Sleep Technician Research Articles

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.

O014 Tolerance of polysomnography in children with neurodisability versus neurotypical peers

Abstract Background Diagnostic polysomnography (PSG) is the gold standard test to evaluate children for sleep-disordered breathing (SDB). Little is known about how well children with neurodisability tolerate the components of PSG compared to neurotypical children. Methods We conducted a retrospective cohort study of children >12 months old who underwent diagnostic PSG at our centre from 01/01/2021-30/06/2021, examining how PSG-related monitoring leads were tolerated, based primarily on sleep technician and physician reports. Data extracted included reports of how children tolerated PSG set-up and the individual leads through the night. Children with neurodisability were compared to neurotypical children and sub-analyses were conducted related to particular sub-groups (e.g. Trisomy 21). Results 132 children with neurodisability and 139 neurotypical children underwent diagnostic PSG. Mean age was 8 years, 50% had a sleep disorder identified on PSG and 39% were female, with no significant differences between the groups. The most-poorly tolerated sensor for all children was the nasal pressure transducer (poorly tolerated in 30%), followed by thermistor (14%) and EEG leads (6%). Children with neurodisability were less likely to tolerate all PSG leads (44% did not tolerate all) compared to neurotypical children (20%) [relative risk 1.8, 95%CI 1.2-1.7, p<0.05]. Children with Trisomy 21 had an increased likelihood of PSG lead intolerance (63%) compared to neurotypical children [relative risk 2.3, 95%CI 1.4-3.8 p<0.05]. Conclusion This retrospective study demonstrates that children with neurodisability are less likely to tolerate PSG monitoring than neurotypical children and highlights the need to develop alternative measures for evaluation of SDB in this population.

A Deep Learning Framework for Automatic Sleep Apnea Classification Based on Empirical Mode Decomposition Derived from Single-Lead Electrocardiogram.

Background: Although polysomnography (PSG) is a gold standard tool for diagnosing sleep apnea (SA), it can reduce the patient’s sleep quality by the placement of several disturbing sensors and can only be interpreted by a highly trained sleep technician or scientist. In recent years, electrocardiogram (ECG)-derived respiration (EDR) and heart rate variability (HRV) have been used to automatically diagnose SA and reduce the drawbacks of PSG. Up to now, most of the proposed approaches focus on machine-learning (ML) algorithms and feature engineering, which require prior expert knowledge and experience. The present study proposes an SA detection algorithm to differentiate a normal and apnea event using a deep-learning (DL) framework based on 1D and 2D deep CNN with empirical mode decomposition (EMD) of a preprocessed ECG signal. The EMD is ideally suited to extract essential components which are characteristic of the underlying biological or physiological processes. In addition, the simple and compact architecture of 1D deep CNN, which only performs 1D convolutions, and pretrained 2D deep CNNs, are suitable for real-time and low-cost hardware implementation. Method: This study was validated using 7 h to nearly 10 h overnight ECG recordings from 33 subjects with an average apnea-hypopnea index (AHI) of 30.23/h originated from PhysioNet Apnea-ECG database (PAED). In preprocessing, the raw ECG signal was normalized and filtered using the FIR band pass filter. The preprocessed ECG signal was then decomposed using the empirical mode decomposition (EMD) technique to generate several features. Several important generated features were selected using neighborhood component analysis (NCA). Finally, deep learning algorithm based on 1D and 2D deep CNN were used to perform the classification of normal and apnea event. The synthetic minority oversampling technique (SMOTE) was also applied to evaluate the influence of the imbalanced data problem. Results: The segment-level classification performance had 93.8% accuracy with 94.9% sensitivity and 92.7% specificity based on 5-fold cross-validation (5fold-CV), meanwhile, the subject-level classification performance had 83.5% accuracy with 75.9% sensitivity and 88.7% specificity based on leave-one-subject-out cross-validation (LOSO-CV). Conclusion: A novel and robust SA detection algorithm based on the ECG decomposed signal using EMD and deep CNN was successfully developed in this study.

