Apnea-hypopnea Events Research Articles

In adults with moderate-to-severe OSA and obesity, tirzepatide reduced apnea-hypopnea events vs. placebo.

Malhotra A, Grunstein RR, Fietze I, et al; SURMOUNT-OSA Investigators. Tirzepatide for the treatment of obstructive sleep apnea and obesity. N Engl J Med. 21 Jun 2024. [Epub ahead of print.] 38912654.

Application study of apnea-hypopnea duration for assessing adult obstructive sleep apnea.

Obstructive sleep apnea (OSA) is a common sleep disordered breathing disorder, which can cause serious damage to multiple human systems. Although polysomnography (PSG) is the current gold standard for diagnosis, it is complex and expensive. Therefore, it is of great significance to find a simple, economical and rapid primary screening and diagnosis method to replace PSG for the diagnosis of OSA. The purpose of this study is to propose a new method for the diagnosis and classification of OSA, which is used to automatically detect the duration of sleep apnea hypopnea events (AHE), so as to estimate the ratio(S) of the total duration of all-night AHE to the total sleep time only based on the sound signal of sleep respiration, and to identify OSA. We performed PSG tests on participants and extracted relevant sleep breathing sound signal data. This study is carried out in two stages. In the first stage, the relevant PSG report data of eligible subjects were recorded, the total duration of AHE in each subject's data was extracted, and the S value was calculated to evaluate the severity of OSA. In the second stage, only the sleep breath sound signal data of the same batch of subjects were used for automatic detection, and the S value in the sleep breath sound signal was extracted, and the S value was compared with the PSG diagnosis results to calculate the accuracy of the experimental method. Among 225 subjects. Using PSG as the reference standard, the S value extracted from the PSG diagnostic data report can accurately diagnose OSA(accuracy rate 99.56%) and distinguish its severity (accuracy rate 95.11%). The accuracy of the S value detected in the sleep breathing sound signal in the diagnosis of severe OSA reached 100%. The results show that the experimental parameter S value is feasible in OSA diagnosis and classification. OSA can be identified and evaluated only by sleep breathing sounds. This method helps to simplify the diagnostic grading of traditional OSA and lays a foundation for the subsequent development of simple diagnostic grading equipment.

A novel deep learning model for obstructive sleep apnea diagnosis: hybrid CNN-Transformer approach for radar-based detection of apnea-hypopnea events.

The demand for cost-effective and accessible alternatives to polysomnography (PSG), the conventional diagnostic method for obstructive sleep apnea (OSA), has surged. In this study, we have developed and validated a deep learning model for detecting apnea-hypopnea events using radar data. We conducted a single-center prospective cohort study, dividing participants with suspected sleep-disordered breathing into development and temporally independent test sets. Utilizing a hybrid CNN-Transformer architecture, we performed 5-fold cross-validation on the development set to develop and subsequently validate the model. Evaluation metrics included sensitivity for event detection, mean absolute error (MAE), intraclass correlation coefficient (ICC), and Pearson correlation coefficient (r) for apnea-hypopnea index (AHI) estimation. Linearly weighted kappa statistics (κ) assessed OSA severity. The development set comprised 54 participants (July 2021-May 2022), while the test set included 35 participants (June 2022-June 2023). In the test set, our model achieved an event detection sensitivity of 67.2% (95% CI: 65.8%, 68.5%) and demonstrated a MAE of 7.54 (95% CI: 5.36, 9.72), indicating good agreement (ICC = 0.889 [95% CI: 0.792, 0.942]) and a strong correlation (r = 0.892 [95% CI: 0.795, 0.945]) with the ground truth for AHI estimation. Furthermore, OSA severity estimation showed substantial agreement (κ = 0.780 [95% CI: 0.658, 0.903]). Our study highlights radar sensors and advanced AI models' potential to improve OSA diagnosis, paving the path for future radar-based diagnostic models in sleep medicine research.

