Apnea-ECG Database Research Articles

Sleep Apnea Detection Model Using Time Window and One-Dimensional Convolutional Neural Network on Single-Lead Electrocardiogram

Sleep apnea is an important disorder that involves frequent disruptions in breathing during sleep, which can result in numerous serious health issues, such as cognitive deterioration, cardiovascular illness, and heightened mortality risk. This study introduces a detailed model designed for the detection of sleep apnea using single-lead electrocardiogram signals, providing an accurate detection method. We can use single-lead ECG signals to get ECG-Derived Respiration (EDR). EDR combines important respiratory signals with RR intervals to help find sleep apnea more accurately. We structure the research process into seven systematic stages, ensuring a comprehensive approach to the issue. The process commences with the acquisition of data from the "Apnea-ECG Database" accessible on the PhysioNet platform, which underpins the ensuing analysis. Subsequent to data collection, we execute a sequence of preprocessing procedures, including segmentation, filtering, and R-peak detection, to enhance the ECG data for analysis. After that, we do feature extraction, which gives us 12 unique features from the RR interval and 6 features from the R-peak amplitude, which are both necessary for the model to work. The research subsequently utilizes feature engineering, implementing a Time Window methodology to encapsulate the temporal dynamics of the data. To ensure the results are robust, we conduct model evaluation using stratified K-fold cross-validation with five folds. The modeling technique employs a 1D Convolutional Neural Network (1D-CNN) utilizing the Adam optimizer. Ultimately, the performance assessment shows an accuracy score reaching 89.87%, sensitivity at 86.16%, specificity at 92.30%, and an AUC score of 0.96, attained with a Time Window size of 15. This model signifies a substantial improvement in performance relative to previous studies and serves as a feasible option for the detection of sleep apnea

Determination of Signs of Sleep Apnea Using Machine Learning Methods in Combination with Reducing the Dimensionality of Heart Rate Variability Features

Obstructive Sleep Apnea Syndrome (OSAS) is a clinically significant disorder characterized by recurrent episodes of upper airway obstruction, manifesting as either apnea or hypopnea, predominantly occurring at the pharyngeal level. Despite the preservation of respiratory muscle function during these episodes, OSAS poses considerable health risks, including cardiovascular complications and cognitive impairment. In recent years, a growing body of literature has explored novel methodologies to discern and diagnose OSAS, with a particular focus on cardiac activity analysis through Heart Rate Variability (HRV). This study contributes to the existing literature by conducting a comprehensive HRV analysis aimed at identifying indicative patterns of sleep apnea. The analysis incorporates diverse parameters within both time and frequency domains, facilitating a nuanced understanding of the complex interplay between cardiac dynamics and respiratory disruptions during sleep. In an effort to enhance the interpretability of the data, various scaling and dimensionality reduction techniques, such as Principal Component Analysis (PCA), t-distributed Stochastic Neighbor Embedding (t-SNE), and Uniform Manifold Approximation and Projection (UMAP), were applied. The dataset utilized in this investigation comprises records from 70 patients, sourced from the Apnea-ECG Database on the Physionet platform. To discern the optimal classification model, several machine learning algorithms were employed after the dimensionality reduction, including k-Nearest Neighbors (k-NN), logistic regression, Support Vector Machine (SVM), Decision Tree, Random Forest, and Gradient Boosting. Intriguingly, the results demonstrate a remarkable 100% accuracy across all classifiers when utilizing the UMAP dimensionality reduction method. A distinctive feature of the proposed methodology lies in its amalgamation of machine learning techniques with HRV parameters post-dimensionality reduction. This approach not only enhances the interpretability of the complex physiological data but also underscores the potential applicability of the developed model in real-world scenarios for the detection of OSAS. The robustness of the proposed approach, as evidenced by its high accuracy rates, positions it as a promising tool for advancing diagnostic capabilities in the realm of sleep medicine. Future research endeavors may further refine and validate this methodology, paving the way for its integration into clinical practice and contributing to the broader landscape of sleep disorder diagnostics.

Multi-Feature Automatic Extraction for Detecting Obstructive Sleep Apnea Based on Single-Lead Electrocardiography Signals.

