Classification of Obstructive Sleep Apnoea from single-lead ECG signals using convolutional neural and Long Short Term Memory networks

AI-driven approaches for automatic detection of sleep apnea/hypopnea based on human physiological signals: a review

Sleep apnea/hypopnea is a sleep disorder characterized by repeated pauses in breathing which could induce a series of health problems such as cardiovascular disease (CVD) and even sudden death. Polysomnography (PSG) is the most common way to diagnose sleep apnea/hypopnea. Considering that PSG data acquisition is complex and the diagnosis of sleep apnea/hypopnea requires manual scoring, it is very time-consuming and highly professional. With the development of wearable devices and AI techniques, more and more works have been focused on building machine and deep learning models that use single or multi-modal physiological signals to achieve automated detection of sleep apnea/hypopnea. This paper provides a comprehensive review of automatic sleep apnea/hypopnea detection methods based on AI-based techniques in recent years. We summarize the general process used by existing works with a flow chart, which mainly includes data acquisition, raw signal pre-processing, model construction, event classification, and evaluation, since few papers consider these. Additionally, the commonly used public database and pre-processing methods are also reviewed in this paper. After that, we separately summarize the existing methods related to different modal physiological signals including nasal airflow, pulse oxygen saturation (SpO2), electrocardiogram (ECG), electroencephalogram (EEG) and snoring sound. Furthermore, specific signal pre-processing methods based on the characteristics of different physiological signals are also covered. Finally, challenges need to be addressed, such as limited data availability, imbalanced data problem, multi-center study necessity etc., and future research directions related to AI are discussed.

Deep learning-based LDL-C level prediction and explainable AI interpretation

This study investigates the use of deep learning (DL) models to predict low-density lipoprotein cholesterol (LDL-C) levels. The dataset obtained from New York-Presbyterian Hospital/Weill Cornell Medical Center includes triglycerides (TG), total cholesterol (TC) and high-density lipoprotein cholesterol (HDL-C). LDL-C prediction was performed using DL models such as CNN, RNN and LSTM and the results were compared with traditional machine learning (ML) and LDL-C formulas. The obtained results showed that DL models are more successful than traditional formulas while giving closer results to ML models. It is shown that DL models can predict LDL-C with higher accuracy compared to the Sampson, and Martin equation. In particular, RNN and LSTM models performed better in LDL-C prediction than the other formulas. In addition, the prediction results of DL models were explained using Local Interpretable Model-Agnostic Explanations (LIME) method. The features of the proposed models provide more parameters to explain the AI Model better in comparison with the ML models but require more computational efforts to explain DL model decisions. The results demonstrate that DL models in predicting LDL-C levels are more effective than traditional methods for LDL-C prediction and can be used in clinical applications. As a result, the findings might provide significant contributions to assessing cardiovascular disease risk and planning treatment protocols.

Explainable AI-driven scalogram analysis and optimized transfer learning for sleep apnea detection with single-lead electrocardiograms

Sleep apnea, a fatal sleep disorder causing repetitive respiratory cessation, requires immediate intervention due to neuropsychological issues. However, existing approaches such as polysomnography, considered the most reliable and accurate test to detect sleep apnea, frequently require multichannel ECG recordings and advanced feature extraction algorithms, significantly restricting their wider application. Deep learning has recently emerged as a viable method for detecting sleep apnea. Our study describes a unique method for detecting sleep apnea utilizing single-lead ECG signals and deep learning techniques. In our proposed method, we have employed the continuous wavelet transform to convert electrocardiogram (ECG) signals into scalograms, which allows us to capture both the time and frequency domains. To enhance the classification performance, we have implemented an optimized pre-trained GoogLeNet architecture as a transfer learning model. In this study, we have analyzed the PhysioNet Apnea ECG dataset, UCDDB dataset and the MIT-BIH polysomnographic dataset for training and evaluation for per-segment classification, to demonstrate the effectiveness of our approach. In our experiments, the proposed model achieves remarkable results, with an accuracy of 93.85%, sensitivity of 93.42%, specificity of 94.30%, and F1 score of 93.83% for the Apnea ECG dataset in per-segment classification. Our model excels on the UCDDB dataset with 87.20% accuracy, 80.99% sensitivity, 93.39% specificity, and an 86.34% F1-score. Furthermore, the model obtains 88.58% accuracy, 88.78% sensitivity, 88.38% specificity, and 88.61% F1 score on the MIT BIH polysomnographic dataset, showing its robust performance and balanced precision-recall trade-off. Afterwards, LIME, an explainable AI method, has been implemented to illustrate the insights responsible for predicting apnea or non apnea.

