Sleep Apnea Detection from Single-Lead ECG Using Features Based on ECG-Derived Respiration (EDR) Signals

A Comprehensive Study on a Deep-Learning-Based Electrocardiography Analysis for Estimating the Apnea-Hypopnea Index

This study introduces a deep-learning-based automatic sleep scoring system to detect sleep apnea using a single-lead electrocardiography (ECG) signal, focusing on accurately estimating the apnea-hypopnea index (AHI). Unlike other research, this work emphasizes AHI estimation, crucial for the diagnosis and severity evaluation of sleep apnea. The suggested model, trained on 1465 ECG recordings, combines the deep-shallow fusion network for sleep apnea detection network (DSF-SANet) and gated recurrent units (GRUs) to analyze ECG signals at 1-min intervals, capturing sleep-related respiratory disturbances. Achieving a 0.87 correlation coefficient with actual AHI values, an accuracy of 0.82, an F1 score of 0.71, and an area under the receiver operating characteristic curve of 0.88 for per-segment classification, our model was effective in identifying sleep-breathing events and estimating the AHI, offering a promising tool for medical professionals.

The Use of Respiratory Effort Improves an ECG-Based Deep Learning Algorithm to Assess Sleep-Disordered Breathing

BACKGROUND

Sleep apnea is a prevalent sleep-disordered breathing (SDB) condition that affects a large population worldwide. Research has demonstrated the potential of using electrocardiographic (ECG) signals (heart rate and ECG-derived respiration, EDR) to detect SDB. However, EDR may be a suboptimal replacement for respiration signals.

METHODS

We evaluated a previously described ECG-based deep learning algorithm in an independent dataset including 198 patients and compared performance for SDB event detection using thoracic respiratory effort versus EDR. We also evaluated the algorithm in terms of apnea-hypopnea index (AHI) estimation performance, and SDB severity classification based on the estimated AHI.

RESULTS

Using respiratory effort instead of EDR, we achieved an improved performance in SDB event detection (F1 score = 0.708), AHI estimation (Spearman's correlation = 0.922), and SDB severity classification (Cohen's kappa of 0.62 was obtained based on AHI).

CONCLUSION

Respiratory effort is superior to EDR to assess SDB. Using respiratory effort and ECG, the previously described algorithm achieves good performance in a new dataset from an independent laboratory confirming its adequacy for this task.

Accurate Detection of Arrhythmias on Raw Electrocardiogram Images:An Aggregation Attention Multi-label Model for Diagnostic Assistance

BACKGROUND

The low rate of detection of abnormalities has been a major problem with current artificial intelligence-based electrocardiogram diagnostic algorithms, particularly when applied under real-world clinical scenarios.

METHODS

We proposed an aggregation attention multilabel electrocardiogram classification model (AA-ECG) that can be applied directly to raw images to identify cardiac abnormalities using image-level annotation only. To develop and validate the model, we conducted a prospective two-site study to build two large-scale real-world datasets of 12-lead electrocardiogram images, annotated by clinical experts in a multilabeled manner. We compared the proposed model with seven state-of-the-art classifiers on both datasets in 27 main categories.

RESULTS

In total, 47,733 electrocardiogram images from 37,442 consecutive patients were included in the development set, while 18,581 from 18,345 in the external set. The proposed model achieved better overall performance than the other seven models.The visualization of the attention maps provided an approach to build medical interpretability for machine intelligence.

CONCLUSIONS

The proposed model had high diagnostic accuracy in identifying cardiac abnormalities on two real-world datasets. It has the potential to help clinicians provide more efficient cardiac care with fewer medical resources.

A wearable device for at-home obstructive sleep apnea assessment: State-of-the-art and research challenges

In the last 3 years, almost all medical resources have been reserved for the screening and treatment of patients with coronavirus disease (COVID-19). Due to a shortage of medical staff and equipment, diagnosing sleep disorders, such as obstructive sleep apnea (OSA), has become more difficult than ever. In addition to being diagnosed using polysomnography at a hospital, people seem to pay more attention to alternative at-home OSA detection solutions. This study aims to review state-of-the-art assessment techniques for out-of-center detection of the main characteristics of OSA, such as sleep, cardiovascular function, oxygen balance and consumption, sleep position, breathing effort, respiratory function, and audio, as well as recent progress in the implementation of data acquisition and processing and machine learning techniques that support early detection of severe OSA levels.

