Automated Detection of Sleep Apnea and Hypopnea Events Based on Robust Airflow Envelope Tracking in the Presence of Breathing Artifacts

Ciolek, Marcin; Niedźwiecki, Maciej; Sieklicki, Stefan; Drozdowski, Jacek; Siebert, Janusz

doi:10.1109/jbhi.2014.2325997

Cited by 37 publications

(24 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the recent years, several studies have focused on automated detection of sleep apnea events based exclusively on the analysis of a single respiratory signal. Many studies used the thermal oronasal airflow sensors to build classical machine learning methods [ 34 , 38 , 39 , 40 , 41 , 44 , 74 , 75 , 76 ] while others used the nasal pressure signal [ 11 , 17 , 35 , 43 , 45 , 77 , 78 , 79 , 80 , 81 ]. Although being much less widely explored, the use of respiratory wearable belts in automated detection of sleep apnea also showed very good results [ 73 , 82 , 83 , 84 , 85 ].…”

Section: Discussionmentioning

confidence: 99%

“…Then, robust classifiers were used to discriminate between the classes of apnea and non-apnea segments. Examples of classification algorithms that have been used with respiratory signals include threshold-based detectors [ 34 , 35 , 36 , 37 , 38 ], support vector machines (SVM) [ 39 , 40 ], artificial neural networks (ANN) [ 41 , 42 , 43 , 44 ], as well as linear discriminant analysis (LDA) combined with regression trees (CART) and the boosting algorithm AdaBoost (AB) [ 45 ].…”

Section: Background and Problem Statementmentioning

confidence: 99%

See 1 more Smart Citation

Deep Recurrent Neural Networks for Automatic Detection of Sleep Apnea from Single Channel Respiration Signals

ElMoaqet

Eid

Glos

et al. 2020

Sensors

View full text Add to dashboard Cite

Sleep apnea is a common sleep disorder that causes repeated breathing interruption during sleep. The performance of automated apnea detection methods based on respiratory signals depend on the signals considered and feature extraction methods. Moreover, feature engineering techniques are highly dependent on the experts’ experience and their prior knowledge about different physiological signals and conditions of the subjects. To overcome these problems, a novel deep recurrent neural network (RNN) framework is developed for automated feature extraction and detection of apnea events from single respiratory channel inputs. Long short-term memory (LSTM) and bidirectional long short-term memory (BiLSTM) are investigated to develop the proposed deep RNN model. The proposed framework is evaluated over three respiration signals: Oronasal thermal airflow (FlowTh), nasal pressure (NPRE), and abdominal respiratory inductance plethysmography (ABD). To demonstrate our results, we use polysomnography (PSG) data of 17 patients with obstructive, central, and mixed apnea events. Our results indicate the effectiveness of the proposed framework in automatic extraction for temporal features and automated detection of apneic events over the different respiratory signals considered in this study. Using a deep BiLSTM-based detection model, the NPRE signal achieved the highest overall detection results with true positive rate (sensitivity) = 90.3%, true negative rate (specificity) = 83.7%, and area under receiver operator characteristic curve = 92.4%. The present results contribute a new deep learning approach for automated detection of sleep apnea events from single channel respiration signals that can potentially serve as a helpful and alternative tool for the traditional PSG method.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Background and Problem Statementmentioning

confidence: 99%

Deep Recurrent Neural Networks for Automatic Detection of Sleep Apnea from Single Channel Respiration Signals

ElMoaqet

Eid

Glos

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…The standard way to diagnose sleep apnea is polysomnography (PSG), this test includes direct observation of the patient, along with electroencephalogram (EEG) control hypertension, breathing rhythm, heart rhythm, oxygen saturation, eye movements and muscles' electric actions. This test is used to discriminate central, obstructive or mixed apnea and calculates the apnea-hypopnea index by dividing the sum of apneas by the hours of sleep [11]. However, this device is too costly and its interpretation requires experts and it is not available everywhere [12].…”

Section: Introductionmentioning

confidence: 99%

Determination of Sleep Apnea Severity Using Multi-Layer Perceptron Neural Network

2020

View full text Add to dashboard Cite

“…Apnoea events in standard sleep studies are readily recognised by human-based scoring and some machine-learning-based apnoea-detectors [61][62][63][64] simply by gross reductions in airflow. These automated apnoea detectors typically work by identifying changes in respiratory activity at the event level, and as such, are optimised for estimating the AHI, for which they achieve moderate to high success [65].…”