Detection of Cheyne-Stokes Breathing using a transformer-based neural network.

Annotation of sleep disordered breathing, including Cheyne-Stokes Breathing (CSB), is an expensive and time-consuming process for the clinician. To solve the problem, this paper presents a deep learning-based algorithm for automatic sample-wise detection of CSB in nocturnal polysomnographic (PSG) recordings. 523 PSG recordings were retrieved from four different sleep cohorts and subsequently scored for CSB by three certified sleep technicians. The data was pre-processed and 16 time domain features were extracted and passed into a neural network inspired by the transformer unit. Finally, the network output was post-processed to achieve physiologically meaningful predictions. The algorithm reached a F1-score of 0.76, close to the certified sleep technicians showing that it is possible to automatically detect CSB with the proposed model. The algorithm had difficulties distinguishing between severe obstructive sleep apnea and CSB but this was not dissimilar to technician performance. In conclusion, the proposed algorithm showed promising results and a confirmation of the performance could make it relevant as a screening tool in a clinical setting.

Minimal EEG channel selection for depression detection with connectivity features during sleep

Background and objectivesSleeping cortical electroencephalogram (EEG) has the potential for depression detection, for different sleep structure and cortical connection have been proved in depressed patients. However, the operation of multi-channel sleep EEG recording is cumbersome and requires laboratory equipment and professional sleep technician. Here, we focus on the depression detection using minimal sleep EEG channels. MethodsSixteen channels of EEG data of 30 patients with depression and 30 age-matched normal controls were recorded during sleep. Power spectral density of each single EEG channel was calculated, followed by measuring the symbolic transfer entropy (STE) and weighed phase lag index (WPLI) between EEG channel pairs in various frequency bands. Thereafter, these features were evaluated by F-score in the two-way classification (depression vs. control) of 30-s sleep EEG segments. Based on the F-score, entropy method was introduced to calculate the weight which could further assess the classification ability of various EEG channels or channel pairs. Finally, machine learning was implemented to verify the important EEG channels or channel pairs in depression diagnosis. ResultsThe features characterizing the inter-hemispheric connectivity in the posterior lobe, especially in the temporal lobe, showed high classification capacity. The classification accuracy of using two and four EEG channels in the temporal lobe were 97.96% and 99.61%, respectively. ConclusionsThis study showed the possibility of using only a few sleep EEG channels for depression screening, which may greatly facilitate the diagnosis of depression outside the hospital.

0579 The impact of intracranial EEG on sleep is independent of whether a craniotomy was performed

Abstract Introduction Patients with refractory epilepsy are often evaluated with intracranial electrodes prior to resection. While depth electrodes can be placed through small burr-holes, grids and strips generally require large craniotomies. We have observed many differences in patient experience between these two populations. As sleep is crucial for many aspects of health and healing, our objective was to quantify whether subjects with craniotomies had different sleep patterns. Methods We analyzed data from N=47 patients with refractory epilepsy who underwent intracranial EEG monitoring at the University of Michigan (N = 23 with craniotomies). Sleep stages were scored by a certified sleep technician using simultaneously recorded scalp EEG. To quantify sleep patterns, we computed the fraction and average bout-length of each state of vigilance. Results No statistical difference was found between subjects with or without craniotomies for any measure (p>0.4, Wilcoxon Rank Sum). The median fraction of time awake for all subjects was 0.70 (0.65-0.74, 95% confidence interval). However, sleep architecture appeared altered, with median fraction of sleep time in NREM 1 being 0.07(0.06-0.09), NREM 2 being 0.16 (0.13-0.17), NREM 3 being only 0.01 (0.0-0.2) and REM being 0.05 (0.04-0.06). The median bout lengths for all stages of sleep was less than 5 minutes. Conclusion Intracranial monitoring appears to alter sleep similarly for both subjects who received craniotomies and those who had smaller burr-holes. The impact on sleep is not a significant factor when deciding between grid or depth electrodes. Support (If Any) National Institutes of Health (K01-ES026839 and R01-NS094399), and the Doris Duke Foundation (grant number 2015096).

