scholarly journals Estimating a Sleep Apnea Hypopnea Index Based on the ERB Correlation Dimension of Snore Sounds

2021 ◽  
Vol 2 ◽  
Author(s):  
Limin Hou ◽  
Qiang Pan ◽  
Hongliang Yi ◽  
Dan Shi ◽  
Xiaoyu Shi ◽  
...  
Keyword(s):  
Sleep Apnea ◽  
Correlation Dimension ◽  
Gaussian Mixture Models ◽  
Training Group ◽  
Gaussian Mixture ◽  
Apnea Hypopnea Index ◽  
Effective Parameters ◽  
Snore Sounds ◽  
Severity Levels ◽  
New Perspective

This paper proposes a new perspective of analyzing non-linear acoustic characteristics of the snore sounds. According to the ERB (Equivalent Rectangular Bandwidth) scale used in psychoacoustics, the ERB correlation dimension (ECD) of the snore sound was computed to feature different severity levels of sleep apnea hypopnea syndrome (SAHS). For the training group of 93 subjects, snore episodes were manually segmented and the ECD parameters of the snores were extracted, which established the gaussian mixture models (GMM). The nocturnal snore sound of the testing group of another 120 subjects was tested to detect SAHS snores, thus estimating the apnea hypopnea index (AHI), which is called AHIECD. Compared to the AHIPSG value of the gold standard polysomnography (PSG) diagnosis, the estimated AHIECD achieved an accuracy of 87.5% in diagnosis the SAHS severity levels. The results suggest that the ECD vectors can be effective parameters for screening SAHS.

scholarly journals Gaussian Mixture Models for Detecting Sleep Apnea Events Using Single Oronasal Airflow Record

2020 ◽  
Vol 10 (21) ◽  
pp. 7889
Author(s):  
Hisham ElMoaqet ◽  
Jungyoon Kim ◽  
Dawn Tilbury ◽  
Satya Krishna Ramachandran ◽  
Mutaz Ryalat ◽  
...  
Keyword(s):  
Sleep Apnea ◽  
Probability Model ◽  
Gaussian Mixture Models ◽  
Gaussian Mixture ◽  
Cerebrovascular Diseases ◽  
Apnea Hypopnea Index ◽  
Related Disorder ◽  
Machine Learning Classification ◽  
Obstructive Sleep ◽  
Rule Based Classifier

Sleep apnea is a common sleep-related disorder that significantly affects the population. It is characterized by repeated breathing interruption during sleep. Such events can induce hypoxia, which is a risk factor for multiple cardiovascular and cerebrovascular diseases. Polysomnography, the gold standard, is expensive, inaccessible, uncomfortable and an expert technician is needed to score sleep-related events. To address these limitations, many previous studies have proposed and implemented automatic scoring processes based on fewer sensors and machine learning classification algorithms. However, alternative device technologies developed for both home and hospital still have limited diagnostic accuracy for detecting apnea events even though many of the previous investigational algorithms are based on multiple physiological channel inputs. In this paper, we propose a new probabilistic algorithm based on (only) oronasal respiration signal for automated detection of apnea events during sleep. The proposed model leverages AASM recommendations for characterizing apnea events with respect to dynamic changes in the local respiratory airflow baseline. Unlike classical threshold-based classification models, we use a Gaussian mixture probability model for detecting sleep apnea based on the posterior probabilities of the respective events. Our results show significant improvement in the ability to detect sleep apnea events compared to a rule-based classifier that uses the same classification features and also compared to two previously published studies for automated apnea detection using the same respiratory flow signal. We use 96 sleep patients with different apnea severity levels as reflected by their Apnea-Hypopnea Index (AHI) levels. The performance was not only analyzed over obstructive sleep apnea (OSA) but also over other types of sleep apnea events including central and mixed sleep apnea (CSA, MSA). Also the performance was comprehensively analyzed and evaluated over patients with varying disease severity conditions, where it achieved an overall performance of TPR=88.5%, TNR=82.5%, and AUC=86.7%. The proposed approach contributes a new probabilistic framework for detecting sleep apnea events using a single airflow record with an improved capability to generalize over different apnea severity conditions

A Comparison of Each Sleep Stage Autonomic Nervous System Activity in Different Sleep Apnea Severity Levels

2020 ◽  
Vol 10 (6) ◽  
pp. 1274-1280
Author(s):  
Yung-Ming Chung ◽  
Shyh-Liang Lou ◽  
Peng-Zhe Tsai ◽  
Ming-Chen Wang ◽  
Liang-Wen Hang
Keyword(s):  
Nervous System ◽  
Autonomic Nervous System ◽  
Sleep Apnea ◽  
Eye Movement ◽  
Sleep Stage ◽  
Public Health Issue ◽  
Sleep Stages ◽  
Apnea Hypopnea Index ◽  
Autonomic Nervous ◽  
Severity Levels

