Performance evaluation of the spectral autocorrelation function and autoregressive models for automated sleep apnea detection using single-lead ECG signal

Diagnostic accuracy of machine learning algorithms in electrocardiogram-based sleep apnea detection: A systematic review and meta-analysis

Sleep apnea is a prevalent disorder affecting 10 % of middle-aged individuals, yet it remains underdiagnosed due to the limitations of polysomnography (PSG), the current diagnostic gold standard. Single-lead electrocardiography (ECG) has been proposed as a potential alternative diagnostic tool, but interpretation challenges remain. Recent advances in machine learning and deep learning technologies offer promising approaches for enhancing the detection of sleep apnea through automated analysis of ECG signals. This meta-analysis aims to evaluate the diagnostic accuracy of machine learning (ML) and deep learning (DL) algorithms in detecting sleep apnea patterns from single-lead ECG data. A comprehensive literature search across multiple databases was conducted through November 2023, adhering to PRISMA-DTA guidelines. Studies that included sensitivity and specificity data for ECG-based sleep apnea detection using (machine learning/deep learning) ML/DL were selected. The analysis included 84 studies, demonstrating high diagnostic accuracy for ML/DL algorithms, with pooled sensitivity and specificity of over 90 % in per-segment analysis and close to 97 % in per-record analysis. Despite strong diagnostic performance, variations in algorithm effectiveness and methodological biases were noted. This meta-analysis highlights the potential of ML and DL in improving sleep apnea diagnosis and outlines areas for future research to address current limitations.

Automatic detection of sleep apnea from a single-lead ECG signal based on spiking neural network model

BACKGROUND

Sleep apnea (SLA) is a commonly encountered sleep disorder characterized by repetitive cessation of respiration while sleeping. In the past few years, researchers have focused on developing less complex and more cost-effective diagnostic approaches for identifying SLA recipients, in contrast to the cumbersome, complicated, and expensive conventional methods.

METHOD

This study presents a biologically plausible learning approach of spiking neural networks (SNN) with temporal coding and a tempotron learning model for diagnosing SLA disorder using single-lead electrocardiogram (ECG) data information. The proposed framework utilizes temporal encoding and the leaky integrate and fire model to transform the ECG signal into spikes for capturing the signal's dynamic pattern nature and to simulate input response behaviors. The tempoton learning technique, a spike-based algorithm, trains the SNN model to identify SLA event patterns from encoded output spike trains. This study utilized ECG data to extract heart rate variability (HRV) and ECG-derived respiration (EDR) signals from 1-min segment data of ECG records for input to SNN model. Thirty-five recordings of both released and withheld data from the Apnea-ECG databases from Physionet have been applied to train the SNN model and validate the model's efficacy in identifying SLA occurrences.

RESULTS

The proposed method demonstrated substantial improvements compared to other SLA detection techniques, achieving a significant accuracy of 94.63 % for per-segment detection, along with specificity, sensitivity, F1-score and AUC values of 96.21 %, 92.04 %, 0.9285, and 0.9851 respectively. The accuracy for per-recording detection achieved 100 %, with a correlation coefficient value of 0.986. Additionally, the experiment used UCD data for validation methods, achieving an accuracy of 84.573 %.

CONCLUSIONS

These results suggest the effectiveness and accessibility of the presented approach for accurately identifying SLA cases. The suggested model enhances the performance of SLA detection when contrasted with various techniques based on feature engineering and feature learning.

EfficientNet-based machine learning architecture for sleep apnea identification in clinical single-lead ECG signal data sets

OBJECTIVE

Our objective was to create a machine learning architecture capable of identifying obstructive sleep apnea (OSA) patterns in single-lead electrocardiography (ECG) signals, exhibiting exceptional performance when utilized in clinical data sets.

METHODS

We conducted our research using a data set consisting of 1656 patients, representing a diverse demographic, from the sleep center of China Medical University Hospital. To detect apnea ECG segments and extract apnea features, we utilized the EfficientNet and some of its layers, respectively. Furthermore, we compared various training and data preprocessing techniques to enhance the model's prediction, such as setting class and sample weights or employing overlapping and regular slicing. Finally, we tested our approach against other literature on the Apnea-ECG database.