Deep learning of sleep apnea-hypopnea events for accurate classification of obstructive sleep apnea and determination of clinical severity

Background/Objective: Automatic apnea/hypopnea events classification, crucial for clinical applications, often faces challenges, particularly in hypopnea detection. This study aimed to evaluate the efficiency of a combined approach using nasal respiration flow (RF), peripheral oxygen saturation (SpO2), and ECG signals during polysomnography (PSG) for improved sleep apnea/hypopnea detection and obstructive sleep apnea (OSA) severity screening. MethodsAn Xception network was trained using main features from RF, SpO2, and ECG signals obtained during PSG. In addition, we incorporated demographic data for enhanced performance. The detection of apnea/hypopnea events was based on RF and SpO2 feature sets, while the screening and severity categorization of OSA utilized predicted apnea/hypopnea events in conjunction with demographic data. ResultsUsing RF and SpO2 feature sets, our model achieved an accuracy of 94 % in detecting apnea/hypopnea events. For OSA screening, an exceptional accuracy of 99 % and an AUC of 0.99 were achieved. OSA severity categorization yielded an accuracy of 93 % and an AUC of 0.91, with no misclassification between normal and mild OSA versus moderate and severe OSA. However, classification errors predominantly arose in cases with hypopnea-prevalent participants. ConclusionsThe proposed method offers a robust automatic detection system for apnea/hypopnea events, requiring fewer sensors than traditional PSG, and demonstrates exceptional performance. Additionally, the classification algorithms for OSA screening and severity categorization exhibit significant discriminatory capacity.

Obstructive sleep apnea improves with non-invasive hypoglossal nerve stimulation using temporal interference

BackgroundPeripheral nerve stimulation is used in both clinical and fundamental research for therapy and exploration. At present, non-invasive peripheral nerve stimulation still lacks the penetration depth to reach deep nerve targets and the stimulation focality to offer selectivity. It is therefore rarely employed as the primary selected nerve stimulation method. We have previously demonstrated that a new stimulation technique, temporal interference stimulation, can overcome depth and focality issues.MethodsHere, we implement a novel form of temporal interference, bilateral temporal interference stimulation, for bilateral hypoglossal nerve stimulation in rodents and humans. Pairs of electrodes are placed alongside both hypoglossal nerves to stimulate them synchronously and thus decrease the stimulation amplitude required to activate hypoglossal-nerve-controlled tongue movement.ResultsComparing bilateral temporal interference stimulation with unilateral temporal interference stimulation, we show that it can elicit the same behavioral and electrophysiological responses at a reduced stimulation amplitude. Traditional transcutaneous stimulation evokes no response with equivalent amplitudes of stimulation.ConclusionsDuring first-in-man studies, temporal interference stimulation was found to be well-tolerated, and to clinically reduce apnea-hypopnea events in a subgroup of female patients with obstructive sleep apnea. These results suggest a high clinical potential for the use of temporal interference in the treatment of obstructive sleep apnea and other diseases as a safe, effective, and patient-friendly approach. Trial registrationThe protocol was conducted with the agreement of the International Conference on Harmonisation Good Clinical Practice (ICH GCP), applicable United States Code of Federal Regulations (CFR) and followed the approved BRANY IRB File # 22-02-636-1279.

Phrenic nerve stimulation for treatment of central sleep apnea

The prevalence of central sleep apnea (CSA) is rare in general population. However, CSA is prevalent in those with cardiovascular and cerebrovascular disorders. CSA may persist or even worsen with positive airway pressure therapy in some patients and phrenic nerve stimulation (PNS) offers an alternative treatment for patients with CSA. The device is implanted similar to a cardiac pacemaker and typically followed in the sleep clinic. Multiple studies have described the efficacy and safety of PNS. Improvements were seen in apnea hypopnea events, central events, arousals, and daytime sleepiness and maintained through 5 years. Safety demonstrated a 91% freedom from serious adverse events through 1 year. The physiologic approach and improvement in sleep metrics and quality of life with a strong safety profile make this therapy a good option for many patients with central sleep apnea.

Sleep bruxism events: an epiphenomenon of severe obstructive sleep apnea?

