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

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.

Application of artificial intelligence in the diagnosis of sleep apnea

STUDY OBJECTIVES

Machine learning (ML) models have been employed in the setting of sleep disorders. This review aims to summarize the existing data about the role of ML techniques in the diagnosis, classification, and treatment of sleep-related breathing disorders.

METHODS

A systematic search in Medline, EMBASE, and Cochrane databases through January 2022 was performed.

RESULTS

Our search strategy revealed 132 studies that were included in the systematic review. Existing data show that ML models have been successfully used for diagnostic purposes. Specifically, ML models showed good performance in diagnosing sleep apnea using easily obtained features from the electrocardiogram, pulse oximetry, and sound signals. Similarly, ML showed good performance for the classification of sleep apnea into obstructive and central categories, as well as predicting apnea severity. Existing data show promising results for the ML-based guided treatment of sleep apnea. Specifically, the prediction of outcomes following surgical treatment and optimization of continuous positive airway pressure therapy can be guided by ML models.

CONCLUSIONS

The adoption and implementation of ML in the field of sleep-related breathing disorders is promising. Advancements in wearable sensor technology and ML models can help clinicians predict, diagnose, and classify sleep apnea more accurately and efficiently.

CITATION

Bazoukis G, Bollepalli SC, Chung CT, et al. Application of artificial intelligence in the diagnosis of sleep apnea. J Clin Sleep Med. 2023;19(7):1337-1363.

RAFNet: Restricted attention fusion network for sleep apnea detection

Sleep apnea (SA) is a common sleep-related breathing disorder, which would lead to damage of multiple systemic organs or even sudden death. In clinical practice, portable device is an important tool to monitor sleep conditions and detect SA events by using physiological signals. However, SA detection performance is still limited due to physiological signals with time-variability and complexity. In this paper, we focus on SA detection with single lead ECG signals, which can be easily collected by a portable device. Under this context, we propose a restricted attention fusion network called RAFNet for sleep apnea detection. Specifically, RR intervals (RRI) and R-peak amplitudes (Rpeak) are generated from ECG signals and divided into one-minute-long segments. To alleviate the problem of insufficient feature information of the target segment, we combine the target segment with two pre- and post-adjacent segments in sequence, (i.e. a five-minute-long segment), as the input. Meanwhile, by leveraging the target segment as the query vector, we propose a new restricted attention mechanism with cascaded morphological and temporal attentions, which can effectively learn the feature information and depress redundant feature information from the adjacent segments with adaptive assigning weight importance. To further improve the SA detection performance, the target and adjacent segment features are fused together with the channel-wise stacking scheme. Experiment results on the public Apnea-ECG dataset and the real clinical FAH-ECG dataset with sleep apnea annotations show that the RAFNet greatly improves SA detection performance and achieves competitive results, which are superior to those achieved by the state-of-the-art baselines.

Fast Sleep Stage Classification Using Cascaded Support Vector Machines with Single-Channel EEG Signals

Long-term sleep stage monitoring is very important for the diagnosis and treatment of insomnia. With the development of wearable electroencephalogram (EEG) devices, we developed a fast and accurate sleep stage classification method in this study with single-channel EEG signals for practical applications. The original sleep recordings were collected from the Sleep-EDF database. The wavelet threshold denoising (WTD) method and wavelet packet transformation (WPT) method were applied as signal preprocessing to extract six kinds of characteristic waves. With a comprehensive feature system including time, frequency, and nonlinear dynamics, we obtained the sleep stage classification results with different Support Vector Machine (SVM) models. We proposed a novel classification method based on cascaded SVM models with various features extracted from denoised EEG signals. To enhance the accuracy and generalization performance of this method, nonlinear dynamics features were taken into consideration. With nonlinear dynamics features included, the average classification accuracy was up to 88.11% using this method. In addition, with cascaded SVM models, the classification accuracy of the non-rapid eye movement sleep stage 1 (N1) was enhanced from 41.5% to 55.65% compared with the single SVM model, and the overall classification time for each epoch was less than 1.7 s. Moreover, we demonstrated that it was possible to apply this method for long-term sleep stage monitor applications.

At-home wireless monitoring of acute hemodynamic disturbances to detect sleep apnea and sleep stages via a soft sternal patch

Obstructive sleep apnea (OSA) affects more than 900 million adults globally and can create serious health complications when untreated; however, 80% of cases remain undiagnosed. Critically, current diagnostic techniques are fundamentally limited by low throughputs and high failure rates. Here, we report a wireless, fully integrated, soft patch with skin-like mechanics optimized through analytical and computational studies to capture seismocardiograms, electrocardiograms, and photoplethysmograms from the sternum, allowing clinicians to investigate the cardiovascular response to OSA during home sleep tests. In preliminary trials with symptomatic and control subjects, the soft device demonstrated excellent ability to detect blood-oxygen saturation, respiratory effort, respiration rate, heart rate, cardiac pre-ejection period and ejection timing, aortic opening mechanics, heart rate variability, and sleep staging. Last, machine learning is used to autodetect apneas and hypopneas with 100% sensitivity and 95% precision in preliminary at-home trials with symptomatic patients, compared to data scored by professionally certified sleep clinicians.

Sleep apnea screening based on Photoplethysmography data from wearable bracelets using an information-based similarity approach

BACKGROUND AND OBJECTIVE

Sleep apnea (SA) is a common sleep disorder in daily life and is also an aggravating factor for various diseases. Having the potential to replace traditional but complicated diagnostic equipment, portable medical devices are receiving increasing attention, and thus, the demand for supporting algorithms is growing. This study aims to identify SA with wearable devices.

