-old woman presented to our clinic with chief complaints of headache and mandibular heaviness. Physical examination revealed bilateral tenderness in the temporalis and masseter muscles, corresponding to the patient's chief complaint. Thus, a diagnosis of temporomandibular disorders (TMDs)-related headache was made. However, sleep disorders were identified after further consultation. Hence, sleep apnea-related headache was suspected due to a snoring habit with a Mallampati classification of Class IV. Out-of-center sleep testing (OCST) revealed a respiratory event index (REI) of 10.1/h and a low peripheral oxygen saturation (SpO2) of 76%. Consequently, a diagnosis of obstructive sleep apnea (OSA) was made, and treatment using the mandibular advancement device (MAD) was recommended. Following MAD treatment, the patient's sleep quality improved, and morning headaches ceased. Subsequent OCST performed while wearing the MAD showed a significant reduction in the REI to 1.6/h and an increase in the SpO2 to 86%, indicating the therapeutic efficacy of the MAD in treating OSA. MAD treatment effectively alleviated the patient's morning headaches, suggesting that sleep bruxism should not be considered the only cause of headaches. OSA should also be considered and addressed when investigating the potential causes of morning headaches in patients. In patients experiencing TMDs symptoms and morning headaches, TMDs should not be presumed as the sole cause. Dentists should discuss the likelihood of sleep disorders during consultations. If sleep disorders are suspected, the possibility of OSA should be considered, and sleep tests should be conducted when necessary.

Retracted: Intelligent CO2 Monitoring for Diagnosis of Sleep Apnea Using Neural Cryptography Techniques

Retracted: Intelligent CO₂ Monitoring for Diagnosis of Sleep Apnea Using Neural Cryptography Techniques

High prevalence of obstructive sleep apnea in a surgical aortic valve replacement cohort: an observational study.

A high prevalence of sleep apnea has been reported among transcatheter aortic valve replacement (AVR) patients; however, the prevalence of sleep apnea in the younger and relatively healthier population of surgical AVR (SAVR) patients is unknown. We assessed the prevalence of sleep apnea and overall sleep quality in patients having SAVR. Participants aged 50-89 were eligible for recruitment. All participants completed type II HST before SAVR. Sleep apnea was defined as an apnea-hypopnea index (AHI) ≥ 5 events/hour. The current use of positive airway pressure was exclusionary. The 46 participants (32 males/14 females) had a mean age of 66.6 years, body mass index of 30, AHI of 23.5, and obstructive AHI of 22.0. Only four participants had a prior sleep apnea diagnosis, yet all but one had sleep apnea on type II sleep testing. Two-thirds of sleep apnea was moderate or severe (AHI ≥ 15). A quarter of respiratory events were defined by arousals without desaturations. Whereas most sleep parameters resembled those of similarly aged community cohorts, mean percentage of N3 was reduced, accounting for only 3.8% of total sleep time. Type II home sleep testing (HST) revealed a 97.8% prevalence of sleep apnea in this sample, most of which was undiagnosed obstructive sleep apnea. Roughly two-thirds of sleep apnea was moderate or severe. Such a high impact of obstructive sleep apnea among patients with severe aortic valve disease deserves further investigation on potential underlying mechanisms and clinical implications.

Deep and Shallow Learning Model-Based Sleep Apnea Diagnosis Systems: A Comprehensive Study

Deep and Shallow Learning Model-Based Sleep Apnea Diagnosis Systems: A Comprehensive Study

SleepECG-Net: explainable deep learning approach with ECG for pediatric sleep apnea diagnosis

SleepECG-Net: explainable deep learning approach with ECG for pediatric sleep apnea diagnosis

Deep Attention Networks With Multi-Temporal Information Fusion for Sleep Apnea Detection.