This study investigated the temporal relationships between apnea-hypopnea (AH) and sleep bruxism (SB) events and correlated SB to various respiratory/sleep indexes in adult patients with concomitant obstructive sleep apnea (OSA) and SB. Nocturnal PSG data of 147 consecutive OSA patients were examined for comorbid SB. Among the 49 subjects with coexisting OSA and SB, 26 were randomly selected for in-depth appraisal of temporal patterns which were classified as T1 (unrelated activities), T2 (AH events occur before SB events), T3 (SB events occur before AH events), and T4 (AH and SB events occur simultaneously). Data were analyzed using Mann-Whitney U tests and Spearman's correlation (α = 0.05). The majority (84.5%) of AH events were unrelated to SB events. Of the 15.5% of related activities, T2 and T3 patterns occurred in 14.1% and 1.4%, respectively. SB events/index, the percentage of unrelated/related AH-SB events, and T2-T3 episodes were not associated with gender, age, body mass (BMI), and apnea-hypopnea (AHI) index. SB events were related to total sleep time (rs = 0.44), but no significant associations were discerned between SB and AH index. As most AH events were unrelated to SB events, OSA and SB are probably epiphenomena in adult patients with concomitant conditions. Where AH-SB events were related, the T2 temporal pattern, where SB events were subsequent to AH events, featured predominantly alluding to a specific form of secondary SB triggered by sleep micro-arousals. AH and SB events are probably epiphenomena in adult patients with coexisting OSA and SB. Even so, OSA patients should be routinely screened for SB and vice versa considering their frequent comorbidity.

0458 Cardiovascular and sociocultural factors are associated with sleep breathing differences in a diverse Hispanic/Latino cohort

Abstract Introduction Obesity and or obstructive sleep apnea (OSA) can impact awake breathing patterns, such as increments in the breathing rate. However, little is known about their associations with breathing dysregulations during sleep beyond the apnea-hypopnea events. Understanding this could help elucidate treatment mechanisms or different pathways for disease. Furthermore, there is a strong connection between breathing patterns and cardiovascular disease, thus it is also critical to understand the links between cardiovascular risk factors and disease (CVD) and sleep breathing patterns. Methods The Hispanic Community Health Study/Study of Latinos (HCHS/SOL) is a prospective multicenter study of diverse Latinos. A total of N=16,415 participants from four major metropolitan areas and six different Hispanic/Latino backgrounds were sampled for appropriate generalization to the target population. Participants were given an ARES unirecorder device (Carlsbad, San Diego) for a single night of unsupervised at home recording (N=12,022). Raw data from cannula channel (sampled at 10Hz) was processed using the python Bycycle package. Bycycle is a cycle-by-cycle approach to analyzing time series data. Bycycle finds all peaks and throughs in cycles and allows users to extract time dependent information of cycles. We extracted breathing rate (breaths per minute), breathing variability (interquartile range of breathing rate) and time spent in inhalation phase (percent time). Results In multivariable models (N=10,175), age was linked to decreased breathing rate, breathing variability, and time spent in inhalation phase. Compared to females, males had higher breathing variability and spent more time in the inhalation phase. Compared to Mexicans and? Central Americans, Cubans, Dominicans, and Puerto Ricans had less time spent in inhalation phase. Dominicans and Puerto Ricans also had increased breathing rate compared to Mexicans. Smoking, body mass index, and moderate to severe OSA were associated with increased breathing rate and variability. Systolic, but not diastolic blood pressure, was associated with increased breathing rate. We found no significant associations with cardiovascular disease. Conclusion Factors commonly linked to OSA were associated with increased breathing rate, a compensatory mechanism for optimal oxygenation, and breathing variability. Given cessation or reduced breathing during an apnea-hypopnea event, breathing variability may add more precision to account for varying oxygen demands. Support (if any)

Contactless screening for sleep apnea with breathing vibration signals based on modified U-Net