Obstructive sleep apnea (OSA), a prevalent sleep disorder, is intimately associated with various other diseases, particularly cardiovascular conditions. The conventional diagnostic method, nocturnal polysomnography (PSG), despite its widespread use, faces challenges due to its high cost and prolonged duration. Recent developments in electrocardiogram-based diagnostic techniques have opened new avenues for addressing these challenges, although they often require a deep understanding of feature engineering. In this study, we introduce an innovative method for OSA classification that combines a composite deep convolutional neural network model with a multimodal strategy for automatic feature extraction. This approach involves transforming the original dataset into scalogram images that reflect heart rate variability attributes and Gramian angular field matrix images that reveal temporal characteristics, aiming to enhance the diversity and richness of data features. The model comprises automatic feature extraction and feature enhancement components and has been trained and validated on the PhysioNet Apnea-ECG database. The experimental results demonstrate the model's exceptional performance in diagnosing OSA, achieving an accuracy of 96.37%, a sensitivity of 94.67%, a specificity of 97.44%, and an AUC of 0.96. These outcomes underscore the potential of our proposed model as an efficient, accurate, and convenient tool for OSA diagnosis.

Deep learning-based sleep apnea detection using single-lead ECG signals from the PhysioNet apnea-ECG database

Deep learning-based sleep apnea detection using single-lead ECG signals from the PhysioNet apnea-ECG database

Wavelet transform and deep learning-based obstructive sleep apnea detection from single-lead ECG signals.

Sleep apnea is a common sleep disorder. Traditional testing and diagnosis heavily rely on the expertise of physicians, as well as analysis and statistical interpretation of extensive sleep testing data, resulting in time-consuming and labor-intensive processes. To address the problems of complex feature extraction, data imbalance, and low model capacity, we proposed an automatic sleep apnea classification model (CA-EfficientNet) based on the wavelet transform, a lightweight neural network, and a coordinated attention mechanism. The signal is converted into a time-frequency image by wavelet transform and put into the proposed model for classification. The effects of input time window, wavelet transform type and data balancing on the classification performance are considered, and a cost-sensitive algorithm is introduced to more accurately distinguish between normal and abnormal breathing events. PhysioNet apnea ECG database was used for training and evaluation. The 3-min Frequency B-Spline wavelets transform of ECG signal was carried out, and Dice Loss was used to train the classification model of sleep breathing. The classification accuracy was 93.44%, sensitivity was 88.9%, specificity was 96.2% and most indexes were better than other related work.

0254 Diagnosis of Obstructive Sleep Apnea using Koopman Spectral Analysis

Abstract Introduction Koopman operator theory and the Hankel alternative view of the Koopman (HAVOK) model have been widely used to investigate the chaotic dynamics in complex systems. Although the statistics of intermittent dynamics have been evaluated in the HAVOK model, they are not adequate to characterize intermittent forcing. We proposed the Koopman spectral analysis method to characterize the intermittent transition between apeanic and non-apneaic episodes to predict impending OSA episodes. Methods Apnea-ECG Database from Physionet.org was selected to investigate the nonlinear intermittent behaviors of OSA disorder. The data set has 70 records of OSA patients, and the recordings vary from 7 hours to nearly 10 hours each. Each recording consists of a continuous digitized ECG signal and apnea annotations. First, the eigen time-delay coordinates were reconstructed from the heart rate variability (HRV) features. Next, the last eigen time-delay coordinate was modeled as an intermittent forcing component during apneic episodes. Finally, the forcing statistics in OSA were estimated to characterize the intermittency of the pathophysiological process. Results The statistics of the forcing in OSA demonstrated the fat-tailed distribution of the intermittent forcing of the underlying OSA pathophysiological process. The pooled means and standard deviations of the burst duration and the inter-burst duration across OSA patients were also calculated to be 1.73±0.26 minutes and 11.71±2.69 minutes. Scalogram amplitude and spectral decomposition of the wavelet transform exhibited various predominant frequencies and dynamics modes associated with apneic events. Conclusion We have reported the data-driven HAVOK model to obtain an intermittently forced linear system of chaos for the OSA pathophysiological processes The proposed method has been validated on 70 records of OSA patients from Apnea-ECG database. The forcing signal can predict the intermittent transient events, such as the transition from normal to apneic episodes in OSA case. Support (if any) Huynh PK, Setty AR, Le TB, Le TQ. A noise-robust Koopman spectral analysis of an intermittent dynamics method for complex systems: a case study in pathophysiological processes of obstructive sleep apnea. IISE Transactions on Healthcare Systems Engineering. 2022 Nov 1:1-6.