Automatic Home-based Screening of Obstructive Sleep Apnea using Single Channel Electrocardiogram and SPO2 Signals

Obstructive sleep apnea (OSA) is one of the most widespread respiratory diseases today. Complete or relative breathing cessations due to upper airway subsidence during sleep is OSA. It has confirmed potential influence on Covid-19 hospitalization and mortality, and is strongly associated with major comorbidities of severe Covid-19 infection. Un-diagnosed OSA may also lead to a variety of severe physical and mental side-effects. To score OSA severity, nocturnal sleep monitoring is performed under defined protocols and standards called polysomnography (PSG). This method is time-consuming, expensive, and requiring professional sleep technicians. Automatic home-based detection of OSA is welcome and in great demand. It is a fast and effective way for referring OSA suspects to sleep clinics for further monitoring. On-line OSA detection also can be a part of a closed-loop automatic control of the OSA therapeutic/assistive devices. In this paper, several solutions for online OSA detection are introduced and tested on 155 subjects of three different databases. The best combinational solution uses mutual information (MI) analysis for selecting out of ECG and SpO2-based features. Several methods of supervised and unsupervised machine learning are employed to detect apnoeic episodes. To achieve the best performance, the most successful classifiers in four different ternary combination methods are used. The proposed configurations exploit limited use of biological signals, have online working scheme, and exhibit uniform and acceptable performance (over 85%) in all the employed databases. The benefits have not been gathered all together in the previous published methods.

P054 The effect of head up bed-tilt (HUT) on sleep disordered breathing (SDB) in patients with supine dominant sleep apnoea (SDOSA): an exploratory study

Abstract SDB severity is reduced in SDOSA when posture changes from supine to lateral. Sleeping with a head up bed-tilt(HUT) is known to reduce SDB in some OSA patients. In this exploratory study, we tested whether HUT could be used to reduce SDB in SDOSA patients who had refused continuous positive airway pressure therapy(CPAP). We studied 5 male patients (age: 60 to 72years, BMI: 25.8 to 32.2kg/m2). Standard, in-laboratory, overnight-polysomnography was performed (Compumedics Ltd, Australia). Posture was monitored, but not restricted, and bed position was set at horizontal(HB) for half the night and at 7° HUT for the remainder (randomised). Polysomnograms were scored by a sleep technician using AASM criteria. SDB severity was quantified using the apnoea hypopnoea index(AHI) and apnoea index(AI). For this analysis, we focus on periods of supine, stage 2 sleep (S2S) only. Participants spent 23 to 60minutes (range) in S2S with HB and 11 to 36minutes with HUT. AHI was 49 to 138events/hr with HB and 24 to 120events/hr with HUT, representing a fall of 2 to 62events/hr across all patients. AI was 19 to 111events/hr with HB and 0 to 48 events/hr with HUT, a fall of 15 to 96events/hr across all patients. In these CPAP non-compliant, SDOSA patients, S2S in HUT was associated with a reduction in SDB severity that varied between individuals. Notably apnoeic events were reduced in all patients and eliminated in two patients. We conclude that HUT warrants further investigation as a potential alternative therapy for SDOSA patients intolerant of CPAP.