BackgroundObstructive sleep apnea (OSA) is a chronic sleep disorder characterized by frequent cessations or reductions of breathing during sleep. Polysomnography (PSG) is a definitive diagnostic tool for OSA. The costly and obtrusive nature of PSG and poor access to sleep clinics have created a demand for accurate home-based screening devices. MethodsThis paper proposes a novel OSA screening method based solely on breathing vibration signals with a modified U-Net, allowing patients to be tested at home. Sleep recordings over a whole night are collected in a contactless manner, and sleep apnea-hypopnea events are labeled by a deep neural network. The apnea-hypopnea index (AHI) calculated from events estimation is then used to screen for the apnea. The performance of the model is tested by event-based analysis and comparing the estimated AHI with the manually obtained values. ResultsThe accuracy and sensitivity of sleep apnea events detection are 97.5% and 76.4%, respectively. The mean absolute error of AHI estimation for the patients is 3.0 events/hour. The correlation between the ground truth AHI and predicted AHI shows an R2 of 0.95. In addition, 88.9% of all participants are classified into correct AHI categories. ConclusionsThe proposed scheme has great potential as a simple screening tool for sleep apnea. It can accurately detect potential OSA and help the patients to be referred for differential diagnosis of home sleep apnea test (HSAT) or polysomnographic evaluation.

Relevance of cortical arousals for risk stratification in sleep apnea: a 3 cohort analysis.

There is uncertainty on best approaches for defining apnea-hypopnea events. To clarify the contributions of desaturation vs arousal to defining hypopneas, we examined the associations of events with desaturation (≥ 3%) but not arousal (apnea-hypopnea index [AHI]≥3%Only) vs events with arousals but no desaturation (AHIArOnly) with obstructive sleep apnea-related comorbidities and incident cardiovascular disease across multiple cohorts. In the Sleep Heart Health Study (n = 5,473), the Multi-Ethnic Study of Atherosclerosis (n = 1,904), and the Osteoporotic Fractures in Men Study (n = 2,685), we examined the independent associations of AHI≥3%Only and AHIArOnly with hypertension, diabetes, and daytime sleepiness, and incident cardiovascular disease. After adjusting for covariates and AHI based on events with electroencephalogram arousal (regardless of desaturation), AHI≥3%Only was associated with hypertension in Sleep Heart Health Study (odds ratio: 1.12; 95% confidence interval: 1.04,1.21), per 1 standard deviation increase). Similar associations were observed in the Multi-Ethnic Study of Atherosclerosis and Osteoporotic Fractures in Men Study, as well as for associations with diabetes (odds ratio: 1.30; 1.09,1.54, and 1.25; 1.07,1.47, respectively), sleepiness (odds ratio: 1.19; 1.00,1.41; and 1.17; 1.01-1.35), and incident cardiovascular disease (hazard ratio: 1.37; 1.05,1.77 and 1.14; 1.00,1.29). In contrast, after adjusting for events with desaturation (regardless of arousal), AHIArOnly was unassociated with these outcomes. In Sleep Heart Health Study, greater baseline obstructive sleep apnea severity was associated with a reduction in arousal frequency over 5 years (P < .0001). In middle-aged and older individuals, addition of events with arousals does not improve the strength of associations with comorbidities or incident cardiovascular disease. Research is needed to understand generalizability to younger individuals and the mechanistic role of arousals in obstructive sleep apnea. Azarbarzin A, Sands SA, Han S, etal. Relevance of cortical arousals for risk stratification in sleep apnea: a 3 cohort analysis. J Clin Sleep Med. 2023;19(8):1475-1484.

Shorter respiratory event duration is related to prevalence of type 2 diabetes.

Obstructive sleep apnea (OSA) is a heterogeneous sleep disorder often comorbid with metabolic diseases, and type 2 diabetes (T2DM) is one of them. Although apnea hypopnea index (AHI) is currently the diagnostic criteria for OSA severity, a controversial relationship between AHI and T2DM has been found. On the other hand, the duration of apnea-hypopnea events has been shown to be a useful metric for predicting mortality. This study aimed to test whether average respiratory event duration was associated with prevalence of T2DM. Patients referred to the sleep clinic were recruited in the study. Baseline clinical characteristics and polysomnography parameters including average respiratory event duration were collected. The association of average respiratory event duration with the prevalence of T2DM was evaluated by univariate and multivariate logistic regression analyses. A total of 260 participants were enrolled, and 92 (35.4%) had T2DM. Univariate analysis revealed that age, body mass index (BMI), total sleep time, sleep efficiency, history of hypertension, and shorter average respiratory event duration were associated with T2DM. In multivariate analysis, only age and BMI remained significant. While average respiratory event duration was insignificant in multivariate analysis, subtype event analysis showed that shorter average apnea duration was both significant in univariate (OR, 0.95; 95% CI, 0.92-0.98) and multivariate analyses (OR, 0.95; 95% CI, 0.91-0.99). Neither average hypopnea duration nor AHI was associated with T2DM. Significant association (OR, 1.19; 95% CI, 1.12-1.25) was observed between shorter average apnea duration and lower respiratory arousal threshold after multivariate adjustment. However, causal mediation analysis revealed no mediating effect of arousal threshold on average apnea duration and T2DM. The average apnea duration may be a useful metric in the diagnosis of OSA comorbidity. Shorter average apnea duration indicating poor sleep quality and augmented autonomic nervous system responses might be the potential pathological mechanisms leading to T2DM.