RESULTS

Our research found that the EfficientNet model achieved the best apnea segment detection using overlapping slicing and sample-weight settings, with an AUC of 0.917 and an accuracy of 0.855. For patient screening with AHI > 30, we combined the trained model with XGBoost, leading to an AUC of 0.975 and an accuracy of 0.928. Additional tests using PhysioNet data showed that our model is comparable in performance to existing models regarding its ability to screen OSA levels.

CONCLUSIONS

Our suggested architecture, coupled with training and preprocessing techniques, showed admirable performance with a diverse demographic dataset, bringing us closer to practical implementation in OSA diagnosis. Trial registration The data for this study were collected retrospectively from the China Medical University Hospital in Taiwan with approval from the institutional review board CMUH109-REC3-018.

HARDC : A novel ECG-based heartbeat classification method to detect arrhythmia using hierarchical attention based dual structured RNN with dilated CNN

Deep learning-based models have achieved significant success in detecting cardiac arrhythmia by analyzing ECG signals to categorize patient heartbeats. To improve the performance of such models, we have developed a novel hybrid hierarchical attention-based bidirectional recurrent neural network with dilated CNN (HARDC) method for arrhythmia classification. This solves problems that arise when traditional dilated convolutional neural network (CNN) models disregard the correlation between contexts and gradient dispersion. The proposed HARDC fully exploits the dilated CNN and bidirectional recurrent neural network unit (BiGRU-BiLSTM) architecture to generate fusion features. As a result of incorporating both local and global feature information and an attention mechanism, the model's performance for prediction is improved. By combining the fusion features with a dilated CNN and a hierarchical attention mechanism, the trained HARDC model showed significantly improved classification results and interpretability of feature extraction on the PhysioNet 2017 challenge dataset. Sequential Z-Score normalization, filtering, denoising, and segmentation are used to prepare the raw data for analysis. CGAN (Conditional Generative Adversarial Network) is then used to generate synthetic signals from the processed data. The experimental results demonstrate that the proposed HARDC model significantly outperforms other existing models, achieving an accuracy of 99.60%, F1 score of 98.21%, a precision of 97.66%, and recall of 99.60% using MIT-BIH generated ECG. In addition, this approach significantly reduces run time when using dilated CNN compared to normal convolution. Overall, this hybrid model demonstrates an innovative and cost-effective strategy for ECG signal compression and high-performance ECG recognition. Our results indicate that an automated and highly computed method to classify multiple types of arrhythmia signals holds considerable promise.

Automatic diagnosis of sleep apnea from biomedical signals using artificial intelligence techniques: Methods, challenges, and future works

Apnea is a sleep disorder that stops or reduces airflow for a short time during sleep. Sleep apnea may last for a few seconds and happen for many while sleeping. This reduction in breathing is associated with loud snoring, which may awaken the person with a feeling of suffocation. So far, a variety of methods have been introduced by researchers to diagnose sleep apnea, among which the polysomnography (PSG) method is known to be the best. Analysis of PSG signals is very complicated. Many studies have been conducted on the automatic diagnosis of sleep apnea from biological signals using artificial intelligence (AI), including machine learning (ML) and deep learning (DL) methods. This research reviews and investigates the studies on the diagnosis of sleep apnea using AI methods. First, computer aided diagnosis system (CADS) for sleep apnea using ML and DL techniques along with its parts including dataset, preprocessing, and ML and DL methods are introduced. This research also summarizes the important specifications of the studies on the diagnosis of sleep apnea using ML and DL methods in a table. In the following, a comprehensive discussion is made on the studies carried out in this field. The challenges in the diagnosis of sleep apnea using AI methods are of paramount importance for researchers. Accordingly, these obstacles are elaborately addressed. In another section, the most important future works for studies on sleep apnea detection from PSG signals and AI techniques are presented. Ultimately, the essential findings of this study are provided in the conclusion section.

This article is categorized under:

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.

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.

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.