Development of Self-Powered Energy-Harvesting Electronic Module and Signal-Processing Framework for Wearable Healthcare Applications

A battery-operated biomedical wearable device gradually assists in clinical tasks to monitor patients' health states regarding early diagnosis and detection. This paper presents the development of a self-powered portable electronic module by integrating an onboard energy-harvesting facility for electrocardiogram (ECG) signal processing and personalized health monitoring. The developed electronic module provides a customizable approach to power the device using a lithium-ion battery, a series of silicon photodiode arrays, and a solar panel. The new architecture and techniques offered by the developed method include an analog front-end unit, a signal processing unit, and a battery management unit for the acquiring and processing of real-time ECG signals. The dynamic multi-level wavelet packet decomposition framework has been used and applied to an ECG signal to extract the desired features by removing overlapped and repeated samples from an ECG signal. Further, a random forest with deep decision tree (RFDDT) architecture has been designed for offline ECG signal classification, and experimental results provide the highest accuracy of 99.72%. One assesses the custom-developed sensor by comparing its data with those of conventional biosensors. The onboard energy-harvesting and battery management circuits are designed with a BQ25505 microprocessor with the support of silicon photodiodes and solar cells which detect the ambient light variations and provide a maximum of 4.2 V supply to enable the continuous operation of an entire module. The measurements conducted on each unit of the proposed method demonstrate that the proposed signal-processing method significantly reduces the overlapping samples from the raw ECG data and the timing requirement criteria for personalized and wearable health monitoring. Also, it improves temporal requirements for ECG data processing while achieving excellent classification performance at a low computing cost.

An Artificial Intelligence-Based Non-Invasive Approach for Cardiovascular Disease Risk Stratification in Obstructive Sleep Apnea Patients: A Narrative Review

Background

Obstructive sleep apnea (OSA) is a severe condition associated with numerous cardiovascular complications, including heart failure. The complex biological and morphological relationship between OSA and atherosclerotic cardiovascular disease (ASCVD) poses challenges in predicting adverse cardiovascular outcomes. While artificial intelligence (AI) has shown potential for predicting cardiovascular disease (CVD) and stroke risks in other conditions, there is a lack of detailed, bias-free, and compressed AI models for ASCVD and stroke risk stratification in OSA patients. This study aimed to address this gap by proposing three hypotheses: (i) a strong relationship exists between OSA and ASCVD/stroke, (ii) deep learning (DL) can stratify ASCVD/stroke risk in OSA patients using surrogate carotid imaging, and (iii) including OSA risk as a covariate with cardiovascular risk factors can improve CVD risk stratification.

Methods

The study employed the Preferred Reporting Items for Systematic reviews and Meta-analyses (PRISMA) search strategy, yielding 191 studies that link OSA with coronary, carotid, and aortic atherosclerotic vascular diseases. This research investigated the link between OSA and CVD, explored DL solutions for OSA detection, and examined the role of DL in utilizing carotid surrogate biomarkers by saving costs. Lastly, we benchmark our strategy against previous studies.

Results

(i) This study found that CVD and OSA are indirectly or directly related. (ii) DL models demonstrated significant potential in improving OSA detection and proved effective in CVD risk stratification using carotid ultrasound as a biomarker. (iii) Additionally, DL was shown to be useful for CVD risk stratification in OSA patients; (iv) There are important AI attributes such as AI-bias, AI-explainability, AI-pruning, and AI-cloud, which play an important role in CVD risk for OSA patients.

Conclusions

DL provides a powerful tool for CVD risk stratification in OSA patients. These results can promote several recommendations for developing unique, bias-free, and explainable AI algorithms for predicting ASCVD and stroke risks in patients with OSA.