New Predictive Equation for Optimal Continuous Positive Airway Pressure in Adult Patients with Obstructive Sleep Apnea

Objective: This study aimed to develop and validate a new continuous positive airway pressure (CPAP) prediction equation and compare it with other formulas.Material and Methods: We retrospectively included patients with obstructive sleep apnea who underwent a CPAP titration study between January 2012 and December 2016. All clinical and polysomnographic data were collected. The new prediction equation was developed using the first data set, and the predictability performance was validated using the second data set.Results: Among the 266 enrolled patients, 73.7% were male, and the mean body mass index (BMI) was 30.8±7.4 kg/m2 . Five variables, namely age, BMI, neck circumference (NC), apnea–hypopnea index (AHI), and minimum pulse oxygen saturation (Min SpO2 ), highly correlated with the optimal titration pressure, and were therefore included in the equation, as stated below:Predicted pressure (cm H2 O) = 2.26 + (0.02xAge) + (0.04xBMI) + (0.11xNC) + (0.04xAHI) - (0.04xMin SpO2 )This equation accounted for 54.4% of the variance in predicting the optimal titration pressure (R2 =0.544, p-value <0.001). Its optimal estimation was 62.0% in the validated group. The equation-derived predicted pressure correlated with good agreement with the laboratory-derived optimal titration pressure (r=0.70, 95% CI=0.6335–0.755, p-value<0.001) according to Bland–Altman analysis. Conclusion: Our equation is highly consistent with the CPAP titration study in predicting fixed CPAP pressure, and is thereby beneficial for sleep technicians in establishing a starting pressure for such studies at a sleep laboratory.

Daytime polysomnography to perform titration for upper airway stimulation in patients with obstructive sleep apnea.

PurposeUpper airway stimulation (UAS) is an innovative treatment for patients with obstructive sleep apnea (OSA). UAS titrations are performed 3 months after activation of the device to optimize its effectiveness. In general, these titrations are performed during an in-laboratory overnight polysomnography (PSG). However, overnight titrations are expensive and can be logistically challenging because they are labor-intensive which causes shortage of sleep technicians available for night shifts. In addition, recently, overnight PSGs were postponed and canceled due to the COVID-19 pandemic. We aimed to assess the feasibility of a daytime PSG to perform titration of UAS therapy as an alternative for a conventional overnight PSG.MethodsWe performed a prospective single-center observational cohort study. Patients were included when planned for UAS titration; this was approximately 6 months after UAS activation. Data on sleep architecture, patient experience, and respiratory outcomes were collected to evaluate the feasibility. An overnight follow-up PSG 12 months after implantation was used to compare sleep architecture and therapy response.ResultsOf 23 patients, four were excluded from analysis because of technical issues during PSG. Even though patients slept significantly shorter during the daytime PSG, this was enough time to complete the titration successfully with 30-min sleep in final therapeutic settings in 84% of the patients. Patients (94%) had a positive experience with the daytime titration. Respiratory outcomes were significantly reduced during titration and were maintained at the 12-month follow-up.ConclusionDaytime titrations are a valuable alternative for conventional overnight titrations. Our findings suggest the implementation of daytime titrations as standard of care. This will contribute to easier logistics and better work circumstances for sleep technicians without jeopardizing titration quality.

Sleep increases leaks and asynchronies during home noninvasive ventilation: a polysomnographic study.

In patients treated with noninvasive ventilation, sleep-related breathing changes can modify patient-ventilator interactions, which could reduce its effectiveness. The aim of this prospective observational study was to determine the impact of sleep/wake state on leaks, upper airway obstructive events, and asynchronies in patients treated by long-term noninvasive ventilation. Stable patients adapted to noninvasive ventilation were considered for nocturnal polysomnography. Unintentional leaks, upper airway obstructive events, and asynchronies were compared between sleep and awake periods. Twenty-eight patients were enrolled. Underlying diagnoses were neuromuscular disease (n = 11), chest wall disease (n = 8), and obesity-hypoventilation (n = 9). Leaks were more frequent in sleep than in awake periods, with a median of 10% (interquartile range [IQR], 0%-75%) vs 1% (IQR, 0%-9%) of time (P < .001), respectively. During sleep, asynchronies with and without associated leak affected 27% of breaths (IQR, 16%-39%) compared with non-leak-related asynchronies that were recorded in 8% (IQR, 3%-25%) of breaths (P < .001). Asynchronies affecting more than 10% of total breaths were more frequent in sleep (25 patients, 89%) than in awake time (8 patients, 29%; P = .25). Eleven patients (39%) presented with 5 or more upper airway obstructive events without reduction in ventilatory drive per hour of sleep. In patients adapted to home noninvasive ventilation, leaks, asynchronies, and upper airway obstructive events are frequent during the night and are concentrated in sleep periods. Asynchronies are often associated with leaks. These findings may have clinical implications considering that in patients with low sleep efficiency respiratory events could be underestimated if sleep is not evaluated. Martí S, Ferré A, Sampol G, etal. Sleep increases leaks and asynchronies during home noninvasive ventilation: a polysomnographic study. J Clin Sleep Med. 2022;18(1):225-233.