METHODS

Static information-based similarity (sIBS) and dynamic information-based similarity (dIBS) were proposed to analyze short-term fluctuations in heart rate (HR) with wearable devices. This study included overnight photoplethysmography (PPG) signals from 92 subjects obtained from wearable bracelets.

RESULTS

The results showed that sIBS achieved the highest correlation coefficient with the apnea-hypopnea index (R=-0.653, p=0). dIBS showed a good balance in sensitivity and specificity (75.0% and 72.1%, respectively). Combining sIBS and dIBS with other classical time-frequency domain indices could simultaneously achieve good accuracy and balance (84.7% accuracy, 76.7% sensitivity and 89.6% specificity).

CONCLUSIONS

This research showed that both classic time-frequency domain indices and IBS indices changed significantly only in the severe SA group. This novel method could serve as an effective way to assess SA and provide new insight into its pathophysiology.

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.

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.

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.

A fused-image-based approach to detect obstructive sleep apnea using a single-lead ECG and a 2D convolutional neural network

Obstructive sleep apnea (OSA) is a common chronic sleep disorder that disrupts breathing during sleep and is associated with many other medical conditions, including hypertension, coronary heart disease, and depression. Clinically, the standard for diagnosing OSA involves nocturnal polysomnography (PSG). However, this requires expert human intervention and considerable time, which limits the availability of OSA diagnosis in public health sectors. Therefore, electrocardiogram (ECG)-based methods for OSA detection have been proposed to automate the polysomnography procedure and reduce its discomfort. So far, most of the proposed approaches rely on feature engineering, which calls for advanced expert knowledge and experience. This paper proposes a novel fused-image-based technique that detects OSA using only a single-lead ECG signal. In the proposed approach, a convolutional neural network extracts features automatically from images created with one-minute ECG segments. The proposed network comprises 37 layers, including four residual blocks, a dense layer, a dropout layer, and a soft-max layer. In this study, three time-frequency representations, namely the scalogram, the spectrogram, and the Wigner-Ville distribution, were used to investigate the effectiveness of the fused-image-based approach. We found that blending scalogram and spectrogram images further improved the system's discriminative characteristics. Seventy ECG recordings from the PhysioNet Apnea-ECG database were used to train and evaluate the proposed model using 10-fold cross validation. The results of this study demonstrated that the proposed classifier can perform OSA detection with an average accuracy, recall, and specificity of 92.4%, 92.3%, and 92.6%, respectively, for the fused spectral images.

Development of Automated Sleep Stage Classification System Using Multivariate Projection-Based Fixed Boundary Empirical Wavelet Transform and Entropy Features Extracted from Multichannel EEG Signals

The categorization of sleep stages helps to diagnose different sleep-related ailments. In this paper, an entropy-based information–theoretic approach is introduced for the automated categorization of sleep stages using multi-channel electroencephalogram (EEG) signals. This approach comprises of three stages. First, the decomposition of multi-channel EEG signals into sub-band signals or modes is performed using a novel multivariate projection-based fixed boundary empirical wavelet transform (MPFBEWT) filter bank. Second, entropy features such as bubble and dispersion entropies are computed from the modes of multi-channel EEG signals. Third, a hybrid learning classifier based on class-specific residuals using sparse representation and distances from nearest neighbors is used to categorize sleep stages automatically using entropy-based features computed from MPFBEWT domain modes of multi-channel EEG signals. The proposed approach is evaluated using the multi-channel EEG signals obtained from the cyclic alternating pattern (CAP) sleep database. Our results reveal that the proposed sleep staging approach has obtained accuracies of 91.77%, 88.14%, 80.13%, and 73.88% for the automated categorization of wake vs. sleep, wake vs. rapid eye movement (REM) vs. Non-REM, wake vs. light sleep vs. deep sleep vs. REM sleep, and wake vs. S1-sleep vs. S2-sleep vs. S3-sleep vs. REM sleep schemes, respectively. The developed method has obtained the highest overall accuracy compared to the state-of-art approaches and is ready to be tested with more subjects before clinical application.

A Smart Service Platform for Cost Efficient Cardiac Health Monitoring

AIM

In this study we have investigated the problem of cost effective wireless heart health monitoring from a service design perspective.

SUBJECT AND METHODS

There is a great medical and economic need to support the diagnosis of a wide range of debilitating and indeed fatal non-communicable diseases, like Cardiovascular Disease (CVD), Atrial Fibrillation (AF), diabetes, and sleep disorders. To address this need, we put forward the idea that the combination of Heart Rate (HR) measurements, Internet of Things (IoT), and advanced Artificial Intelligence (AI), forms a Heart Health Monitoring Service Platform (HHMSP). This service platform can be used for multi-disease monitoring, where a distinct service meets the needs of patients having a specific disease. The service functionality is realized by combining common and distinct modules. This forms the technological basis which facilitates a hybrid diagnosis process where machines and practitioners work cooperatively to improve outcomes for patients.

RESULTS

Human checks and balances on independent machine decisions maintain safety and reliability of the diagnosis. Cost efficiency comes from efficient signal processing and replacing manual analysis with AI based machine classification. To show the practicality of the proposed service platform, we have implemented an AF monitoring service.

CONCLUSION

Having common modules allows us to harvest the economies of scale. That is an advantage, because the fixed cost for the infrastructure is shared among a large group of customers. Distinct modules define which AI models are used and how the communication with practitioners, caregivers and patients is handled. That makes the proposed HHMSP agile enough to address safety, reliability and functionality needs from healthcare providers.