MPCNN: A Novel Matrix Profile Approach for CNN-based Single Lead Sleep Apnea in Classification Problem

Sleep apnea (SA) is a significant respiratory condition that poses a major global health challenge. Deep Learning (DL) has emerged as an efficient tool for the classification problem in electrocardiogram (ECG)-based SA diagnoses. Despite these advancements, most common conventional feature extractions derived from ECG signals in DL, such as R-peaks and RR intervals, may fail to capture crucial information encompassed within the complete ECG segments. In this study, we propose an innovative approach to address this diagnostic gap by delving deeper into the comprehensive segments of the ECG signal. The proposed methodology draws inspiration from Matrix Profile algorithms, which generate an Euclidean distance profile from fixed-length signal subsequences. From this, we derived the Min Distance Profile (MinDP), Max Distance Profile (MaxDP), and Mean Distance Profile (MeanDP) based on the minimum, maximum, and mean of the profile distances, respectively. To validate the effectiveness of our approach, we use the modified LeNet-5 architecture as the primary CNN model, along with two existing lightweight models, BAFNet and SE-MSCNN. Our experiment results on the PhysioNet Apnea-ECG dataset (70 overnight recordings), and the UCDDB dataset (25 overnight recordings) revealed that our new feature extraction method achieved per-segment accuracies of up to 92.11% and 81.25%, respectively. Moreover, using the PhysioNet data, we achieved a per-recording accuracy of 100% and yielded the highest correlation of 0.989 compared to state-of-the-art methods. By introducing a new feature extraction method based on distance relationships, we enhanced the performance of certain lightweight models in DL, showing potential for home sleep apnea test (HSAT) and SA detection in IoT devices. The source code for this work is made publicly available in GitHub: https://github.com/vinuni-vishc/MPCNN-Sleep-Apnea.

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.

BAFNet: Bottleneck Attention Based Fusion Network for Sleep Apnea Detection

Sleep apnea (SA) is a common sleep-related breathing disorder that tends to induce a series of complications, such as pediatric intracranial hypertension, psoriasis, and even sudden death. Therefore, early diagnosis and treatment can effectively prevent malignant complications SA incurs. Portable monitoring (PM) is a widely used tool for people to monitor their sleep conditions outside of hospitals. In this study, we focus on SA detection based on single-lead electrocardiogram (ECG) signals which are easily collected by PM. We propose a bottleneck attention based fusion network named BAFNet, which mainly includes five parts of RRI (R-R intervals) stream network, RPA (R-peak amplitudes) stream network, global query generation, feature fusion, and classifier. To learn the feature representation of RRI/RPA segments, fully convolutional networks (FCN) with cross-learning are proposed. Meanwhile, to control the information flow between RRI and RPA networks, a global query generation with bottleneck attention is proposed. To further improve the SA detection performance, a hard sample scheme with k-means clustering is employed. Experiment results show that BAFNet can achieve competitive results, which are superior to the state-of-the-art SA detection methods. It means that BAFNet has great potential to be applied in the home sleep apnea test (HSAT) for sleep condition monitoring.

Wearable 12-Lead ECG Acquisition Using a Novel Deep Learning Approach from Frank or EASI Leads with Clinical Validation

The 12-lead electrocardiogram (ECG) is crucial in assessing patient decisions. However, portable ECG devices capable of acquiring a complete 12-lead ECG are scarce. For the first time, a deep learning-based method is proposed to reconstruct the 12-lead ECG from Frank leads (VX, VY, and VZ) or EASI leads (VES, VAS, and VAI). The innovative ECG reconstruction network called M2Eformer is composed of a 2D-ECGblock and a ProbDecoder module. The 2D-ECGblock module adaptively segments EASI leads into multi-periods based on frequency energy, transforming the 1D time series into a 2D tensor representing within-cycle and between-cycle variations. The ProbDecoder module aims to extract Probsparse self-attention and achieve one-step output for the target leads. Experimental results from comparing recorded and reconstructed 12-lead ECG using Frank leads indicate that M2Eformer outperforms traditional ECG reconstruction methods on a public database. In this study, a self-constructed database (10 healthy individuals + 15 patients) was utilized for the clinical diagnostic validation of ECG reconstructed from EASI leads. Subsequently, both the ECG reconstructed using EASI and the recorded 12-lead ECG were subjected to a double-blind diagnostic experiment conducted by three cardiologists. The overall diagnostic consensus among three cardiology experts, reaching a rate of 96%, indicates the significant utility of EASI-reconstructed 12-lead ECG in facilitating the diagnosis of cardiac conditions.