A Comprehensive Review: Computational Models for Obstructive Sleep Apnea Detection in Biomedical Applications

Obstructive sleep apnea (OSA) is a sleep disorder characterized by periodic episodes of partial or complete upper airway obstruction caused by narrowing or collapse of the pharyngeal airway despite ongoing breathing efforts during sleep. Fall in the blood oxygen saturation and cortical arousals are prompted by this reduction in the airflow which lasts for at least 10 seconds. Impaired labor performance, debilitated quality of life, excessive daytime sleepiness, high snoring, and tiredness even after a whole night's sleep are the primary symptoms of OSA. In due course, the long-standing contributions of OSA culminate in hypertension, arrhythmia, cerebrovascular disease, and heart failure. The traditional diagnostic approach of OSA is the laboratory-based polysomnography (PSG) overnight sleep study, which is a tedious and labor-intensive process that exaggerates the discomfort to the patient. With the advent of computer-aided diagnosis (CAD), automatic detection of OSA has gained increasing interest among researchers in the area of sleep disorders as it influences both diagnostic and therapeutic decisions. The research literature on sleep apnea published during the last decade has been surveyed, focusing on the varied screening approaches accustomed to identifying OSA events and the developmental knowledge offered by multiple contributors from the software perspective. The current study presents an overview of the pathophysiology of OSA, the detection methods, physiological signals related to OSA, the different preprocessing, feature extraction, feature selection, and classification techniques employed for the detection and classification of OSA. Consequently, the research challenges and research gaps in the diagnosis of OSA are identified, critically analyzed, and presented in the best possible light.

Fuzzy Approximate Entropy of Extrema Based on Multiple Moving Averages as a Novel Approach in Obstructive Sleep Apnea Screening

Objective: Obstructive sleep apnea (OSA) is a respiratory disease associated with autonomic nervous system dysfunction. As a novel method for analyzing OSA depending on heart rate variability, fuzzy approximate entropy of extrema based on multiple moving averages (Emma-fApEn) can effectively assess the sympathetic tension limits, thereby realizing a good performance in the disease severity screening. Method: Sixty 6-h electrocardiogram recordings (20 healthy, 16 mild/moderate OSA and 34 severe OSA) from the PhysioNet database were used in this study. The performances of minima of Emma-fApEn (fApEn-minima), maxima of Emma-fApEn (fApEn-maxima) and classic time-frequency domain indices for each recording were assessed by significance analysis, correlation analysis, parameter optimization and OSA screening. Results: fApEn-minima and fApEn-maxima had significant differences between the severe OSA group and the other two groups, while the mean value (Mean) and the ratio of low-frequency power and high-frequency power (LH) could significantly differentiate OSA recordings from healthy recordings. The correlation coefficient between fApEn-minima and apnea-hypopnea index was the highest (|R| = 0.705). Machine learning methods were used to evaluate the performances of the above four indices. Random forest (RF) achieved the highest accuracy of 96.67% in OSA screening and 91.67% in severe OSA screening, with a good balance in both. Conclusion: Emma-fApEn may be used as a simple preliminary detection tool to assess the severity of OSA prior to polysomnography analysis.

Apnea Detection in Polysomnographic Recordings Using Machine Learning Techniques

Sleep disorders are diagnosed in sleep laboratories by polysomnography, a multi-parameter examination that monitors biological signals during sleep. The subsequent evaluation of the obtained records is very time-consuming. The goal of this study was to create an automatic system for evaluation of the airflow and SpO2 channels of polysomnography records, through the use of machine learning techniques and a large database, for apnea and desaturation detection (which is unusual in other studies). To that end, a convolutional neural network (CNN) was designed using hyperparameter optimization. It was then trained and tested for apnea and desaturation. The proposed CNN was compared with the commonly used k-nearest neighbors (k-NN) method. The classifiers were designed based on nasal airflow and blood oxygen saturation signals. The final neural network accuracy for apnea detection reached 84%, and that for desaturation detection was 74%, while the k-NN classifier reached accuracies of 83% and 64% for apnea detection and desaturation detection, respectively.