Sleep Apnea (SA) is a prevalent sleep disorder with multifaceted etiologies that can have severe consequences for patients. Diagnosing SA traditionally relies on the in-laboratory polysomnogram (PSG), which records various human physiological activities overnight. SA diagnosis involves manual scoring by qualified physicians. Traditional machine learning methods for SA detection depend on hand-crafted features, making feature selection pivotal for downstream classification tasks. In recent years, deep learning has gained popularity in SA detection due to its capability for automatic feature extraction and superior classification accuracy. This study introduces a Deep Attention Network with Multi-Temporal Information Fusion (DAN-MTIF) for SA detection using single-lead electrocardiogram (ECG) signals. This framework utilizes three 1D convolutional neural network (CNN) blocks to extract features from R-R intervals and R-peak amplitudes using segments of varying lengths. Recognizing that features derived from different temporal scales vary in their contribution to classification, we integrate a multi-head attention module with a self-attention mechanism to learn the weights for each feature vector. Comprehensive experiments and comparisons between two paradigms of classical machine learning approaches and deep learning approaches are conducted. Our experiment results demonstrate that (1) compared with benchmark methods, the proposed DAN-MTIF exhibits excellent performance with 0.9106 accuracy, 0.9396 precision, 0.8470 sensitivity, 0.9588 specificity, and 0.8909 [Formula: see text] score at per-segment level; (2) DAN-MTIF can effectively extract features with a higher degree of discrimination from ECG segments of multiple timescales than those with a single time scale, ensuring a better SA detection performance; (3) the overall performance of deep learning methods is better than the classical machine learning algorithms, highlighting the superior performance of deep learning approaches for SA detection.

Current status and future of diagnosis and treatment of obstructive sleep apnea

Current status and future of diagnosis and treatment of obstructive sleep apnea

Heritability and genetic correlations for sleep apnea, insomnia, and hypersomnia in a large clinical biobank

RationaleComorbid insomnia and sleep apnea is reported to have worse outcomes than either condition alone. The local genetic correlations of these disorders are unknown. ObjectivesTo identify local genomic regions with heritability for clinically diagnosed sleep apnea and insomnia, and to identify local genetic correlations between these disorders and/or hypersomnia. MethodsFifty thousand two hundred seventeen patients of European ancestry were examined. Global and local heritability and genetic correlations for independent regions were calculated, adjusting for obesity and other covariates. ResultsSleep apnea and insomnia were significantly globally heritable and had 118 and 168 genetic regions with local heritability p-values <.05, respectively. One region had a significant genetic correlation for sleep apnea and hypersomnia (p-value = 9.85 × 10−4). ConclusionsClinically diagnosed sleep apnea and insomnia have minimal shared genetic architecture, supporting genetically distinct comorbid insomnia and sleep apnea components. However, additional correlated regions may be identified with additional sample size and methodological improvements.

A comparative study of accuracy in major adaptive filters for motion artifact removal in sleep apnea tests.

Sleep apnea is probably the most common respiratory disorder; respiration and blood oxygen saturation (SpO2) are major concerns in sleep apnea and are also the two main parameters checked by polysomnography (PSG, the gold standard for diagnosing sleep apnea). In this study, we used a simple, non-invasive monitoring system based on photoplethysmography (PPG) to continuously monitor SpO2 and heart rate (HR) for individuals at home. Various breathing experiments were conducted to investigate the relationship between SpO2, HR, and apnea under different conditions, where two techniques (empirical formula and customized formula) for calculating SpO2 and two methods (resting HR and instantaneous HR) for assessing HR were compared. Various adaptive filters were implemented to compare the effectiveness in removing motion artifacts (MAs) during the tests. This study fills the gap in the literature by comparing the performance of different adaptive filters on estimating SpO2 and HR during apnea. The results showed that up-down finger motion introduced more MA than left-right motion, and the errors in SpO2 estimation were increased as the frequency of movement was increased; due to the low sampling frequency features of these tests, the insertion of adaptive filter increased the noise in the data instead of eliminating the MA for SpO2 estimation; the normal least mean squares (NLMS) filter is more effective in removing MA in HR estimation than other filters.