Roles of nurses in sleep medicine

Sleep health becomes an important component of global public health. The incidence of sleep disorders is increasing rapidly worldwide, which seriously affects people's quality of life. In China, the lack of professional sleep physicians and technicians, the distribution of sleep centers and the unbalanced development of medical resources have seriously restricted the development of sleep medicine and the improvement of sleep health guarantee level. In Europe and America and other developed countries, sleep medicine has become a new interdisciplinary discipline. The development of nurses as sleep coordinator has become an irresistible trend. Nurses have been trained to become the main force of sleep technicians. These successful attempts in the field of sleep medicine provide reference for promoting the development of nursing care in China from the aspects of medical care, teaching and research.

Implementing a sleep technician-supervised and personalized APAP interface fitting session prior to initiation of home APAP therapy improves adherence in patients with obstructive sleep apnea.

Home automatic positive airway pressure (APAP) therapy is becoming a mainstay treatment of obstructive sleep apnea. It is typically prescribed without any prior supervised titration. Initial experience of APAP treatment dictates subsequent use. Discomfort related to the APAP interface contributes to poor APAP adherence. After obtaining institutional review board approval, 156 adult patients newly diagnosed with obstructive sleep apnea were prospectively randomized into 2 groups (group A and group B). Group A received a 30-minute personalized interface/mask fitting session supervised by a certified sleep technician, during which APAP therapy was simulated and patients were educated on proper use. Patients sampled different interfaces to address any issues with comfort. Group B received usual care where patients obtained an interface through durable medical equipment suppliers. Primary endpoints included percent APAP usage (number of days APAP was used for ≥ 4 hours divided by 30 days) and APAP usage (number of days APAP was used for any duration) during the initial 30 days of home APAP therapy. Interface-associated air leak served as the secondary endpoint. Mean percent APAP usage was higher in group A compared to group B (78.4% vs 67.8%; P = .04). On average, group A utilized the APAP machine on more days compared to group B (27 vs 24 days; P = .01). APAP interface associated air leak was lower in group A compared to group B (14.9 vs 21.1 l/min; P = .03). Our findings demonstrate that implementing a personalized interface fitting session supervised by a sleep technician improves APAP adherence. Syed Z, Mehta I, Hella JR, Barber K, Khorfan F. Implementing a sleep technician-supervised and personalized APAP interface fitting session prior to initiation of home APAP therapy improves adherence in patients with obstructive sleep apnea. J Clin Sleep Med. 2021;17(10):2057-2065.

463 The Effect of Intervention of Medical Staff on the Adherence of CPAP and Heart Rate in Patients with Obstructive Sleep Apnea