Sleep apnea has increasingly become a public health issue. To further elucidate the physiological changes in different sleep apnea severity levels, we analyzed the autonomic nervous system (ANS) activity in each sleep stage by heart rate variability (HRV), moreover, we clarified how sleep apnea severity affects hypnogram and sleep quality. Subjects used in this study was obtained from PhysioNet, and the patient data were grouped into mild, moderate, and severe levels of sleep apnea according to apnea–hypopnea index (AHI). The electrocardiogram readings during the period of free apnea were extracted and evaluated by HRV and represented to the sleep stages as follows: Awake, rapid eye movement (REM), and nonrapid eye movement (NREM) in different sleep apnea levels, respectively. The results indicated that the severe group (AHI ≥ 30 events per hour) has higher sympathetic nervous system (SNS) activity and lower parasympathetic nervous system (PNS) activity in NREM. This elevates the ANS tone in NREM similar to Awake, making the ANS activity between NREM and Awake indistinguishable. Furthermore, we evaluated the effects both with (w/) and without (w/o) apnea events in REM and NREM separately. Apnea events that occurred in REM (w/) were not different compared to those in REM (w/o). On the other hand, apnea events occurring in NREM (w/) activated SNS and suppressed PNS activity. This altered the ANS tone, which suggested an early sleep stage transition to REM or Awake. This study indicates how sleep apnea severity correlates to the imbalance of ANS activity and it might disrupt the normal hypnogram. Consequently, from the ANS point of view that patients with severe apnea do not get appropriate rest from sleeping, these patients need some medical interventions or treatment to prevent the development of chronic diseases.

Improvement in Obstructive Sleep Apnea (OSA) in Super Morbidly Obese Patients After Bariatric Surgery

2020 ◽  
Vol 103 (8) ◽  
pp. 725-728
Keyword(s):  
Bariatric Surgery ◽  
Obstructive Sleep Apnea ◽  
Sleep Apnea ◽  
Lifestyle Modification ◽  
Apnea Hypopnea Index ◽  
Morbidly Obese ◽  
Obese Patients ◽  
Obstructive Sleep ◽  
Objective Evidence

Background: Lifestyle modification is the mainstay therapy for obese patients with obstructive sleep apnea (OSA). However, most of these patients are unable to lose the necessary weight, and bariatric surgery (BS) has been proven to be an effective modality in selected cases. Objective: To provide objective evidence that BS can improve OSA severity. Materials and Methods: A prospective study was conducted in super morbidly obese patients (body mass index [BMI] greater than 40 kg/m² or BMI greater than 35 kg/m² with uncontrolled comorbidities) scheduled for BS. Polysomnography (PSG) was performed for preoperative assessment and OSA was treated accordingly. After successful surgery, patients were invited to perform follow-up PSG at 3, 6, and 12 months. Results: Twenty-four patients with a mean age of 35.0±14.0 years were enrolled. After a mean follow-up period of 7.8±3.4 months, the mean BMI, Epworth sleepiness scale (ESS), and apnea-hypopnea index (AHI) significantly decreased from 51.6±8.7 to 38.2±6.8 kg/m² (p<0.001), from 8.7±5.9 to 4.7±3.5 (p=0.003), and from 87.6±38.9 to 28.5±21.5 events/hour (p<0.001), respectively. Conclusion: BS was shown to dramatically improve clinical and sleep parameters in super morbidly obese patients. Keywords: Morbid obesity, Bariatric surgery, Obstructive sleep apnea (OSA)

Aerodynamics Analysis of the Impact of Nasal Surgery on Patients with Obstructive Sleep Apnea and Nasal Obstruction

ORL ◽  
2021 ◽  
pp. 1-8
Author(s):  
Lifeng Li ◽  
Demin Han ◽  
Hongrui Zang ◽  
Nyall R. London
Keyword(s):  
Obstructive Sleep Apnea ◽  
Sleep Apnea ◽  
Nasal Obstruction ◽  
Upper Airway ◽  
Apnea Hypopnea Index ◽  
Nasal Surgery ◽  
Subjective Sleep Quality ◽  
Obstructive Sleep ◽  
Significant Difference ◽  
The Impact