Validity study of a multiscaled fusion network using single-lead electrocardiogram signals for obstructive sleep apnea diagnosis.

We evaluated the validity of a squeeze-and-excitation and multiscaled fusion network (SE-MSCNN) using single-lead electrocardiogram (ECG) signals for obstructive sleep apnea detection and classification. Overnight polysomnographic data from 436 participants at the Sleep Center of the First Affiliated Hospital of Sun Yat-sen University were used to generate a new FAH-ECG dataset comprising 260, 88, and 88 single-lead ECG signal recordings for training, validation, and testing, respectively. The SE-MSCNN was employed for detection of apnea-hypopnea events from the acquired ECG segments. Sensitivity, specificity, accuracy, and F1 scores were assigned to assess algorithm performance. We also used the SE-MSCNN to estimate the apnea-hypopnea index, classify obstructive sleep apnea severity, and compare the agreement between 2 sleep technicians. The SE-MSCNN's accuracy, sensitivity, specificity, and F1 score on the FAH-ECG dataset were 86.6%, 83.3%, 89.1%, and 0.843, respectively. Although slightly inferior to previously reported results using public datasets, it is superior to state-of-the-art open-source models. Furthermore, the SE-MSCNN had good agreement with manual scoring, such that the Spearman's correlations for the apnea-hypopnea index between the SE-MSCNN and 2 technicians were 0.93 and 0.94, respectively. Cohen's kappa scores in classifying the SE-MSCNN and the 2 sleep technicians were 0.72 and 0.78, respectively. In this study, we validated the use of the SE-MSCNN in a clinical environment, and despite some limitations the network appeared to meet the performance standards for generalizability. Therefore, updating algorithms based on single-lead ECG signals can facilitate the development of novel wearable devices for efficient obstructive sleep apnea screening. Yue H, Li P, Li Y, etal. Validity study of a multiscaled fusion network using single-lead electrocardiogram signals for obstructive sleep apnea diagnosis. J Clin Sleep Med. 2023;19(6):1017-1025.

Automated Detection of Sleep Apnea-Hypopnea Events Based on 60 GHz Frequency-Modulated Continuous-Wave Radar Using Convolutional Recurrent Neural Networks: A Preliminary Report of a Prospective Cohort Study.

Radar is a promising non-contact sensor for overnight polysomnography (PSG), the gold standard for diagnosing obstructive sleep apnea (OSA). This preliminary study aimed to demonstrate the feasibility of the automated detection of apnea-hypopnea events for OSA diagnosis based on 60 GHz frequency-modulated continuous-wave radar using convolutional recurrent neural networks. The dataset comprised 44 participants from an ongoing OSA cohort, recruited from July 2021 to April 2022, who underwent overnight PSG with a radar sensor. All PSG recordings, including sleep and wakefulness, were included in the dataset. Model development and evaluation were based on a five-fold cross-validation. The area under the receiver operating characteristic curve for the classification of 1-min segments ranged from 0.796 to 0.859. Depending on OSA severity, the sensitivities for apnea-hypopnea events were 49.0–67.6%, and the number of false-positive detections per participant was 23.4–52.8. The estimated apnea-hypopnea index showed strong correlations (Pearson correlation coefficient = 0.805–0.949) and good to excellent agreement (intraclass correlation coefficient = 0.776–0.929) with the ground truth. There was substantial agreement between the estimated and ground truth OSA severity (kappa statistics = 0.648–0.736). The results demonstrate the potential of radar as a standalone screening tool for OSA.