Nocturnal Heart Rate Variability Might Help in Predicting Severe Obstructive Sleep-Disordered Breathing.

Obstructive sleep apnea (OSA) can have long-term cardiovascular and metabolic effects. The identification of OSA-related impairments would provide diagnostic and prognostic value. Heart rate variability (HRV) as a measure of cardiac autonomic regulation is a promising candidate marker of OSA and OSA-related conditions. We took advantage of the Physionet Apnea-ECG database for two purposes. First, we performed time- and frequency-domain analysis of nocturnal HRV on each recording of this database to evaluate the cardiac autonomic regulation in patients with nighttime sleep breathing disorders. Second, we conducted a logistic regression analysis (backward stepwise) to identify the HRV indices able to predict the apnea-hypopnea index (AHI) categories (i.e., "Severe OSA", AHI ≥ 30; "Moderate-Mild OSA", 5 ≥ AHI < 30; and "Normal", AHI < 5). Compared to the "Normal", the "Severe OSA" group showed lower high-frequency power in normalized units (HFnu) and higher low-frequency power in normalized units (LFnu). The standard deviation of normal R-R intervals (SDNN) and the root mean square of successive R-R interval differences (RMSSD) were independently associated with sleep-disordered breathing. Our findings suggest altered cardiac autonomic regulation with a reduced parasympathetic component in OSA patients and suggest a role of nighttime HRV in the characterization and identification of sleep breathing disorders.

CNN Model for Sleep Apnea Detection Based on SpO2 Signal

Sleep Apnea-Hypopnea Syndrome (SAHS) is one of the common sleep disorders which cause hypertension, coronary artery disease, stroke, and diabetes mellitus, as well as the increment of vehicle collisions. Polysomnography is a traditional way of diagnosing sleep disorder which requires multiple sensors for producing multiple physiological signals. Traditional Polysomnography causes huge costs for diagnosing SAHS because it requires numerous sensors as well as time. This study has developed a model by using deep learning techniques to minimize the cost and time for SAHS diagnosing. This study has utilized the SpO2 signal by using a Convolutional Neural Network (CNN) as a deep learning technique to detect SAHS in any individuals. The sleep disorder depends on the amount of blood in the body which is detected by the SpO2 signal.&amp;nbsp; The proposed CNN model consists of eight layers: three convolution layers, three max-pooling layers, one fully connected layer, and one softmax layer. Two datasets were used: the Apnea-ECG and UCD databases; the first has eight subjects, and the last has 25 subjects. In carrying out the tests, our model achieved an accuracy of 95.5% with the Apnea-ECG database and 90.2% with the UCD database. The suggested technique has provided a cost-effective and efficient way of identifying SAHS in any individual.&amp;nbsp;

Obstructive Sleep Apnea Detection using Frequency Analysis of Electrocardiographic RR Interval and Machine Learning Algorithms.