Classification of sleep apnea using EMD-based features and PSO-trained neural networks

In this study, we propose a method for detecting obstructive sleep apnea (OSA) based on the features extracted from empirical mode decomposition (EMD) and the neural networks trained by particle swarm optimization (PSO) in the classification phase. After extracting the features from the intrinsic mode functions (IMF) of each heart rate variability (HRV) signal of each segment, these features were applied to the input of popular classifiers such as multi-layer perceptron neural networks (MLPNN), Naïve Bayes, linear discriminant analysis (LDA), k-nearest neighborhood (KNN), and support vector machines (SVM) were applied. The results show that the MLPNN learned with back propagation (BP) algorithm has a diagnostic accuracy of less than 90%, and this may be due to being derivative based property of the BP algorithm, which causes trapping in the local minima. For Improving MLPNN's performance, we used the PSO algorithm instead of the BP method in training part. Therefore, the MLPNN's accuracy improved from 89.36 to 97.66% after the application of the PSO algorithm. The proposed method has also reached to 97.78 and 97.96% in sensitivity and specificity, respectively. So, it can be concluded that the proposed method achieves better or comparable results when compared with the previous works in this field.

Technical aspects of cardiorespiratory estimation using subspace projections and cross entropy

BACKGROUND

Respiratory sinus arrhythmia (RSA) is a form of cardiorespiratory coupling. Its quantification has been suggested as a biomarker to diagnose different diseases. Two state-of-the-art methods, based on subspace projections and entropy, are used to estimate the RSA strength and are evaluated in this paper. Their computation requires the selection of a model order, and their performance is strongly related to the temporal and spectral characteristics of the cardiorespiratory signals.

OBJECTIVE

To evaluate the robustness of the RSA estimates to the selection of model order, delays, changes of phase and irregular heartbeats as well as to give recommendations for their interpretation on each case.

APPROACH

Simulations were used to evaluate the model order selection when calculating the RSA estimates explained before, as well as 3 different scenarios that can occur in signals acquired in non-controlled environments and/or from patient populations: the presence of irregular heartbeats; the occurrence of delays between heart rate variability (HRV) and respiratory signals; and the changes over time of the phase between HRV and respiratory signals.

MAIN RESULTS

It was found that using a single model order for all the calculations suffices to characterize the RSA estimates correctly. In addition, the RSA estimation in signals containing more than 5 irregular heartbeats in a period of 5 minutes might be misleading. Regarding the delays between HRV and respiratory signals, both estimates are robust. For the last scenario, the two approaches tolerate phase changes up to 54°, as long as this lasts less than one fifth of the recording duration.

SIGNIFICANCE

Guidelines are given to compute the RSA estimates in non-controlled environments and patient populations.

Classification of Sleep Apnea Based on Sub-Band Decomposition of EEG Signals

To classify between normal and sleep apnea subjects based on sub-band decomposition of electroencephalogram (EEG) signals. This study comprised 159 subjects obtained from the ISRUC (Institute of System and Robotics—University of Coimbra), Sleep-EDF (European Data Format), and CAP (Cyclic Alternating Pattern) Sleep database, which consists of normal and sleep apnea subjects. The wavelet packet decomposition method was incorporated to categorize the EEG signals into five frequency bands, namely, alpha, beta, delta, gamma, and theta. Entropy and energy (non-linear) for all bands was calculated and as a result, 10 features were obtained for each EEG signal. The ratio of EEG bands included four parameters, including heart rate, brain perfusion, neural activity, and synchronization. In this study, a support vector machine with kernels and random forest classifiers was used for classification. The performance measures demonstrated that the improved results were obtained from the support vector machine classifier with a kernel polynomial order 2. The accuracy (90%), sensitivity (100%), and specificity (83%) with 14 features were estimated using the data obtained from ISRUC database. The proposed study is feasible and seems to be accurate in classifying the subjects with sleep apnea based on the extracted features from EEG signals using a support vector machine classifier.