Section: Evaluation Of Physiological Signals In Advanced Sleep Studiesmentioning

confidence: 99%

“…The traditional assessment of sleep studies relies upon manual scoring of events, where a trained expert scorer utilises information from multiple associated channels within a polysomnogram, and in conjunction with deductive reasoning, can identify and label relevant events. Experimental machinebased alternatives to traditional sleep scoring are being developed with algorithms that are excellent at objective pattern recognition [62,65,204]. However, they are limited by their training experience and inability to extrapolate sensibly outside these bounds [205].…”

Section: Evaluation Of Airflow Obstruction Measures With Manual Scoringmentioning

confidence: 99%

Developing methods to quantify the severity of airflow obstruction in the clinical sleep environment

Mann¹

View full text Add to dashboard Cite

Obstructive sleep apnoea (OSA) is a significant public health problem, with comorbidities including excessive daytime sleepiness, increased risk of motor vehicle accidents, cardiovascular disease, cognitive impairment, and decreased quality of life. OSA is characterised by intermittent periods of pharyngeal obstruction resulting in the absence (apnoea) or reduction (hypopnoea) of airflow during sleep. OSA severity is currently reported by the apnoea-hypopnoea index (AHI): the frequency of apnoeas and hypopnoeas per hour of sleep. However, the AHI is a poor predictor of an individual's day to day performance, symptomology and long-term health outcomes. This is likely due to a limitation with the event-based AHI, which inadequately describes the underlying neuro-mechanical airway resistance that leads to pharyngeal obstruction, and as such, does not capture the severity of airflow obstruction. Therefore, the overarching goal of this thesis is to develop non-invasive methods to objectively characterise the severity of airflow obstruction on a breath-by-breath basis. Previous literature has identified characteristics within the airflow signal that may indicate airflow obstruction. However, analysis of these features on a breath-by-breath basis requires accurate demarcation of "breath timing" (i.e. inspiratory and expiratory phases). As such, the first aim of this thesis was to develop methods that accurately demarcate breaths. We segmented breaths into inspiratory (TI, shortest period achieving 95% inspiratory volume), expiratory (TE, shortest period achieving 95% expiratory volume), and an inter-breath transition period (TTrans, the period between TE and subsequent TI). In a cohort of 37 patients with an epiglottic pressure catheter, we observed that compensatory increases in the inspiratory period (1.57±0.27 vs 1.74±0.27 seconds, mean±SD, P≤0.001) from reference breaths to partial airway obstruction (identified by increasing epiglottic pressure swings without increasing airflow) were primarily explained by reductions in the inter-breath transition period (0.82±0.28 vs 0.59±0.21 seconds, mean±SD, P≤0.001) and not by reduction of the expiratory airflow period (1.68±0.32 vs 1.60±0.25 seconds, mean±SD, P≤0.05). In addition to developing a method for demarcating breaths, we also identify TTrans as a novel feature associated with increased airway obstruction. Using our newly developed breath timing method in conjunction with the other known markers of flow limitation, we then aimed to characterise the flow shape of individual breaths to develop a transparent machine learning strategy for the non-invasive quantification of the severity of airflow iii obstruction. We defined gold-standard obstruction severity as the ratio of oronasal pneumotach (flow) and ventilatory drive (calibrated intra-oesophageal diaphragm EMG, drive), presented as a continuous breath-by-breath variable, flow:drivemeasured. Multivariable linear regression used noninvasive flow-shape features (inspiratory/expiratory timing, flatness, scooping, flutter...

show abstract

Automated Detection of Sleep Apnea and Hypopnea Events Based on Robust Airflow Envelope Tracking in the Presence of Breathing Artifacts

Cited by 37 publications

References 34 publications

Deep Recurrent Neural Networks for Automatic Detection of Sleep Apnea from Single Channel Respiration Signals

Deep Recurrent Neural Networks for Automatic Detection of Sleep Apnea from Single Channel Respiration Signals

Determination of Sleep Apnea Severity Using Multi-Layer Perceptron Neural Network

Developing methods to quantify the severity of airflow obstruction in the clinical sleep environment

Contact Info

Product

Resources

About