Predictive Power of XGBoost_BiLSTM Model: A Machine-Learning Approach for Accurate Sleep Apnea Detection Using Electronic Health Data

Sleep apnea is a common disorder that can cause pauses in breathing and can last from a few seconds to several minutes, as well as shallow breathing or complete cessation of breathing. Obstructive sleep apnea is strongly associated with the risk of developing several heart diseases, including coronary heart disease, heart attack, heart failure, and stroke. In addition, obstructive sleep apnea increases the risk of developing irregular heartbeats (arrhythmias), which can lead to low blood pressure. To prevent these conditions, this study presents a novel machine-learning (ML) model for predicting sleep apnea based on electronic health data that provides accurate predictions and helps in identifying the risk factors that contribute to the development of sleep apnea. The dataset used in the study includes 75 features and 10,765 samples from the Swedish National Study on Aging and Care (SNAC). The proposed model is based on two modules: the XGBoost module assesses the most important features from feature space, while the Bidirectional Long Short-Term Memory Networks (BiLSTM) module classifies the probability of sleep apnea. Using a cross-validation scheme, the proposed XGBoost_BiLSTM algorithm achieves an accuracy of 97% while using only the six most significant features from the dataset. The model’s performance is also compared with conventional long-short-term memory networks (LSTM) and other state-of-the-art ML models. The results of the study suggest that the proposed model improved the diagnosis and treatment of sleep apnea by identifying the risk factors.

Chat GPT for the management of obstructive sleep apnea: do we have a polar star?

This study explores the potential of the Chat-Generative Pre-Trained Transformer (Chat-GPT), a Large Language Model (LLM), in assisting healthcare professionals in the diagnosis of obstructive sleep apnea (OSA). It aims to assess the agreement between Chat-GPT's responses and those of expert otolaryngologists, shedding light on the role of AI-generated content in medical decision-making. A prospective, cross-sectional study was conducted, involving 350 otolaryngologists from 25 countries who responded to a specialized OSA survey. Chat-GPT was tasked with providing answers to the same survey questions. Responses were assessed by both super-experts and statistically analyzed for agreement. The study revealed that Chat-GPT and expert responses shared a common answer in over 75% of cases for individual questions. However, the overall consensus was achieved in only four questions. Super-expert assessments showed a moderate agreement level, with Chat-GPT scoring slightly lower than experts. Statistically, Chat-GPT's responses differed significantly from experts' opinions (p = 0.0009). Sub-analysis revealed areas of improvement for Chat-GPT, particularly in questions where super-experts rated its responses lower than expert consensus. Chat-GPT demonstrates potential as a valuable resource for OSA diagnosis, especially where access to specialists is limited. The study emphasizes the importance of AI-human collaboration, with Chat-GPT serving as a complementary tool rather than a replacement for medical professionals. This research contributes to the discourse in otolaryngology and encourages further exploration of AI-driven healthcare applications. While Chat-GPT exhibits a commendable level of consensus with expert responses, ongoing refinements in AI-based healthcare tools hold significant promise for the future of medicine, addressing the underdiagnosis and undertreatment of OSA and improving patient outcomes.

Optimization of CNN using modified Honey Badger Algorithm for Sleep Apnea detection

Sleep Apnea (SA) is the most prevalent breathing sleep problem, and if left untreated, it can lead to catastrophic neurological and cardiovascular illnesses. Conventionally, polysomnography (PSG) is used to diagnose SA. Nonetheless, this approach necessitates several electrodes, cables, and a professional to oversee the experiment. A promising alternative is using a single-channel signal for SA diagnosis, with the electrocardiogram (ECG) signal being among the most relevant and easily recordable. Recently, a convolutional neural network (CNN) has been used to extract efficient features from training data instead of manually selecting characteristics from ECG. However, selecting the best hyperparameter values for CNN can be challenging due to the vast number of possibilities. To address this, we propose a modified Honey Badger Algorithm (MHBA) combined with three improvement initiatives: quasi-opposition learning, arbitrary weighting agent, and adaptive mutation method. Our approach is evaluated on the Physionet Apnea ECG database, consisting of 70 single-lead ECG recordings annotated by qualified medical professionals. The experiments show that the MHBA outperforms traditional CNN and machine learning methods with an accuracy of 91.3%, AUC of 97.5%, specificity of 93.6%, and sensitivity of 90.1%. Our results demonstrate the effectiveness of the MHBA for SA detection.