FASSNet: fast apnea syndrome screening neural network based on single-lead electrocardiogram for wearable devices

Objective. Sleep apnea (SA) is a chronic condition that fragments sleep and results in intermittent hypoxemia, which in long run leads to cardiovascular diseases like stroke. Diagnosis of SA through polysomnography is costly, inconvenient, and has long waiting list. Wearable devices provide a low-cost solution to the ambulatory detection of SA syndrome for undiagnosed patients. One of the wearables are the ones based on minute-by-minute analysis of single-lead electrocardiogram (ECG) signal. Processing ECG segments online at wearables contributes to memory conservation and privacy protection in long-term SA monitoring, and light-weight models are required due to stringent computation resource.Approach.We propose fast apnea syndrome screening neural network (FASSNet), an effective end-to-end neural network to perform minute-apnea event detection. Low-frequency components of filtered ECG spectrogram are selected as input. The model initially processes the spectrogram via convolution blocks. Bidirectional long-short-term memory blocks are used along the frequency axis to complement position information of frequency bands. Layer normalisation is implemented to retain in-epoch information since apnea periods have variable lengths. Experiments were carried out on 70 recordings of Apnea-ECG database, where each 60 s ECG segment is manually labelled as an apnea or normal minute by technician. Both ten-fold and patient-agnostic validation protocols are adopted.Main results.FASSNet is light-weighted, since its value of model parameters and multiply accumulates are 0.06% and 28.33% of those of an AlexNet benchmark, respectively. Meanwhile, FASSNet achieves an accuracy of 87.09%, a sensitivity of 77.96%, a specificity of 91.74%, and an F1 score of 81.61% in apnea event detection. Its accuracy of diagnosing SA syndrome severity exceeds 90% under the patient-agnostic protocol.Significance:FASSNet is a computationally efficient and accurate neural network for wearables to detect SA events and estimate SA severity based on minute-level diagnosis.

Obstructive sleep apnea detection using discrete wavelet transform-based statistical features

MOTIVATION AND OBJECTIVE

Obstructive sleep apnea (OSA) is a sleep disorder identified in nearly 10% of middle-aged people, which deteriorates the normal functioning of human organs, notably that of the heart. Furthermore, untreated OSA is associated with increased hypertension, diabetes, stroke, and cardiovascular diseases, thereby increasing the mortality risk. Therefore, early identification of sleep apnea is of significant interest.

METHOD

In this paper, an automated approach for OSA diagnosis using a single-lead electrocardiogram (ECG) has been reported. Three sets of features, namely moments of power spectrum density (PSD), waveform complexity measures, and higher-order moments, are extracted from the 1-min segmented ECG subbands obtained from discrete wavelet transform (DWT). Later, correlation-based feature selection with particle swarm optimization (PSO) search strategy is employed for getting an optimum feature vector. This process retained 18 significant features from initially computed 32 features. Finally, the acquired feature set is fed to different classifiers including, linear discriminant analysis, nearest neighbors, support vector machine, and random forest to perform per segment classification.

RESULTS

Experiments on the publicly available physionet single-lead ECG dataset show that the proposed approach using the random forest classifier effectively discriminates normal and OSA ECG signals. Specifically, our method achieved an accuracy of 89% and 90%, with 50-50 hold-out validation and 10-fold cross-validation, respectively. Besides, in both these validation scenarios, our method obtained 96% of the area under ROC. Importantly, our proposed approach provided better performance results than most of the existing methodologies.

Robust, ECG-based detection of Sleep-disordered breathing in large population-based cohorts

STUDY OBJECTIVES

Up to 5% of adults in Western countries have undiagnosed sleep-disordered breathing (SDB). Studies have shown that electrocardiogram (ECG)-based algorithms can identify SDB and may provide alternative screening. Most studies, however, have limited generalizability as they have been conducted using the apnea-ECG database, a small sample database that lacks complex SDB cases.