AIOSA: An approach to the automatic identification of obstructive sleep apnea events based on deep learning

Obstructive Sleep Apnea Syndrome (OSAS) is the most common sleep-related breathing disorder. It is caused by an increased upper airway resistance during sleep, which determines episodes of partial or complete interruption of airflow. The detection and treatment of OSAS is particularly important in patients who suffered a stroke, because the presence of severe OSAS is associated with higher mortality, worse neurological deficits, worse functional outcome after rehabilitation, and a higher likelihood of uncontrolled hypertension. The gold standard test for diagnosing OSAS is polysomnography (PSG). Unfortunately, performing a PSG in an electrically hostile environment, like a stroke unit, on neurologically impaired patients is a difficult task; moreover, the number of strokes per day vastly outnumbers the availability of polysomnographs and dedicated healthcare professionals. Hence, a simple and automated recognition system to identify OSAS cases among acute stroke patients, relying on routinely recorded vital signs, is highly desirable. The vast majority of the work done so far focuses on data recorded in ideal conditions and highly selected patients, and thus it is hardly exploitable in real-life circumstances, where it would be of actual use. In this paper, we propose a novel convolutional deep learning architecture able to effectively reduce the temporal resolution of raw waveform data, like physiological signals, extracting key features that can be used for further processing. We exploit models based on such an architecture to detect OSAS events in stroke unit recordings obtained from the monitoring of unselected patients. Unlike existing approaches, annotations are performed at one-second granularity, allowing physicians to better interpret the model outcome. Results are considered to be satisfactory by the domain experts. Moreover, through tests run on a widely-used public OSAS dataset, we show that the proposed approach outperforms current state-of-the-art solutions.

The novel approach of temporal dependency complexity analysis of heart rate variability in obstructive sleep apnea

Obstructive sleep apnea (OSA) is a serious sleep disorder, which leads to changes in autonomic nerve function and increases the risk of cardiovascular disease. Heart rate variability (HRV) has been widely used as a non-invasive method for assessing the autonomic nervous system (ANS). We proposed the two-dimensional sample entropy of the coarse-grained Gramian angular summation field image (CgSampEn_2D) index. It is a new index for HRV analysis based on the temporal dependency complexity. In this study, we used 60 electrocardiogram (ECG) records from the Apnea-ECG database of PhysioNet (20 healthy records and 40 OSA records). These records were divided into 5-min segments. Compared with the classical indices low-to-high frequency power ratio (LF/HF) and sample entropy (SampEn), CgSampEn_2D utilizes the correlation information between different time intervals in the RR sequences and preserves the temporal dependency of the RR sequences, which improves the OSA detection performance significantly. The OSA screening accuracy of CgSampEn_2D (93.3%) is higher than that of LF/HF (80.0%) and SampEn (73.3%). Additionally, CgSampEn_2D has a significant association with the apnea-hypopnea index (AHI) (R = -0.740, p = 0). CgSampEn_2D reflects the complexity of the OSA autonomic nerve more comprehensively and provides a novel idea for the screening of OSA disease.

ECG Signal Modeling Using Volatility Properties: Its Application in Sleep Apnea Syndrome

This study presents and evaluates the mathematical model to estimate the mean and variance of single-lead ECG signals in sleep apnea syndrome. Our objective is to use the volatility property of the ECG signal for modeling. ECG signal is a stochastic signal whose mean and variance are time-varying. So, we propose to decompose this nonstationarity into two additive components; a homoscedastic Autoregressive Integrated Moving Average (ARIMA) and a heteroscedastic time series in terms of Exponential Generalized Autoregressive Conditional Heteroskedasticity (EGARCH), where the former captures the linearity property and the latter the nonlinear characteristics of the ECG signal. First, ECG signals are segmented into one-minute segments. The heteroskedasticity property is then examined through various tests such as the ARCH/GARCH test, kurtosis, skewness, and histograms. Next, the ARIMA model is applied to signals as a linear model and EGARCH as a nonlinear model. The appropriate orders of models are estimated by using the Bayesian Information Criterion (BIC). We assess the effectiveness of our model in terms of mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). The data in this article is obtained from the Physionet Apnea-ECG database. Results show that the ARIMA-EGARCH model performs better than other models for modeling both apneic and normal ECG signals in sleep apnea syndrome.