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.

Sleep apnea detection from single-lead electrocardiogram signals using effective deep-shallow fusion network

Objective.Explore a network architecture that can efficiently perform single-lead electrocardiogram (ECG) sleep apnea (SA) detection by utilizing the beneficial information of extended ECG segments and reducing the impact of their noisy information.Approach.We propose an effective deep-shallow fusion network (EDSFnet). The deeper residual network is used to extract high-level features with stronger semantics and less noise from the original ECG segments. The shallower convolutional neural network is used to extract lower-level features with higher resolution containing more detailed neighborhood information from the extended ECG segments. These two types of features are then fused using Effective Channel Attention, implementing automatic weight assignment to take advantage of their complementary nature.Main results.The performance of EDSFnet is evaluated on the Apnea-ECG dataset and the FAH-ECG dataset. In the Apnea-ECG dataset with 35 subjects as the training set and 35 subjects as the test set, the accuracy of EDSFnet was 92.6% and 100% for per-segment and per-recording test, respectively. In the FAH-ECG dataset with 348 subjects as the training set and 88 subjects as the test set, the accuracy of EDSFnet was 89.0% and 93.2% for per-segment and per-recording test, respectively. EDSFnet has achieved state-of-the-art results in both experiments using the publicly available Apnea-ECG dataset and subject-independent experiments using the FAH-ECG clinical dataset.Significance.The success of EDSFnet in handling SA detection underlines its robustness and adaptability. By achieving superior results across different datasets, EDSFnet offers promise in advancing the cost-effective and efficient detection of SA through single-lead ECG, reducing the burden on patients and healthcare systems alike.

Reseek-Arrhythmia: Empirical Evaluation of ResNet Architecture for Detection of Arrhythmia

Arrhythmia is a cardiac condition characterized by an irregular heart rhythm that hinders the proper circulation of blood, posing a severe risk to individuals' lives. Globally, arrhythmias are recognized as a significant health concern, accounting for nearly 12 percent of all deaths. As a result, there has been a growing focus on utilizing artificial intelligence for the detection and classification of abnormal heartbeats. In recent years, self-operated heartbeat detection research has gained popularity due to its cost-effectiveness and potential for expediting therapy for individuals at risk of arrhythmias. However, building an efficient automatic heartbeat monitoring approach for arrhythmia identification and classification comes with several significant challenges. These challenges include addressing issues related to data quality, determining the range for heart rate segmentation, managing data imbalance difficulties, handling intra- and inter-patient variations, distinguishing supraventricular irregular heartbeats from regular heartbeats, and ensuring model interpretability. In this study, we propose the Reseek-Arrhythmia model, which leverages deep learning techniques to automatically detect and classify heart arrhythmia diseases. The model combines different convolutional blocks and identity blocks, along with essential components such as convolution layers, batch normalization layers, and activation layers. To train and evaluate the model, we utilized the MIT-BIH and PTB datasets. Remarkably, the proposed model achieves outstanding performance with an accuracy of 99.35% and 93.50% and an acceptable loss of 0.688 and 0.2564, respectively.

Prediction of Sleep Apnea Events Using a CNN-Transformer Network and Contactless Breathing Vibration Signals

It is estimated that globally 425 million subjects have moderate to severe obstructive sleep apnea (OSA). The accurate prediction of sleep apnea events can offer insight into the development of treatment therapies. However, research related to this prediction is currently limited. We developed a covert framework for the prediction of sleep apnea events based on low-frequency breathing-induced vibrations obtained from piezoelectric sensors. A CNN-transformer network was utilized to efficiently extract local and global features from respiratory vibration signals for accurate prediction. Our study involved overnight recordings of 105 subjects. In five-fold cross-validation, we achieved an accuracy of 85.9% and an F1 score of 85.8%, which are 3.5% and 5.3% higher than the best-performed classical model, respectively. Additionally, in leave-one-out cross-validation, 2.3% and 3.8% improvements are observed, respectively. Our proposed CNN-transformer model is effective in the prediction of sleep apnea events. Our framework can thus provide a new perspective for improving OSA treatment modes and clinical management.