METHODS

Here, we developed a fully automatic, data-driven algorithm that classifies apnea and hypopnea events based on the ECG using almost 10 000 polysomnographic sleep recordings from two large population-based samples, the Sleep Heart Health Study (SHHS) and the Multi-Ethnic Study of Atherosclerosis (MESA), which contain subjects with a broad range of sleep and cardiovascular diseases (CVDs) to ensure heterogeneity.

RESULTS

Performances on average were sensitivity(Se)=68.7%, precision (Pr)=69.1%, score (F1)=66.6% per subject, and accuracy of correctly classifying apnea-hypopnea index (AHI) severity score was Acc=84.9%. Target AHI and predicted AHI were highly correlated (R2 = 0.828) across subjects, indicating validity in predicting SDB severity. Our algorithm proved to be statistically robust between databases, between different periodic leg movement index (PLMI) severity groups, and for subjects with previous CVD incidents. Further, our algorithm achieved the state-of-the-art performance of Se=87.8%, Sp=91.1%, Acc=89.9% using independent comparisons and Se=90.7%, Sp=95.7%, Acc=93.8% using a transfer learning comparison on the apnea-ECG database.

CONCLUSIONS

Our robust and automatic algorithm constitutes a minimally intrusive and inexpensive screening system for the detection of SDB events using the ECG to alleviate the current problems and costs associated with diagnosing SDB cases and to provide a system capable of identifying undiagnosed SDB cases.

Automated sleep apnea detection from cardio-pulmonary signal using bivariate fast and adaptive EMD coupled with cross time-frequency analysis

Sleep apnea is a sleep related pathology in which breathing or respiratory activity of an individual is obstructed, resulting in variations in the cardio-pulmonary (CP) activity. The monitoring of both cardiac (heart rate (HR)) and pulmonary (respiration rate (RR)) activities are important for the automated detection of this ailment. In this paper, we propose a novel automated approach for sleep apnea detection using the bivariate CP signal. The bivariate CP signal is formulated using both HR and RR signals extracted from the electrocardiogram (ECG) signal. The approach consists of three stages. First, the bivariate CP signal is decomposed into intrinsic mode functions (IMFs) and residuals for both HR and RR channels using bivariate fast and adaptive empirical mode decomposition (FAEMD). Second, the features are extracted using time-domain analysis, spectral analysis, and time-frequency domain analysis of IMFs from CP signal. The time-frequency domain features are computed from the cross time-frequency matrices of IMFs of CP signal. The cross time-frequency matrix of each IMF is evaluated using the Stockwell (S)-transform. Third, the support vector machine (SVM) and the random forest (RF) classifiers are used for automated detection of sleep apnea with the features from the bivariate CP signal. Our proposed approach has demonstrated an average sensitivity and specificity of 82.27% and 78.67%, respectively for sleep apnea detection using the 10-fold cross-validation method. The approach has yielded an average sensitivity and specificity of 73.19% and 73.13%, respectively for the subject-specific cross-validation. The performance of the approach was compared with other CPC features used for the detection of sleep apnea.

Sleep apnea detection from ECG using variational mode decomposition

Sleep apnea is a pervasive breathing problem during night sleep, and its repetitive occurrence causes various health problems. Polysomnography is commonly used for apnea screening which is an expensive, time-consuming, and complex process. In this paper, a simple but efficient technique based on the variational mode decomposition (VMD) for automated detection of sleep apnea from single-lead ECG is proposed. The heart rate variability and ECG-derived respiration signals obtained from ECG are decomposed into different modes using the VMD, and these modes are used for extracting different features including spectral entropies, interquartile range, and energy. The principal component analysis is employed to reduce the dimension of the feature vector. The experiments are conducted using the Apnea-ECG dataset, and the classification performance of various classifiers is investigated. In per-segment classification, an accuracy of about 87.5% (Sens: 84.9%, Spec: 88.2%) is achieved using the K-nearest neighbor classifier. In per-recording classification, the proposed technique using the linear discriminant analysis model outperformed the existing apnea detection approaches by achieving the accuracy of 100%. The algorithm also provided the best agreement between the estimated and reference apnea-hypopnea index (AHI) values. These results show that the algorithm has the potential to be used for home-based apnea screening systems.