An Automated System for Sleep Apnea Detection

Sleep apnea (SA) is a common sleep-related breathing disorder that can occur hundreds of times per night and can lead to catastrophic cardiovascular and neurological disorders if it happens frequently enough. Polysomnography (PSG) is the standard diagnostic tool for sleep apnea. However, it requires suspected patients to spend one to two nights in the lab and capture roughly 16 signals under professional supervision. The broad use of PSG in public health applications is hampered by complex processes. Some researchers have recently advocated using a single-lead ECG signal to detect SA. These techniques are based on the assumption that SA only uses the current ECG signal segment. SA, on the other hand, is time-dependent; that is, the SA of the preceding ECG segment has an impact on the current SA diagnosis. The authors present a time window artificial neural network that takes advantage of the time dependence between ECG signal segments while requiring no prior assumptions regarding training data distribution. The proposed method's performance has been greatly improved when compared to classic on-time window machine learning approaches as well as previous work after being verified on a genuine ECG signal dataset.

Obstructive Sleep Apnea in Adults and Ear, Nose, and Throat (ENT) Health: A Narrative Review.

Obstructive sleep apnea (OSA), a form of sleep-disordered breathing, is a significant health concern that leads to substantial morbidity. The collapse or occlusion of the upper airway, which results in reduced or cessation of airflow, is the pathophysiology of sleep apnea. The condition has been attributed to numerous cardiovascular, metabolic, and neuropsychological issues and carries serious health concerns. The ensuing intermittent hypoxia and sleep disruption set off a chain of physiological reactions that aid in developing endothelial dysfunction, systemic inflammation, and oxidative stress. The following line of treatment depends on the appropriate diagnosis of sleep apnea and the underlying cause. The gold standard for diagnosis is polysomnography (PSG), which assesses different physiological parameters during sleep. However, because polysomnography is expensive, patients may use more friendly screening and diagnostic testing kits, like home sleep apnea testing. The clinical symptoms and head and neck history may reveal essential risk factors. The primary objectives of management treatments for sleep apnea are to lessen symptoms, enhance sleep quality, and reduce any health concerns that may be present. It is advised to start with lifestyle changes such as quitting alcohol and sedative use, losing weight, and exercising frequently. The primary treatment for moderate to severe sleep apnea is continuous positive airway pressure (CPAP) therapy, which includes administering pressurized air to keep the airway open while you sleep. Oral appliances, positional therapy, surgery, and complementary therapies are other treatment choices that can be adapted to each patient's needs and preferences. The goal of the review is to evaluate the morphological and functional aspects of the upper airway, including the nose and throat, that influence the onset and severity of OSA. With a focus on the interaction between otorhinolaryngologists, sleep medicine specialists, and other healthcare professionals, we aim to consider how OSA affects otorhinolaryngology-related medical issues, look at any potential reciprocal relationships, and provide a summary of the interdisciplinary management strategy for OSA. We tried to analyse the various surgical and non-surgical therapy options for OSA management available in the otorhinolaryngology field for improving OSA symptoms and results.

ECG-based convolutional neural network in pediatric obstructive sleep apnea diagnosis