Obstructive Sleep Apnea (OSA) is a respiratory disorder due to obstructive upper airway (mainly in the oropharynx) periodically during sleep. The common examination used to diagnose sleep disorders is Polysomnography (PSG). Diagnose with PSG feels uncomfortable for the patient because the patient's body is fitted with many sensors. This study aims to propose an OSA detection using the Fast Fourier Transform (FFT) statistics of electrocardiographic RR Interval (R interval from one peak to the peak of the pulse of the next pulse R) and machine learning algorithms. In this case-control study, data were taken from the Massachusetts Institute of Technology at Beth Israel Hospital (MIT-BIH) based on the Apnea ECG database (RR Interval). The machine learning algorithms were Linear Discriminant Analysis (LDA), Artificial Neural Network (ANN), K-Nearest Neighbors (K-NN), and Support Vector Machine (SVM). The OSA detection technique was designed and tested, and five features of the FFT were examined, namely mean (f1), Shannon entropy (f2), standard deviation (f3), median (f4), and geometric mean (f5). The OSA detection found the highest performance using ANN. Among the ANN types tested, the ANN with gradient descent backpropagation resulted in the best performance with accuracy, sensitivity, and specificity of 84.64%, 94.21%, and 64.03%, respectively. The lowest performance was found when LDA was applied. ANN with gradient-descent backpropagation performed higher than LDA, SVM, and KNN for OSA detection.

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.

Multi-task feature fusion network for Obstructive Sleep Apnea detection using single-lead ECG signal

Efficient daily monitoring of Obstructive Sleep Apnea (OSA) and timely implementation of treatment is one of the important measures to ensure human health and sleep quality. Unfortunately, as the clinical gold standard, polysomnography (PSG) is complex to detect and cannot be popularized on a large scale. In recent years, OSA detection methods for single-lead electrocardiogram (ECG) signal based on deep learning have emerged. However, the detection performance of these deep learning methods based on a single learning task is often unsatisfactory. In order to solve this problem, we propose an OSA detection method based on one-dimensional multi-task feature fusion convolutional neural network (1D-MTFFNet). First of all, the borderline synthetic minority oversampling technique (Borderline-SMOTE) is used to alleviate the problem of data imbalance. Secondly, a multi-task learning method based on the combination of unsupervised feature learning and supervised feature learning is proposed to improve the feature extraction performance of the network. Finally, feature fusion between multiple tasks and between different levels is achieved by channel shuffling. We use the Apnea-ECG database of PhysioNet to conduct experiments. In terms of segment detection results, the proposed method achieves an accuracy of 91.13%, and the sensitivity and specificity reach 90.32% and 91.63% respectively. In terms of individual screening, the accuracy of the proposed method reached 100%. The overall performance is at the level of the most advanced methods.

Detection of Episodes of Sleep Apnea and Hypopnea in ECG and EEG Signals by Machine Learning

The article is devoted to the application of machine learning methods for computerized detection of sleep apnea episodes based on the analysis of single-channel signals of the electrocardiogram (ECG) and electroencephalogram (EEG). To study the possibilities of machine learning to detect apnea based on ECG and EEG analysis, we used Apnea-ECG database and MIT-BIH polysomnographic database from PhysioNet, which contain annotations to each minute of records indicating the presence or absence of apnea/hypopnea at the current time. In order to apply machine learning methods to the problem of automated detection of sleep apnea/hypopnea episodes in ECG and EEG signals, long-term polysomnograms available in MIT-BIH polysomnographic database were segmented according to annotations into shorter sections lasting 30 seconds each. The study used 267 segments lasting 30 seconds for the class "norm", 258 segments for the class "apnea" and 273 segments for the class "hypopnea", a total of 798 simultaneous ECG and EEG recordings. The aim of this work is to identify and compare informative signs of sleep apnea episodes in terms of heart rate variability (HRV) and brain electrical activity, as well as the choice of classification methods that provide the highest accuracy for this task. Features of cardiorhythmograms in time and frequency domains, spectral-temporal and wavelet characteristics, as well as parameters of EEG signals based on energy ratio of EEG rhythms, Hearst index, Higuchi fractal dimension and sample entropy for EEG signals are considered. Using different sets of features, the accuracy of classifiers based on decision trees, discriminant analysis, support vector machines, k-nearest neighbor method, and ensemble training was determined. Based on this, combination of features and classifiers is proposed, which provides the highest accuracy of recognition of sleep apnea episodes according to single-channel ECG and EEG signals, taken separately and in the case of a combination of their features. The best results of classification of signals "norm", "apnea" and "hypopnea" were obtained for the model trained using weighted method k nearest neighbors with 25 features of HRV: the total percentage of correctly identified cases for three classes was 99.9% (797 correctly identified cases of 798). By reducing the number of HRV parameters to 9, the best machine learning result was achieved using the bagging ensemble algorithm with 30 decision trees: the total percentage of correctly identified cases for all three classes was 99.4% (793 correctly identified cases from 798: for "norm" - 265 cases from 267, for "apnea" - 257 cases from 258, for "hypopnea" - 271 cases from 273). The use of EEG parameters as features for apnea/hypopnea recognition showed worse results compared to HRV parameters. In this case, the best result of machine learning was achieved using support vector machines with quadratic kernel function: the total percentage of correctly identified cases for three classes was 91.9% and the signals corresponding to norm were most badly recognized (27 cases were classified as hypopnea, and in 9 cases - as sleep apnea). The combination of HRV and EEG parameters gave the best accuracy of 99.1%, but the results are comparable to using only HRV parameters. The obtained results indicate that HRV parameters allow recognizing sleep apnea and hypopnea with higher accuracy than EEG parameters, but EEG signal undoubtedly reflects signs of sleep apnea/hypopnea and also can be used for apnea recognition.