Isolated rapid eye movement sleep behavior disorder combined with obstructive sleep apnea: response to treatment and its associated factors

Objective/BackgroundWhen isolated rapid eye movement (REM) sleep behavior disorder (iRBD) is combined with obstructive sleep apnea (OSA), the pattern of temporal association between REM without atonia (RWA) and apnea-hypopnea events may be related to improvements in RBD symptoms after positive airway pressure (PAP) treatment. We evaluated the frequency of improvement in RBD symptoms after PAP and the relationship of the degree of co-occurrence between RWA and apnea-hypopnea events to RBD symptom improvement after PAP treatment. Patients/methodsIn an institutional cohort with sleep disorders, 31 patients with video-polysomnography confirmed iRBD and concomitant OSA with an apnea-hypopnea index (AHI) of ≥15/h who received PAP treatment were included. Along with gross video-polysomnography parameters such as AHI and electromyography activity index during REM sleep, a mini-epoch-based parameter apnea–hypopnea–electromyography activity ratio (AH EMG activity ratio) was used to evaluate the co-occurrence between RWA and apnea-hypopnea events. Improvement in RBD symptoms after PAP treatment was designated as a clinical global impression-improvement (CGI-I) score of 0–3 at three-month. ResultsTwenty-three (74.2%) patients exhibited improvement in RBD symptoms after PAP treatment. No patient was taking an antidepressant medication. An AH EMG activity ratio of ≥15% (Odds ratio [OR] 10.146, 95% CI 1.302–79.032, P = 0.027) was significantly associated with clinical improvement after PAP treatment in a regression model adjusted for age, sex, AHI, and electromyography activity index during REM. ConclusionsTreatment of concomitant OSA with PAP can improve symptoms of iRBD. Respiratory events that co-occur with RWA may predict improvement in RBD symptoms after PAP treatment.

Progress in clinical research of REM-related obstructive sleep apnea

REM-related obstructive sleep apnea （REM-OSA） refers to apneas and hypopneas in which most respiratory events occur during REM. The total AHI of REM-OSA is low compared to NREM-OSA, but the duration of apnea hypopnea events is longer and the oxygen saturation is lower. Only focusing on the total AHI value will miss the diagnosis of REM-OSA, and even some patients with severe hypoxemia cannot be effectively treated.REM-OSA may be an early manifestation of OSA, and active early recognition and intervention may benefit patients.The pathophysiology and mechanism of REM-OSA are still unclear. In this article, we reviewed the existing REM-OSA related research.

Deep-Learning Model Based on Convolutional Neural Networks to Classify Apnea-Hypopnea Events from the Oximetry Signal.

Automated analysis of the blood oxygen saturation (SpO2) signal from nocturnal oximetry has shown usefulness to simplify the diagnosis of obstructive sleep apnea (OSA), including the detection of respiratory events. However, the few preceding studies using SpO2 recordings have focused on the automated detection of respiratory events versus normal respiration, without making any distinction between apneas and hypopneas. In this sense, the characteristics of oxygen desaturations differ between obstructive apnea and hypopnea episodes. In this chapter, we use the SpO2 signal along with a convolutional neural network (CNN)-based deep-learning architecture for the automatic identification of apnea and hypopnea events. A total of 398 SpO2 signals from adult OSA patients were used for this purpose. A CNN architecture was trained using 30-s epochs from the SpO2 signal for the automatic classification of three classes: normal respiration, apnea, and hypopnea. Then, the apnea index (AI), the hypopnea index (HI), and the apnea-hypopnea index (AHI) were obtained by aggregating the outputs of the CNN for each subject (AICNN, HICNN, and AHICNN). This model showed a promising diagnostic performance in an independent test set, with 80.3% 3-class accuracy and 0.539 3-class Cohen's kappa for the classification of respiratory events. Furthermore, AICNN, HICNN, and AHICNN showed a high agreement with the values obtained from the standard PSG: 0.8023, 0.6774, and 0.8466 intra-class correlation coefficients (ICCs), respectively. This suggests that CNN can be used to analyze SpO2 recordings for the automated diagnosis of OSA in at-home oximetry tests.