SCNN: Scalogram-based convolutional neural network to detect obstructive sleep apnea using single-lead electrocardiogram signals

Sleep apnea is a common symptomatic disease affecting nearly 1 billion people around the world. The gold standard approach for determining the severity of sleep apnea is full-night polysomnography conducted in the laboratory, which is very costly and cumbersome. In this work, we propose a novel scalogram-based convolutional neural network (SCNN) to detect obstructive sleep apnea (OSA) using single-lead electrocardiogram (ECG) signals. Firstly, we use continuous wavelet transform (CWT) to convert ECG signals into conventional scalograms. In parallel, we also apply empirical mode decomposition (EMD) to the signals to find correlated intrinsic mode functions (IMFs) and then apply CWT on the IMFs to obtain hybrid scalograms. Finally, we train a lightweight CNN model on these scalograms to extract deep features for OSA detection. Experiments on the benchmark Apnea-ECG dataset demonstrate that our proposed model results in an accuracy of 94.30%, sensitivity 94.30%, specificity 94.51%, and F1-score 95.85% in per-segment classification. Our model also achieves an accuracy of 81.86%, sensitivity 71.62%, specificity 86.05%, and F1-score 69.63% for UCDDB dataset. Furthermore, our model achieves an accuracy of 100.00% in per-recording classification for Apnea-ECG dataset. The experimental results outperform the existing OSA detection approaches using ECG signals.

Detection of Ventricular Fibrillation Based on Ballistocardiography by Constructing an Effective Feature Set

Ventricular fibrillation (VF) is a type of fatal arrhythmia that can cause sudden death within minutes. The study of a VF detection algorithm has important clinical significance. This study aimed to develop an algorithm for the automatic detection of VF based on the acquisition of cardiac mechanical activity-related signals, namely ballistocardiography (BCG), by non-contact sensors. BCG signals, including VF, sinus rhythm, and motion artifacts, were collected through electric defibrillation experiments in pigs. Through autocorrelation and S transform, the time-frequency graph with obvious information of cardiac rhythmic activity was obtained, and a feature set of 13 elements was constructed for each 7 s segment after statistical analysis and hierarchical clustering. Then, the random forest classifier was used to classify VF and non-VF, and two paradigms of intra-patient and inter-patient were used to evaluate the performance. The results showed that the sensitivity and specificity were 0.965 and 0.958 under 10-fold cross-validation, and they were 0.947 and 0.946 under leave-one-subject-out cross-validation. In conclusion, the proposed algorithm combining feature extraction and machine learning can effectively detect VF in BCG, laying a foundation for the development of long-term self-cardiac monitoring at home and a VF real-time detection and alarm system.

Automatic seizure detection using orthogonal matching pursuit, discrete wavelet transform, and entropy based features of EEG signals

BACKGROUND AND OBJECTIVE

Epilepsy is a prevalent disorder that affects the central nervous system, causing seizures. In the current study, a novel algorithm is developed using electroencephalographic (EEG) signals for automatic seizure detection from the continuous EEG monitoring data.

METHODS

In the proposed methods, the discrete wavelet transform (DWT) and orthogonal matching pursuit (OMP) techniques are used to extract different coefficients from the EEG signals. Then, some non-linear features, such as fuzzy/approximate/sample/alphabet and correct conditional entropy, along with some statistical features are calculated using the DWT and OMP coefficients. Three widely-used EEG datasets were utilized to assess the performance of the proposed techniques.

RESULTS

The proposed OMP-based technique along with the support vector machine classifier yielded an average specificity of 96.58%, an average accuracy of 97%, and an average sensitivity of 97.08% for different types of classification tasks. Moreover, the proposed DWT-based technique provided an average sensitivity of 99.39%, an average accuracy of 99.63%, and an average specificity of 99.72%.

CONCLUSIONS

The experimental findings indicated that the proposed algorithms outperformed other existing techniques. Therefore, these algorithms can be implemented in relevant hardware to help neurologists with seizure detection.

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.