Electrocardiogram Monitoring Wearable Devices and Artificial-Intelligence-Enabled Diagnostic Capabilities: A Review

Worldwide, population aging and unhealthy lifestyles have increased the incidence of high-risk health conditions such as cardiovascular diseases, sleep apnea, and other conditions. Recently, to facilitate early identification and diagnosis, efforts have been made in the research and development of new wearable devices to make them smaller, more comfortable, more accurate, and increasingly compatible with artificial intelligence technologies. These efforts can pave the way to the longer and continuous health monitoring of different biosignals, including the real-time detection of diseases, thus providing more timely and accurate predictions of health events that can drastically improve the healthcare management of patients. Most recent reviews focus on a specific category of disease, the use of artificial intelligence in 12-lead electrocardiograms, or on wearable technology. However, we present recent advances in the use of electrocardiogram signals acquired with wearable devices or from publicly available databases and the analysis of such signals with artificial intelligence methods to detect and predict diseases. As expected, most of the available research focuses on heart diseases, sleep apnea, and other emerging areas, such as mental stress. From a methodological point of view, although traditional statistical methods and machine learning are still widely used, we observe an increasing use of more advanced deep learning methods, specifically architectures that can handle the complexity of biosignal data. These deep learning methods typically include convolutional and recurrent neural networks. Moreover, when proposing new artificial intelligence methods, we observe that the prevalent choice is to use publicly available databases rather than collecting new data.

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.

A review of automated sleep disorder detection

Automated sleep disorder detection is challenging because physiological symptoms can vary widely. These variations make it difficult to create effective sleep disorder detection models which support hu-man experts during diagnosis and treatment monitoring. From 2010 to 2021, authors of 95 scientific papers have taken up the challenge of automating sleep disorder detection. This paper provides an expert review of this work. We investigated whether digital technology and Artificial Intelligence (AI) can provide automated diagnosis support for sleep disorders. We followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines during the content discovery phase. We compared the performance of proposed sleep disorder detection methods, involving differ-ent datasets or signals. During the review, we found eight sleep disorders, of which sleep apnea and insomnia were the most studied. These disorders can be diagnosed using several kinds of biomedical signals, such as Electrocardiogram (ECG), Polysomnography (PSG), Electroencephalogram (EEG), Electromyogram (EMG), and snore sound. Subsequently, we established areas of commonality and distinctiveness. Common to all reviewed papers was that AI models were trained and tested with labelled physiological signals. Looking deeper, we discovered that 24 distinct algorithms were used for the detection task. The nature of these algorithms evolved, before 2017 only traditional Machine Learning (ML) was used. From 2018 onward, both ML and Deep Learning (DL) methods were used for sleep disorder detection. The strong emergence of DL algorithms has considerable implications for future detection systems because these algorithms demand significantly more data for training and testing when compared with ML. Based on our review results, we suggest that both type and amount of labelled data is crucial for the design of future sleep disorder detection systems because this will steer the choice of AI algorithm which establishes the desired decision support. As a guiding principle, more labelled data will help to represent the variations in symptoms. DL algorithms can extract information from these larger data quantities more effectively, therefore; we predict that the role of these algorithms will continue to expand.

Obstructive sleep apnea detection from single-lead electrocardiogram signals using one-dimensional squeeze-and-excitation residual group network

Obstructive sleep apnea (OSA), which has high morbidity and complications, is diagnosed via polysomnography (PSG). However, this method is expensive, time-consuming, and causes discomfort to the patient. Single-lead electrocardiogram (ECG) is a potential alternative to PSG for OSA diagnosis. Recent studies have successfully applied deep learning methods to OSA detection using ECG and obtained great success. However, most of these methods only focus on heart rate variability (HRV), ignoring the importance of ECG-derived respiration (EDR). In addition, they used relatively simple networks, and cannot extract more complex features. In this study, we proposed a one-dimensional squeeze-and-excitation (SE) residual group network to thoroughly extract the complementary information between HRV and EDR. We used the released and withheld sets in the Apnea-ECG dataset to develop and test the proposed method, respectively. In the withheld set, the method has an accuracy of 90.3%, a sensitivity of 87.6%, and a specificity of 91.9% for per-segment detection, indicating an improvement over existing methods for the same dataset. The proposed method can be integrated with wearable devices to realize inexpensive, convenient, and highly efficient OSA detectors.