A longitudinal study of the accuracy of positive airway pressure therapy machine-detected apnea-hypopnea events.

During positive airway pressure (PAP) therapy for sleep apnea syndromes, the machine-detected respiratory event index (REIFLOW) is an important method for clinicians to evaluate the beneficial effects of PAP. There are concerns about the accuracy of this detection, which also confounds a related question, How common and severe are residual events on PAP? Patients with obstructive sleep apnea who underwent a split-night polysomnography were recruited prospectively. Those treated with PAP and tracked by the EncoreAnywhere system (Philips Respironics, Murrysville, PA) were analyzed. Those who stopped PAP within 1 month were excluded from this analysis. Compliance, therapy data, and waveform data were analyzed. Machine-detected vs manually scored events were compared at the first, third, sixth, and 12th month from PAP initiation. Logistic regression was used to determine factors associated with a high REIFLOW difference. One hundred and seventy-nine patients with a mean age 59.06 ± 13.97 years, median body mass index of 33.60 (29.75-38.75) kg/m2, and median baseline apnea-hypopnea index of 46.30 (31.50-65.90) events/h were included. The difference between the machine-detected REIFLOW and manually scored REIFLOW was 10.72 ± 8.43 events/h in the first month and remained stable for up to 12 months. Male sex and large leak ≥ 1.5% were more frequent in patients who had an REIFLOW difference of ≥ 5 events/h of use. A titration arousal index ≥ 15 events/h of sleep, and higher ratio of unstable to stable breathing were also associated with an REIFLOW difference ≥ 5 events/h of use. There is a substantial and sustained difference between manual and automated event estimates during PAP therapy, and some associated factors were identified. Ni Y-N, Thomas RJ. A longitudinal study of the accuracy of positive airway pressure therapy machine-detected apnea-hypopnea events. J Clin Sleep Med. 2022;18(4):1121-1134.

Temporal relationship between sleep-time masseter muscle activity and apnea-hypopnea events: A pilot study.

Obstructive sleep apnea (OSA) is the most common sleep disorder due mainly to peripheral causes, characterized by repeated episodes of obstruction of the upper airways, associated with arousals and snoring. Sleep bruxism (SB) is a masticatory muscle activity during sleep that is characterized as rhythmic (phasic) or nonrhythmic (tonic) and is not a movement disorder or a sleep disorder in otherwise healthy individuals. Given the potentially severe consequences and complications of apnea, the concurrent high prevalence of SB in daily dental practice, getting deeper into the correlation between these phenomena is worthy of interest.. The aim of this study was to investigate the correlation between SB-related masseter muscle activity (MMA) and apnea-hypopnea events as well as to assess their temporal sequence. Thirty (N=30) patients with sleep respiratory disorders and clinical suspicion of sleep bruxism (SB) were recruited. Ambulatory polygraphic recording was performed to detect apnea-hypopnea events (AHEs) and sleep bruxism episodes (SBEs). Pearson test was used to assess the correlation between apnea-hypopnea index (AHI) and SB index (SBI). A 5-s time window with respect to the respiratory events was considered to describe the temporal distribution of SBEs. Furthermore, SBI was compared between groups of patients with different AHI severity (i.e., mild, moderate and severe) using ANOVA. On average, AHI was 27.1±21.8 and SBI 9.1±7.5. No correlation was shown between AHI and SBI. Most of SBEs (66.8%) occurred without a temporal relationship with respiratory events. Considering OSA, 65.7% of SBEs occurred within 5s after AHEs, while in the case of central apnea (CA) 83.8% of SBEs occurred before the respiratory event. The participants with severe apnea (N=9) show a tendency to have higher bruxism indexes when compared to patients with mild (N=11) and moderate apnea (N=10). Findings suggest that: 1. At the study population level, there is no correlation between AHI and SBI, as well as any temporal relationship between SBEs and respiratory events. 2. Specific patterns of temporal relationship might be identified with future studies focusing on the different types of apnea-hypopnea events and bruxism activities.