Introducing the Hybrid "K-means, RLS" Learning for the RBF Network in Obstructive Apnea Disease Detection using Dual-tree Complex Wavelet Transform Based Features

Apnea is one of the deadliest diseases that can be prevented and cured if it is detected in time. In this paper, we propose a precise method for early detection of the obstructive sleep apnea (OSA) disease using the latest feature selection and extraction methods. The feature selection in this paper is based on the Dual tree complex wavelet (DT-CWT) coefficients of the ECG signals of several patients. The feature extraction from these coefficients is done using frequency and time techniques. The Feature selection is done using the spectral regression discriminant analysis (SRDA) algorithm and the classification is performed using the hybrid RBF network. A hybrid RBF neural network is introduced in this paper for detecting apnea that is much less computationally demanding than the previously presented SVM networks. Our findings showed a 3 percent improvement in the detection and at least a 30 percent reduction in the computational complexity in comparison with methods that have been presented recently.

A review of fluid-structure interaction simulation for patients with sleep related breathing disorders with obstructive sleep

Obstructive sleep apnea is one of the most common breathing disorders. Undiagnosed sleep apnea is a hidden health crisis to the patient and it could raise the risk of heart diseases, high blood pressure, depression and diabetes. The throat muscle (i.e., tongue and soft palate) relax narrows the airway and causes the blockage of the airway in breathing. To understand this phenomenon computational fluid dynamics method has emerged as a handy tool to conduct the modeling and analysis of airflow characteristics. The comprehensive fluid-structure interaction method provides the realistic visualization of the airflow and interaction with the throat muscle. Thus, this paper reviews the scientific work related to the fluid-structure interaction (FSI) for the evaluation of obstructive sleep apnea, using computational techniques. In total 102 articles were analyzed, each article was evaluated based on the elements related with fluid-structure interaction of sleep apnea via computational techniques. In this review, the significance of FSI for the evaluation of obstructive sleep apnea has been critically examined. Then the flow properties, boundary conditions and validation of the model are given due consideration to present a broad perspective of CFD being applied to study sleep apnea. Finally, the challenges of FSI simulation methods are also highlighted in this article.

A RR interval based automated apnea detection approach using residual network

BACKGROUND AND OBJECTIVE

Apnea is one of the most common conditions that causes sleep-disorder breathing. With growing number of patients worldwide, more and more patients suffer from complications of apnea. But most of them stay untreated due to the complex and time-consuming polysomnography (PSG) diagnosis method. Effective and precise diagnosis support system using electrocardiograph (ECG) is required. In this paper, we propose an approach using residual network to detect apnea based on RR intervals (intervals between R-peaks of ECG signal).

METHODS

In our model, we apply residual network to represent information carried by RR intervals. Moreover, we proposed a novel perspective, called dynamic autoregressive representation, to provide interpretation of representing the RR intervals by convolutional layers.

RESULTS

This approach is tested for per-segment apnea detection using publicly available dataset on Physionet. 30 overnight recordings are used for training and 5 for testing. We achieve a good result of 94.4% accuracy, 93.0% sensitivity and 94.9% specificity. This result outperform other prevalent methods based on RR intervals. This model also shows its good adaptivity while using ECG-derived respiration signal (EDR) in experiments. Its extensiveness is evaluated and compared in experiments. The proposed model is also compared with deep neural networks using original ECG signals for apnea detection, and it achieves better result using fewer input samples.

CONCLUSIONS

We develop a deep residual network to detect apnea on low-sample-rate RR intervals. The result suggests a possibility of representing RR intervals by neural network. The model showed strong adaptivity when using EDR input.