<b><i>Objective:</i></b> The purpose of this study was to evaluate the effects of nasal surgery on airflow characteristics in patients with obstructive sleep apnea (OSA) by comparing the alterations of airflow characteristics within the nasal and palatopharyngeal cavities. <b><i>Methods:</i></b> Thirty patients with OSA and nasal obstruction who underwent nasal surgery were enrolled. A pre- and postoperative 3-dimensional model was constructed, and alterations of airflow characteristics were assessed using the method of computational fluid dynamics. The other subjective and objective clinical indices were also assessed. <b><i>Results:</i></b> By comparison with the preoperative value, all postoperative subjective symptoms statistically improved (<i>p</i> &#x3c; 0.05), while the Apnea-Hypopnea Index (AHI) changed little (<i>p</i> = 0.492); the postoperative airflow velocity and pressure in both nasal and palatopharyngeal cavities, nasal and palatopharyngeal pressure differences, and total upper airway resistance statistically decreased (all <i>p</i> &#x3c; 0.01). A significant difference was derived for correlation between the alteration of simulation metrics with subjective improvements (<i>p</i> &#x3c; 0.05), except with the AHI (<i>p</i> &#x3e; 0.05). <b><i>Conclusion:</i></b> Nasal surgery can decrease the total resistance of the upper airway and increase the nasal airflow volume and subjective sleep quality in patients with OSA and nasal obstruction. The altered airflow characteristics might contribute to the postoperative reduction of pharyngeal collapse in a subset of OSA patients.

scholarly journals High Plasma Cystine Levels Are Associated with Blood Pressure and Reversed by CPAP in Patients with Obstructive Sleep Apnea

2021 ◽  
Vol 10 (7) ◽  
pp. 1387
Author(s):  
Raphael Boneberg ◽  
Anita Pardun ◽  
Lena Hannemann ◽  
Olaf Hildebrandt ◽  
Ulrich Koehler ◽  
...  
Keyword(s):  
Blood Pressure ◽  
Obstructive Sleep Apnea ◽  
Sleep Apnea ◽  
Mononuclear Cells ◽  
Vascular Risk Factor ◽  
High Plasma ◽  
Apnea Hypopnea Index ◽  
Hypoxic Stress ◽  
Peripheral Blood Mononuclear ◽  
Obstructive Sleep

Obstructive sleep apnea (OSA) independent of obesity (OBS) imposes severe cardiovascular risk. To what extent plasma cystine concentration (CySS), a novel pro-oxidative vascular risk factor, is increased in OSA with or without OBS is presently unknown. We therefore studied CySS together with the redox state and precursor amino acids of glutathione (GSH) in peripheral blood mononuclear cells (PBMC) in untreated male patients with OSA (apnea-hypopnea-index (AHI) > 15 h−1, n = 28) compared to healthy male controls (n = 25) stratifying for BMI ≥ or < 30 kg m−2. Fifteen OSA patients were reassessed after 3–5-months CPAP. CySS correlated with cumulative time at an O2-saturation <90% (Tu90%) (r = 0.34, p < 0.05) beside BMI (r = 0.58, p < 0.001) and was higher in subjects with “hypoxic stress” (59.4 ± 2.0 vs. 50.1 ± 2.7 µM, p < 0.01) defined as Tu90% ≥ 15.2 min (corresponding to AHI ≥ 15 h−1). Moreover, CySS significantly correlated with systolic (r = 0.32, p < 0.05) and diastolic (r = 0.31, p < 0.05) blood pressure. CPAP significantly lowered CySS along with blood pressure at unchanged BMI. Unexpectedly, GSH antioxidant capacity in PBMC was increased with OSA and reversed with CPAP. Plasma CySS levels are increased with OSA-related hypoxic stress and associated with higher blood pressure. CPAP decreases both CySS and blood pressure. The role of CySS in OSA-related vascular endpoints and their prevention by CPAP warrants further studies.

scholarly journals Detecting Apnea/Hypopnea Events Time Location from Sound Recordings for Patients with Severe or Moderate Sleep Apnea Syndrome

2021 ◽  
Vol 11 (15) ◽  
pp. 6888
Author(s):  
Georgia Korompili ◽  
Lampros Kokkalas ◽  
Stelios A. Mitilineos ◽  
Nicolas-Alexander Tatlas ◽  
Stelios M. Potirakis
Keyword(s):  
Sleep Apnea ◽  
Sleep Apnea Syndrome ◽  
Apnea Hypopnea Index ◽  
Event Time ◽  
Severity Estimation ◽  
Apnea Duration ◽  
Respiratory Events ◽  
Moderate Sensitivity ◽  
Apnea Syndrome