Abstract Introduction Recent studies have indicated that obstructive sleep apnea syndrome (OSAS) is associated with hypertension. OSA is a common cause of sympathetic nervous activity. Increase of sympathetic nervous activity causes hypertension. Continuous positive airway pressure (CPAP) is the most useful treatment for OSAS. Good CPAP adherence treatment improve the risk of hypertension. This study examined the effect of intervention of medical staff on the adherence of CPAP, heart rate and sleep stages in patients with OSA. Methods All patients diagnosed with OSA and undergoing subsequent CPAP were clinically followed for 12 months to examine CPAP adherence, as well as longitudinal changes in blood pressure, average heartrate of 24 hours and sleep stages. They were divided into 2 groups, Group A: patients who had individual consulted in person by sleep physician and technicians before start using CPAP and Group B: patents who did not have individual consulted. Patients in both groups were consulted by sleep physician and technicians after start CPAP with utilizing tele-monitoring. If the adherence were poor, the patients were recommended to stop CPAP. We provided 3D accelerometer and an optical pulse photoplethysmography to all the patients and analyzed the data of heart rate and sleep stages. Results A total of 30 OSA patients underwent CPAP, were enrolled in the study and assessed for changes in mean heart rate and body weight during the study period. We found a significant reduction in mean heart rate in both group A and B compared with baseline (p&amp;lt;-0.05). The patients aged under 50 years old and whose AHI&amp;lt;20 times/hour have higher ratio of dropout CPAP therapy. There was no significant difference between Group A and Group B on the persistency rate of CPAP therapy. Also, no significant association was found between group A and B on the adherence of CPAP. Conclusion We showed the importance of the effect of intervention of medical staff on the adherence of CPAP and heart rate in patients with OSA the consultation after starting CPAP for a while with utilizing tele-monitoring data would be more effective compared with that in person before start using CPAP. Support (if any):

253 Better and faster automatic sleep staging with artificial intelligence

Abstract Introduction Sleep staging of polysomnography (PSG) is a time-consuming task, it requires significant training, and significant variability among scorers is expected. A new software (MEBsleep by Medibio Limited) was developed to automatically perform sleep scoring based on machine learning algorithms. This study aimed to perform an extensive investigation of its agreement with expert sleep technicians. Methods Forty polysomnography recordings of patients that were referred for sleep evaluation to three sleep clinics were retrospectively collected. Three experienced technicians independently staged the recording complying with the scoring rules of the American Academy of Sleep Medicine guidelines. Positive Percent Agreement (PPA), Positive Predictive Value (PPV), and other agreement statistics between the automatic and manual staging, among the staging performed by the three technicians, and their differences were calculated. Bootstrap resampling was used to calculate 95% confidence intervals and statistical significance of the differences. Results Automatic staging took less than two minutes per PSG on a consumer laptop. The automatic staging resulted for the most comparable (PPA difference of N1, N3, and REM; PPV difference of N1, N2, N3, and REM) or statistically significantly more in agreement with the technicians’ staging than the between-technician agreement (PPA difference of N2: 3.90%, 95% bootstrap CI 1.79%-6.01%; PPV difference of Wake: 1.16%, 95% bootstrap CI 0.64%/1.67%), with the sole exception of a partial reduction in the positive percent agreement of the Wake stage (PPA difference of Wake -7.04%, 95% bootstrap CI -10.40%/-3.85%). The automatic staging also demonstrated very high accuracy in an indirect comparison with other similar software. Conclusion Given these promising results, the use of this software may support sleep clinicians by improving efficiency in sleep scoring. Support (if any):

Are there sex-related differences in therapeutic CPAP levels in adults undergoing in-laboratory titration?