Obstructive sleep apnea (OSA) is a prevalent respiratory condition in children and is characterized by partial or complete obstruction of the upper airway during sleep. The respiratory events in OSA induce transient alterations of the cardiovascular system that ultimately can lead to increased cardiovascular risk in affected children. Therefore, a timely and accurate diagnosis is of utmost importance. However, polysomnography (PSG), the standard diagnostic test for pediatric OSA, is complex, uncomfortable, costly, and relatively inaccessible, particularly in low-resource environments, thereby resulting in substantial underdiagnosis. Here, we propose a novel deep-learning approach to simplify the diagnosis of pediatric OSA using raw electrocardiogram tracing (ECG). Specifically, a new convolutional neural network (CNN)-based regression model was implemented to automatically predict pediatric OSA by estimating its severity based on the apnea-hypopnea index (AHI) and deriving 4 OSA severity categories. For this purpose, overnight ECGs from 1,610 PSG recordings obtained from the Childhood Adenotonsillectomy Trial (CHAT) database were used. The database was randomly divided into approximately 60%, 20%, and 20% for training, validation, and testing, respectively. The diagnostic performance of the proposed CNN model largely outperformed the most accurate previous algorithms that relied on ECG-derived features (4-class Cohen's kappa coefficient of 0.373 versus 0.166). Specifically, for AHI cutoff values of 1, 5, and 10 events/hour, the binary classification achieved sensitivities of 84.19%, 76.67%, and 53.66%; specificities of 46.15%, 91.39%, and 98.06%; and accuracies of 75.92%, 86.96%, and 91.97%, respectively. Therefore, pediatric OSA can be readily identified by our proposed CNN model, which provides a simpler, faster, and more accessible diagnostic test that can be implemented in clinical practice.

Correlation between Desaturation Event Index and Apnea Hypopnea Index for Diagnosis of Obstructive Sleep Apnea

Correlation between Desaturation Event Index and Apnea Hypopnea Index for Diagnosis of Obstructive Sleep Apnea

Prediction of the Sleep Apnea Severity Using 2D-Convolutional Neural Networks and Respiratory Effort Signals.

The high prevalence of sleep apnea and the limitations of polysomnography have prompted the investigation of strategies aimed at automated diagnosis using a restricted number of physiological measures. This study aimed to demonstrate that thoracic (THO) and abdominal (ABD) movement signals are useful for accurately estimating the severity of sleep apnea, even if central respiratory events are present. Thus, we developed 2D-convolutional neural networks (CNNs) jointly using THO and ABD to automatically estimate sleep apnea severity and evaluate the central event contribution. Our proposal achieved an intraclass correlation coefficient (ICC) = 0.75 and a root mean square error (RMSE) = 10.33 events/h when estimating the apnea-hypopnea index, and ICC = 0.83 and RMSE = 0.95 events/h when estimating the central apnea index. The CNN obtained accuracies of 94.98%, 79.82%, and 81.60% for 5, 15, and 30 events/h when evaluating the complete apnea hypopnea index. The model improved when the nature of the events was central: 98.72% and 99.74% accuracy for 5 and 15 events/h. Hence, the information extracted from these signals using CNNs could be a powerful tool to diagnose sleep apnea, especially in subjects with a high density of central apnea events.

FRI434 Long-term Self-reported Outcomes Of Randomized Testosterone (T) vs Placebo (P) Treatment In The T4DM Study