Detection of Sleep Apnea from Electrocardiogram and Pulse Oximetry Signals Using Random Forest

Sleep apnea (SA) is a common sleep disorder which could impair the human physiological system. Therefore, early diagnosis of SA is of great interest. The traditional method of diagnosing SA is an overnight polysomnography (PSG) evaluation. When PSG has limited availability, automatic SA screening with a fewer number of signals should be considered. The primary purpose of this study is to develop and evaluate a SA detection model based on electrocardiogram (ECG) and blood oxygen saturation (SpO2). We adopted a multimodal approach to fuse ECG and SpO2 signals at the feature level. Then, feature selection was conducted using the recursive feature elimination with cross-validation (RFECV) algorithm and random forest (RF) classifier used to discriminate between apnea and normal events. Experiments were conducted on the Apnea-ECG database. The introduced algorithm obtained an accuracy of 97.5%, a sensitivity of 95.9%, a specificity of 98.4% and an AUC of 0.992 in per-segment classification, and outperformed previous works. The results showed that ECG and SpO2 are complementary in detecting SA, and that the combination of ECG and SpO2 enhances the ability to diagnose SA. Therefore, the proposed method has the potential to be an alternative to conventional detection methods.

Contribution of Different Subbands of ECG in Sleep Apnea Detection Evaluated Using Filter Bank Decomposition and a Convolutional Neural Network.

A variety of feature extraction and classification approaches have been proposed using electrocardiogram (ECG) and ECG-derived signals for improving the performance of detecting apnea events and diagnosing patients with obstructive sleep apnea (OSA). The purpose of this study is to further evaluate whether the reduction of lower frequency P and T waves can increase the accuracy of the detection of apnea events. This study proposed filter bank decomposition to decompose the ECG signal into 15 subband signals, and a one-dimensional (1D) convolutional neural network (CNN) model independently cooperating with each subband to extract and classify the features of the given subband signal. One-minute ECG signals obtained from the MIT PhysioNet Apnea-ECG database were used to train the CNN models and test the accuracy of detecting apnea events for different subbands. The results show that the use of the newly selected subject-independent datasets can avoid the overestimation of the accuracy of the apnea event detection and can test the difference in the accuracy of different subbands. The frequency band of 31.25–37.5 Hz can achieve 100% per-recording accuracy with 85.8% per-minute accuracy using the newly selected subject-independent datasets and is recommended as a promising subband of ECG signals that can cooperate with the proposed 1D CNN model for the diagnosis of OSA.