The most common index for diagnosing Sleep Apnea Syndrome (SAS) is the Apnea-Hypopnea Index (AHI), defined as the average count of apnea/hypopnea events per sleeping hour. Despite its broad use in automated systems for SAS severity estimation, researchers now focus on individual event time detection rather than the insufficient classification of the patient in SAS severity groups. Towards this direction, in this work, we aim at the detection of the exact time location of apnea/hypopnea events. We particularly examine the hypothesis of employing a standard Voice Activity Detection (VAD) algorithm to extract breathing segments during sleep and identify the respiratory events from severely altered breathing amplitude within the event. The algorithm, which is tested only in severe and moderate patients, is applied to recordings from a tracheal and an ambient microphone. It proves good sensitivity for apneas, reaching 81% and 70.4% for the two microphones, respectively, and moderate sensitivity to hypopneas—approx. 50% were identified. The algorithm also presents an adequate estimator of the Mean Apnea Duration index—defined as the average duration of the detected events—for patients with severe or moderate apnea, with mean error 1.7 s and 3.2 s for the two microphones, respectively.

scholarly journals Analysis of nocturnal desaturation waveforms using algorithms in patients with idiopathic pulmonary fibrosis

2021 ◽  
Author(s):  
Yuichiro Yasuda ◽  
Tatsuya Nagano ◽  
Shintaro Izumi ◽  
Mina Yasuda ◽  
Kosuke Tsuruno ◽  
...  
Keyword(s):  
Sleep Apnea ◽  
Idiopathic Pulmonary Fibrosis ◽  
Pulmonary Fibrosis ◽  
Diagnostic Algorithm ◽  
Sleep Time ◽  
Periodic Pattern ◽  
Apnea Hypopnea Index ◽  
Apnea Test ◽  
Eligibility Criteria ◽  
Obstructive Sleep

Abstract Purpose Sleep-disordered breathing is recognized as a comorbidity in patients with idiopathic pulmonary fibrosis (IPF). Among them, nocturnal hypoxemia has been reported to be associated with poor prognosis and disease progression. We developed a diagnostic algorithm to classify nocturnal desaturation from percutaneous oxygen saturation (SpO2) waveform patterns: sustained pattern, periodic pattern, and intermittent pattern. We then investigated the prevalence of nocturnal desaturation and the association between the waveform patterns of nocturnal desaturation and clinical findings of patients with IPF. Methods We prospectively enrolled patients with IPF from seven general hospitals between April 2017 and March 2020 and measured nocturnal SpO2 and nasal airflow by using a home sleep apnea test. An algorithm was used to classify the types of nocturnal desaturation. We evaluated the association between sleep or clinical parameters and each waveform pattern of nocturnal desaturation. Results Among 60 patients (47 men) who met the eligibility criteria, there were 3 cases with the sustained pattern, 49 cases with the periodic pattern, and 41 cases with the intermittent pattern. Lowest SpO2 during sleep and total sleep time spent with SpO2 < 90% were associated with the sustained pattern, and apnea–hypopnea index was associated with the intermittent pattern. Conclusion We demonstrated the prevalence of each waveform and association between each waveform and sleep parameters in patients with IPF. This classification algorithm may be useful to predict the degree of hypoxemia or the complication of obstructive sleep apnea.

scholarly journals Measure of Similarity between GMMs by Embedding of the Parameter Space That Preserves KL Divergence

Mathematics ◽  
2021 ◽  
Vol 9 (9) ◽  
pp. 957
Author(s):  
Branislav Popović ◽  
Lenka Cepova ◽  
Robert Cep ◽  
Marko Janev ◽  
Lidija Krstanović
Keyword(s):  
Computational Complexity ◽  
Parameter Space ◽  
Recognition Accuracy ◽  
Gaussian Mixture Models ◽  
Gaussian Mixture ◽  
Dimensional Manifold ◽  
Dimensional Parameter ◽  
Trade Off ◽  
Measure Of Similarity ◽  
Lower Dimensional

In this work, we deliver a novel measure of similarity between Gaussian mixture models (GMMs) by neighborhood preserving embedding (NPE) of the parameter space, that projects components of GMMs, which by our assumption lie close to lower dimensional manifold. By doing so, we obtain a transformation from the original high-dimensional parameter space, into a much lower-dimensional resulting parameter space. Therefore, resolving the distance between two GMMs is reduced to (taking the account of the corresponding weights) calculating the distance between sets of lower-dimensional Euclidean vectors. Much better trade-off between the recognition accuracy and the computational complexity is achieved in comparison to measures utilizing distances between Gaussian components evaluated in the original parameter space. The proposed measure is much more efficient in machine learning tasks that operate on large data sets, as in such tasks, the required number of overall Gaussian components is always large. Artificial, as well as real-world experiments are conducted, showing much better trade-off between recognition accuracy and computational complexity of the proposed measure, in comparison to all baseline measures of similarity between GMMs tested in this paper.

Sign in / Sign up

Export Citation Format

Share Document