STOP-BANG screener vs objective obstructive sleep apnea testing among younger veterans with PTSD and insomnia: STOP-BANG does not sufficiently detect risk.

Posttraumatic stress disorder (PTSD) and obstructive sleep apnea (OSA) cooccur even in veterans who are younger with lower body mass index. The STOP-BANG screener for OSA relies heavily on high blood pressure, age, and body mass index and may not generalize to veterans with PTSD. The inability to effectively screen veterans for OSA is problematic given negative outcomes of untreated OSA. Our study compared the STOP-BANG to objective OSA diagnostic testing in 48 younger veterans (mean age 43.7 years; 43.8% Caucasian; 20.8% female) seeking treatment for PTSD and insomnia. Apnea-hypopnea events per hour (apnea-hypopnea index), recorded by NOX T3 sleep monitors, were used to diagnose OSA (apnea-hypopnea index ≥ 5 events/h). Logistic regressions examined how STOP-BANG cut-off scores (≥ 3 and ≥ 5) classified OSA status (apnea-hypopnea index ≥ 5 events/h). Follow-up chi-square goodness-of-fit tests examined single-item STOP-BANG performance in the OSA-positive subsample (n = 28). The STOP-BANG (≥ 3) had good sensitivity (92.6%) but poor specificity (47.6%) and negative (0.16) and positive (1.77) likelihood ratios. The STOP-BANG (≥ 5) led to improved specificity (76.19%), but sensitivity (37.04%) and positive (1.56)/negative likelihood ratios (0.83) were poor. Single-item OSA subgroup analyses revealed that body mass index, age, and neck circumference performed poorly, while tiredness and sex performed well. Findings suggest that the STOP-BANG correctly diagnosed OSA in some veterans but missed OSA in large number of younger veterans with PTSD. This suggests objective diagnostic OSA testing is needed in veterans with PTSD. Future research is needed to develop more accurate OSA screening measures in this population. Registry: ClinicalTrials.gov; Name: Integrated CBT-I on PE and PTSD Outcomes (Impact Study); URL: https://www.clinicaltrials.gov/ct2/show/NCT02774642; Identifier: NCT02774642. Lyons R, Barbir LA, Owens R, Colvonen PJ. STOP-BANG screener vs objective obstructive sleep apnea testing among younger veterans with PTSD and insomnia: STOP-BANG does not sufficiently detect risk. J Clin Sleep Med. 2022;18(1):67-73.

Hybrid CNN-LSTM Network for Real-Time Apnea-Hypopnea Event Detection Based on IR-UWB Radar

Polysomnography (PSG) is the gold-standard for sleep apnea and hypopnea syndrome (SAHS) diagnosis. Because the PSG system is not suitable for long-term continuous use owing to the high cost and discomfort caused by attached multi-channel sensors, alternative methods using a non-contact sensor have been investigated. However, the existing methods have limitations in that the radar-person distance is fixed, and the detected apnea hypopnea (AH) event cannot be provided in real-time. In this paper, therefore, we propose a novel approach for real-time AH event detection with impulse-radio ultra-wideband (IR-UWB) radar using a deep learning model. 36 PSG recordings and simultaneously measured IR-UWB radar data were used in the experiments. After the clutter was removed, IR-UWB radar images were segmented by sliding a 20-s window at 1-s shift, and categorized into two classes: AH and N. A hybrid model combining the convolutional neural networks and long short-term memory networks was trained with the data, which consisted of class-balanced segments. Time sequenced classified outputs were then fed to an event detector to identify valid AH events. Therefore, the proposed method showed a Cohen’s kappa coefficient of 0.728, sensitivity of 0.781, specificity of 0.956, and an accuracy of 0.930. According to the apnea-hypopnea index (AHI) estimation analysis, the Pearson’s correlation coefficient between the estimated AHI and reference AHI was 0.97. In addition, the average accuracy and kappa of SAHS diagnosis was 0.98 and 0.96, respectively, for AHI cutoffs of ≥ 5, 15, and 30 events/h. The proposed method achieved the state-of-the-art performance for classifying SAHS severity without any hand-engineered feature regardless of the user’s location. Our approach can be utilized for a cost-effective and reliable SAHS monitoring system in a home environment.