A Hybrid Transformer Model for Obstructive Sleep Apnea Detection Based on Self-Attention Mechanism Using Single-Lead ECG

<i>Objective</i>: Obstructive Sleep Apnea (OSA) is a widespread sleep disorder that seriously affects human health. Detection of OSA with low cost and high accuracy is of great clinical significance. This study proposes a hybrid Transformer model based on self-attention mechanism for OSA detection using single-lead electrocardiogram (ECG). <i>Methods</i>: To reduce the introduction of expert knowledge, a new method for constructing raw inputs is proposed. The data inputs include the raw ECG signal sequence, R-peak amplitude (RA) sequence, inter-beat (RR) interval (RRI) sequence, and RR interval first-order difference (RRID) sequence. Then a multi-perspective channel-attention (MPCA) block is proposed to focus on the contribution of four input signals automatically and extract the fused multi-perspective features. These features together with their position encodings were fed into Transformer blocks to encode the most important information with self-attention mechanism. Finally, the prediction results were output through the linear layer. <i>Results</i>: The proposed method was verified on the Apnea-ECG database. The per-segment classification accuracy reached 0.91 and the area under the ROC (receiver operating characteristic) curve (AUC) was 0.96. The per-recording classification accuracy reached 100% and the mean absolute error (MAE) was 2.71. Our method achieved better classification performance than other state-of-the-art algorithms. <i>Conclusion</i>: The proposed hybrid Transformer model is able to detect OSA accurately using single-lead ECG in a manner similar to detection process by human experts. <i>Significance</i>: Our method provides a convenient and precise solution for clinical OSA detection.

Detection of Obstructive Sleep Apnea Using Non-Negative Matrix Factorization-Based Feature Extraction Approach in Eigen Spectrum Domain

Obstructive sleep apnea (OSA) is the most prevalent type sleeping disorder that highly affects people’s health impairment by threatening the cardiovascular system. As an alternative to standard polysomnography (PSG) analysis, the electrocardiogram (ECG) signal has gained high interests in recent studies of OSA diagnosis. However, the existing techniques are unable to provide high detection accuracy due to their inability of capturing the hidden patterns underlying in the EGC signal. In this context, the proposed OSA detection model is designed in terms of the singular spectrum analysis (SSA) of the ECG signal. This approach investigates the Eigen spectrum of ECG data obtained from SSA. In addition, a non-negative matrix factorization (NMF) scheme is applied to reduce the dimensionality of Eigen space by eliminating its redundant characteristics. Following this, a set of new feature predictors is extracted from the activation matrices. Moreover, the present work employs an ensemble learning method by fusing diverse and accurate base classifiers to realize a high-performance diagnostic system. This study has achieved overall 94.35% accuracy for minute-by-minute OSA detection using Physionet Apnea-ECG and University College Dublin (UCD) Database. Comparative study with the existing methods shows satisfactory performances of the proposed feature extraction scheme and ensemble learning approach.

DeepRTSNet: Deep Robust Two-Stage Networks for ECG Denoising in Practical Use Case

In this paper, we develop a low-cost cellular internet of medical things (IoMT)-based electrocardiogram (ECG) recorder for monitoring heart conditions and used in practical cases. In order to remove noise from signals recorded by these non-clinical devices, we propose a cloud-based denoising approach that focuses on utilizing deep neural network techniques in the time-frequency domain through the two stages. Accordingly, we exploit the fractional Stockwell transform (FrST) to transfer the ECG signal into the time-frequency domain and apply the deep robust two-stage network (DeepRTSNet) for noise cancellation. Due to the practical use case, the various heart physiologies and noise levels in different amplitudes and frequencies are needed to be robust against wide-range noises in actual conditions. We utilize the MIT-BIH Apnea-ECG database (APNEA-ECG) with several different heart physiologies. Next, the different noises consisting of muscle artifacts (MA), baseline wander (BW), and electrode motion (EM) from the MIT-BIH Noise Stress Test Database (NSTDB) and random noise, are added to the signals. The main focus of the noise generation part is the fast Fourier transformation (FFT) of the simulated noisy signal and the practical noisy signal has a maximum cross-correlation to gain a better morphological resemblance between realistic signals and the prepared datasets. Based on the results, DeepRTSNet outperforms prior learning-based methods and conventional non-learning approaches in terms of signal-to-noise ratio (SNR), root mean square error (RMSE), and percent root mean square difference (PRD). Moreover, outcomes reveal that DeepRTSNet has an extraordinary performance with a certain amount of further complexity than others.

Sleep Apnea Classification Algorithm Development Using a Machine-Learning Framework and Bag-of-Features Derived from Electrocardiogram Spectrograms.