Abstract Disclosure: D.J. Handelsman: None. M. Grossmann: None. B.B. Yeap: Consulting Fee; Self; Bayer, Inc., Lawley. Research Investigator; Self; Lawley. B.G. Stuckey: Speaker; Self; Lawley. N. Shankara-Narayana: None. A.J. Conway: None. W. Inder: None. R.I. McLachlan: None. C.A. Allan: None. A. Jenkins: None. D.R. Jesudason: None. K. Bracken: None. K. Robledo: None. G.A. Wittert: Research Investigator; Self; Bayer, Inc., Lilly USA, LLC. The T4DM study randomized 1007 men (age 50-74 yr, waist ≥95 cm, serum T ≤14.0 nmol/L, no pathological hypogonadism) with impaired glucose tolerance or newly diagnosed type 2 diabetes to T undecanoate (1000 mg) or matching placebo injections every 12 weeks for 24 months with a lifestyle program. At study’s end, T treatment reduced OGTT diabetes diagnosis by 40% without change in HbA1C. After a median of 5 years since last injection, a follow-up email survey obtained 705 responses (70%) comprising 599 completed surveys (316 T, 283 P, 10 deceased, 95 declining). Participants in follow-up survey were similar to non-participants in 23 anthropometric and demographic variables at entry to T4DM, but more in follow-up study were randomized to T (53 vs 46%%, p=0.038), had lower entry weight (107 vs 109 kg, p=0.026) and older school leaving age (16.7 vs 16.5 years, p=0.026) but remaining well matched for work status (46% retired, 35% full-time work, p=0.60), alcohol intake (69% nil or light, 3% heavy; p=0.12) and smoking (3% smoking, p=0.61). At long-term follow-up, randomization to T treatment was associated with stronger belief in benefits during study (64% vs 49%, p&amp;lt;0.001) with less for post-study benefits (44% vs 40%, p=0.07) but overall high interest in future studies (surveys 93%, clinical 76%). At entry, 35% had sleep apnea, most (71%) diagnosed pre-study, with new diagnosis more frequent on T during (9% vs 1%, p=0.03), but not before or after, the study. After study, T treatment was prescribed at a higher rate for men who had study T treatment (6% vs 2.8%, p=0.03), mostly using T injections with 81% continuing at 24 months (median) on post-study T treatment. In the long-term, study T treatment did not influence self-reported new post-T4DM study diagnosis of diabetes (19%, p=0.65) or diabetes drug treatments (22%, p=0.31; oral 18%, injectable 2%, both 2%), prostate disease (p=0.49; cancer 3%, non-cancer 8%) or cardiovascular disease (p=0.95; heart disease 13%, stroke 1%). Both groups had similar weight maintenance (maintained 24%, lost 22%, gain 24%, up/down 30%, p=0.91) and further attempts to lose weight (76%, p=0.29; diet 68%, exercise 57%, drugs 6%, surgery 2%). We conclude that randomized T (vs placebo) treatment for 24 months in men with impaired glucose tolerance or new diabetes but without pathological hypogonadism, was associated with higher rates of (a) self-reported benefits during, but not after the study, (b) of resuming T treatment after the study, consistent with androgen dependence due to withdrawal (androgen deficiency) symptoms and/or recalling perceived benefits of study T treatment, and (c) of sleep apnea diagnosis during, but not before or after the study. Five years after T treatment stopped, there was no difference in the long-term rates of self-reported new diagnosis of diabetes, prostate or cardiovascular disease nor change in weight maintenance or weight loss behaviors. Presentation: Friday, June 16, 2023

HOME SLEEP APNEA TESTING: HOW FAR DID WE COME WITH DIAGNOSING AND TREATING SLEEP APNEA AT HOME?

HOME SLEEP APNEA TESTING: HOW FAR DID WE COME WITH DIAGNOSING AND TREATING SLEEP APNEA AT HOME?

Software defined radio frequency sensing framework for intelligent monitoring of sleep apnea syndrome.

Healthy sleep is vital to all functions in the body. It improves physical and mental health, strengthens resistance against diseases, and develops strong immunity against metabolism and chronic diseases. However, a sleep disorder can cause the inability to sleep well. Sleep apnea syndrome is a critical breathing disorder that occurs during sleeping when breathing stops suddenly and starts when awake, causing sleep disturbance. If it is not treated timely, it can produce loud snoring and drowsiness or causes more acute health problems such as high blood pressure or heart attack. The accepted standard for diagnosing sleep apnea syndrome is full-night polysomnography. However, its limitations include a high cost and inconvenience. This article aims to develop an intelligent monitoring framework for detecting breathing events based on Software Defined Radio Frequency (SDRF) sensing and verify its feasibility for diagnosing sleep apnea syndrome. We extract the wireless channel state information (WCSI) for breathing motion using channel frequency response (CFR) recorded in time at every instant at the receiver. The proposed approach simplifies the receiver structure with the added functionality of communication and sensing together. Initially, simulations are conducted to test the feasibility of the SDRF sensing design for the simulated wireless channel. Then, a real-time experimental setup is developed in a lab environment to address the challenges of the wireless channel. We conducted 100 experiments to collect the dataset of 25 subjects for four breathing patterns. SDRF sensing system accurately detected breathing events during sleep without subject contact. The developed intelligent framework uses machine learning classifiers to classify sleep apnea syndrome and other breathing patterns with an acceptable accuracy of 95.9%. The developed framework aims to build a non-invasive sensing system to diagnose patients conveniently suffering from sleep apnea syndrome. Furthermore, this framework can easily be further extended for E-health applications.