The first-choice therapy for adults with moderate/severe obstructive sleep apnea is continuous positive airway pressure (CPAP). However, studies evaluating whether the therapeutic CPAP level obtained from a titration is affected by sex are surprisingly scarce. Our main objective was to verify if sex influenced the optimal CPAP measurement obtained during a titration. This cross-sectional study was conducted in adults diagnosed with moderate/severe obstructive sleep apnea [baseline apnea-hypopnea index (AHI) ≥ 15.0 events/h] who underwent auto-adjusting CPAP titration (S9 or S10 AutoSet ResMed) in a sleep laboratory setting. All participants used a nasal mask during the titration. The optimal pressure, leak, and residual AHI values were registered. Multiple linear regression was used to evaluate if clinical and polysomnographic data influenced the therapeutic CPAP level setting (95th percentile pressure). A total of 1,006 adults were enrolled: 354 women and 652 men. There were no statistically significant sex-related differences in the CPAP requirements and leak values delineated during the titration; all P-values > .005. However, the median residual AHI was significantly higher in males vs females: 2.7 events/h vs 2.2 events/h (P = .008). Body mass index (β: 0.292, P < .001), baseline AHI (β: 0.167, P < .001), and age (β: 0.065, P = .035) were independent predictors of the therapeutic CPAP level settings. Sex does not significantly influence the therapeutic CPAP settings. However, age, BMI, and baseline AHI emerge as independent predictors of the 95thpercentile CPAP requirement during an auto-adjusting CPAP titration. Duarte RLM, Magalhães-da-Silveira FJ, Gozal D. Are there sex-related differences in therapeutic CPAP levels in adults undergoing in-laboratory titration? JClin Sleep Med. 2021;17(9):1815-1820.

Real-time prediction of upcoming respiratory events via machine learning using snoring sound signal.

The aim of the study was to inspect the acoustic properties and sleep characteristics of a preapneic snoring sound. The feasibility of forecasting upcoming respiratory events by snoring sound was also investigated. Participants with habitual snoring or a heavy breathing sound during sleep were recruited consecutively. Polysomnography was conducted, and snoring-related breathing sound was recorded simultaneously. Acoustic features and sleep features were extracted from 30-second samples, and a machine learning algorithm was used to establish 2 prediction models. A total of 74 eligible participants were included. Model 1, tested by 5-fold cross-validation, achieved an accuracy of 0.92 and an area under the curve of 0.94 for respiratory event prediction. Model 2, with acoustic features and sleep information tested by Leave-One-Out cross-validation, had an accuracy of 0.78 and an area under the curve of 0.80. Sleep position was found to be the most important among all sleep features contributing to the performance of the 2 models. Preapneic sound presented unique acoustic characteristics, and snoring-related breathing sound could be deployed as a real-time apneic event predictor. The models, combined with sleep information, serve as a promising tool for an early warning system to forecast apneic events. Wang B, Yi X, Gao J, etal. Real-time prediction of upcoming respiratory events via machine learning using snoring sound signal. J Clin Sleep Med. 2021;17(9):1777-1784.

Night-to-night variability in obstructive sleep apnea using peripheral arterial tonometry: a case for multiple night testing.

Night-to-night variability of obstructive sleep apnea severity is considerable and may depend on the diagnostic modality used. We investigated the night-to-night variability using peripheral arterial tonometry (PAT). Home sleep apnea testing was performed in 51 patients during 3 consecutive nights using PAT. Patients referred to our sleep clinic were screened and prospectively recruited for this study. All recordings were automatically and manually scored according to the PAT scoring guidelines. No systematic differences in PAT-derived apnea-hypopnea index (pAHI) were found between the nights. The night-to-night variability was comparable between manually and automatically scored data. pAHI varied in 35% of patients more than 10 events/h between the nights. The obstructive sleep apnea severity of 24% of patients was misclassified when using 1 night compared to the average of all nights. On average, pAHI varied by 57% from night to night. The variability of pAHI could partially be explained by the variability of time spent in the supine position with more time supine leading to a higher pAHI. On measuring a subsequent night, 12-14% of patients spontaneously fulfilled the commonly accepted criteria for treatment success without any intervention. With repeated recordings of PAT, we found no first night effect. However, there is considerable night-to-night variability similar to values found for polysomnography, which can partially be explained by the variability of time spent in the supine position. Obstructive sleep apnea severity was frequently misclassified due to the night-to-night variability. Our findings make a strong case for multiple testing in the diagnostic work-up of obstructive sleep apnea patients. Tschopp S, Wimmer W, Caversaccio M, Borner U, Tschopp K. Night-to-night variability in obstructive sleep apnea using peripheral arterial tonometry: a case for multiple night testing. J Clin Sleep Med. 2021;17(9):1751-1758.