Background: Heart rate variability (HRV) and electrocardiogram (ECG)-derived respiration (EDR) have been used to detect sleep apnea (SA) for decades. The present study proposes an SA-detection algorithm using a machine-learning framework and bag-of-features (BoF) derived from an ECG spectrogram. Methods: This study was verified using overnight ECG recordings from 83 subjects with an average apnea–hypopnea index (AHI) 29.63 (/h) derived from the Physionet Apnea-ECG and National Cheng Kung University Hospital Sleep Center database. The study used signal preprocessing to filter noise and artifacts, ECG time–frequency transformation using continuous wavelet transform (CWT), BoF feature generation, machine-learning classification using support vector machine (SVM), ensemble learning (EL), k-nearest neighbor (KNN) classification, and cross-validation. The time length of the spectrogram was set as 10 and 60 s to examine the required minimum spectrogram window time length to achieve satisfactory accuracy. Specific frequency bands of 0.1–50, 8–50, 0.8–10, and 0–0.8 Hz were also extracted to generate the BoF to determine the band frequency best suited for SA detection. Results: The five-fold cross-validation accuracy using the BoF derived from the ECG spectrogram with 10 and 60 s time windows were 90.5% and 91.4% for the 0.1–50 Hz and 8–50 Hz frequency bands, respectively. Conclusion: An SA-detection algorithm utilizing BoF and a machine-learning framework was successfully developed in this study with satisfactory classification accuracy and high temporal resolution.

A dual-model deep learning method for sleep apnea detection based on representation learning and temporal dependence

Sleep apnea (SA) is a sleep-breathing disorder accompanied by multiple complications. The SA detection method based on a single-lead electrocardiogram (ECG) has the characteristics of low power consumption and is desirable for the development of wearable equipment. This study proposed a dual-model deep learning method to perform representation learning and introduce long-term temporal dependence. First, the Christov algorithm was used to obtain the RR interval (RRI) of each 1-minute ECG segment, and the adaptive synthetic (ADASYN) sampling method was employed to synthesize the RRI series of the minority class to address the imbalanced learning problem. Then, a representation learning model based on the one-dimensional convolutional neural network (1DCNN-RLM) was built to extract the feature vector of the RRI series. Eventually, a temporal dependence model based on the bidirectional gated recurrent unit (BiGRU-TDM) was constructed to learn the state (SA/normal) transition pattern between the segments and complete the classification task. We employed the apnea-ECG database for experiments. For per-segment detection results, the accuracy, sensitivity, and specificity of this method were 91.1%, 88.9%, and 92.4%, respectively. The per-recording detection accuracy reached 100%. ADASYN alleviates the imbalance of sensitivity and specificity in classification results. The 1DCNN-RLM with powerful representation learning ability has extracted discriminative features. The BiGRU-TDM introduces the long-term time dependence of SA and improves classification performance. The results of this study substantiate that the proposed method is robust and has good transferability. This method provides a reference for the diagnosis of other diseases.

Ensemble of Deep Learning Models for Sleep Apnea Detection: An Experimental Study.

Sleep Apnea is a breathing disorder occurring during sleep. Older people suffer most from this disease. In-time diagnosis of apnea is needed which can be observed by the application of a proper health monitoring system. In this work, we focus on Obstructive Sleep Apnea (OSA) detection from the Electrocardiogram (ECG) signals obtained through the body sensors. Our work mainly consists of an experimental study of different ensemble techniques applied on three deep learning models—two Convolutional Neural Network (CNN) based models, and a combination of CNN and Long Short-Term Memory (LSTM) models, which were previously proposed in the OSA detection domain. We have chosen four ensemble techniques—majority voting, sum rule and Choquet integral based fuzzy fusion and trainable ensemble using Multi-Layer Perceptron (MLP) for our case study. All the experiments are conducted on the benchmark PhysioNet Apnea-ECG Database. Finally, we have achieved highest OSA detection accuracy of 85.58% using the MLP based ensemble approach. Our best result is also able to surpass many of state-of-the-art methods.