A protocol for mitigating safety events in a sleep laboratory.

Polysomnography is a common outpatient procedure and the rate of adverse events is considered low. Due to the emergence and use of home sleep apnea testing, the patient population presenting for in-laboratory testing may have greater medical complexity, suggesting greater risk for in-laboratory adverse events. We believe that there is a greater need for standardized protocols to triage medically vulnerable populations and for formalized training of sleep technicians to respond to safety events. The sleep laboratories affiliated with the Beth Israel Deaconess Medical Center system developed a referral triage protocol for patients undergoing polysomnography and a training protocol for sleep technicians with a formalized response to medical incidents. Safety events occurring from January 2016 to January 2020 were documented and patient demographics, referral characteristics, event characteristics, and outcomes were analyzed. Sixty-five safety events occurred over this period, with a rate of 1:147 studies. The most common events were chest pain (20/65, 31%), shortness of breath (13/65, 20%), and vital sign abnormalities (12/65, 18%). Patients experiencing events were 49% (32/65) female, with a median age of 57 years (range, 19-91 years); 60 of 65 (92%) had documented medical comorbidities, with a median of 3 documented medical or psychiatric comorbidities (range, 0-9). With the formalized response protocol, the time from incident identification to activation of the appropriate response was a median of 3 minutes (range, 0-47 minutes). The incidence of in-laboratory safety events may be greater than previously described due to the widespread use of home sleep apnea testing. Implementation of formalized response protocols and sleep technician training may be necessary to meet the needs of an increasingly medically complex population.

Comparing respiratory polygraphy with pulse transit time analysis versus overnight polysomnography in the diagnosis of obstructive sleep apnoea in children

ObjectiveObstructive sleep apnea syndrome in children is associated with significant morbidity. Polysomnography is the main diagnostic tool but is time consuming and requires skilled manpower to supervise the patient overnight and hence long referral to diagnosis time. However, there are limitations and underestimation of the apnoea hyponea index (AHI) with alternative home sleep apnoea testing (HSAT), such as type 3 respiratory polygraphy (RP). Prior studies have demonstrated pulse transit time (PTT) to be a reliable indicator of cortical arousals. In this study, the use of PTT together with RP will be studied to determine whether the derived AHI is comparable to that of PSG. MethodForty-five patients with suspected OSA met the inclusion criteria underwent PSG in the sleep laboratory for analysis. The raw data for either PSG or RP analysis were allocated separately to two different accredited sleep technicians. The primary outcome AHI derived from PTT with RP was compared to the AHI derived from PSG. Secondary outcomes compared were obstructive apnoea index (OAI), total hypopnoea index (THI) and arousal index (AI). Bland Altman analysis was used to compare the agreement of AHI derived from the 2 modalities and demonstrate whether RP is non inferior or equivalent to the gold standard for diagnosing OSAS. ResultsThe patients studied had a median age of 8.8 years (range 3–17 years). The patients were not limited to certain spectrum of severity OSA and had AHI results spread from mild to severe OSA (AHI 0.4/hr to 72.2/hr). The RP with PTT-derived AHI was strongly correlated to the PSG derived AHI as seen on the Spearman plot (r = 0.98). The Bland Altman plot showed no evidence of underestimation of the AHI due to missed arousal related hypopneas. The difference of AHI derived from RP and PSG results were clinically insignificant. The differences between the PSG and RP total hypopnoea index (THI) and arousal index (AI) were also statistically insignificant. ConclusionThe study shows that RP with PTT can be considered a reliable diagnostic alternative compared with PSG. The role of PTT incorporated with RP was to minimize underestimation of AHI due to missed arousal associated hypopnea events. The results were apparent across mild to severe severity of OSA. There are advantages of RPs particularly in paediatrics. Overall this study offers promising preliminary insights that RP incorporated with PTT can be further explored as an acceptable home diagnostic tool for diagnosing OSA in children.