Search Results (842)

Background: Obstructive sleep apnea is a sleep disorder that is linked to many health complications and can even be lethal in its severe form. Overnight polysomnography is the gold standard for diagnosing apnea, which is expensive, time-consuming, and requires manual analysis by a sleep expert. Artificial intelligence (AI)-embedded wearable device as a portable and less intrusive monitoring system is a highly desired alternative to polysomnography. However, AI models often require substantial storage capacity and computational power for edge inference which makes it a challenging task to implement the models in hardware with memory and power constraints. Methods: This study demonstrates the implementation of depth-wise separable convolution (DSC) as a resource-efficient alternative to spatial convolution (SC) for real-time detection of apneic activity. Single lead electrocardiogram (ECG) and oxygen saturation (SpO₂) signals were acquired from the PhysioNet databank. Using each type of convolution, three different models were developed using ECG, SpO₂, and model fusion. For both types of convolutions, the fusion models outperformed the models built on individual signals across all the performance metrics. Results: Although the SC-based fusion model performed the best, the DSC-based fusion model was 9.4, 1.85, and 11.3 times more energy efficient than SC-based ECG, SpO₂, and fusion models, respectively. Furthermore, the accuracy, precision, and specificity yielded by the DSC-based fusion model were comparable to those of the SC-based individual models (~95%, ~94%, and ~94%, respectively). Conclusions: DSC is commonly used in mobile vision tasks, but its potential in clinical applications for 1-D signals remains unexplored. While SC-based models outperform DSC in accuracy, the DSC-based model offers a more energy-efficient solution with acceptable performance, making it suitable for AI-embedded apnea detection systems. Full article

Sudden cardiac death (SCD) represents a critical acute cardiovascular event characterized by rapid onset of cardiac and respiratory arrest, posing a significant threat to patients due to its high fatality rate. Monitoring indices related to SCD using wearable devices holds profound implications for preemptive measures aimed at reducing the incidence of such life-threatening events. Hence, this study proposed a predictive algorithm for SCD leveraging single-lead electrocardiogram (ECG) signals featuring low signal-to-noise ratios. Initially, simulated electrode motion artifact noise was introduced to ideal ECG signals to emulate the signal conditions with low signal-to-noise ratios encountered in everyday scenarios. To meet the criteria of simplicity and cost-effectiveness required for wearable devices, the analysis focused exclusively on single-lead signals. The proposed algorithm in this study employed a lightweight machine learning approach to extract 12-dimensional features encompassing ventricular late potentials, T-wave electrical alternation, and corrected QT intervals from the signal. The algorithm achieved an average prediction accuracy of 93.22% within 30 min prior to SCD onset, and 95.43% when utilizing a normal sinus rhythm database as a control, demonstrating robust performance. Additionally, a comprehensive Sudden Cardiac Death Index (SCDI) was devised to quantify the risk of SCD, formulated by integrating pivotal two-dimensional features contributing significantly to the algorithm. This index effectively distinguishes high-risk signals indicative of SCD from normal signals, thereby offering valuable supplementary insights in clinical settings. Full article

Smart clothes equipped with flexible sensing systems provide a comfortable means to track health status in real time. Although these sensors are flexible and small, the core signal-processing units still rely on a conventional printed circuit board (PCB), making current health-monitoring devices bulky and inconvenient to wear. In this study, a printed fabric-based hybrid circuit was designed and prepared—with a series of characteristics, such as surface/sectional morphology, electrical properties, and stability—to study its reliability. Furthermore, to verify the function of the fabric-based circuit, simulations and measurements of the circuit, as well as the collection and processing of a normal adult’s electrophysiological signals, were conducted. Under 10,000 stretching and bending cycles with a certain elongation and bending angle, the resistance remained 0.27 Ω/cm and 0.64 Ω/cm, respectively, demonstrating excellent conductivity and reliability. Additionally, the results of the simulation and experiment showed that the circuit can successfully amplify weak electrocardiogram (ECG) signals with a magnification of 1600 times with environmental filtering and 50 Hz of industrial frequency interference. This technology can monitor human electrophysiological signals, such as ECGs, electromyograms (EMGs), and joint motion, providing valuable practical guidance for the unobtrusive monitoring of smart clothes. Full article

Coronary artery disease (CAD) is an irreversible and fatal disease. It necessitates timely and precise diagnosis to slow CAD progression. Electrocardiogram (ECG) and phonocardiogram (PCG), conveying abundant disease-related information, are prevalent clinical techniques for early CAD diagnosis. Nevertheless, most previous methods have relied on single-modal data, restricting their diagnosis precision due to suffering from information shortages. To address this issue and capture adequate information, the development of a multi-modal method becomes imperative. In this study, a novel multi-modal learning method is proposed to integrate both ECG and PCG for CAD detection. Along with deconvolution operation, a novel ECG-PCG coupling signal is evaluated initially to enrich the diagnosis information. After constructing a modified recurrence plot, we build a parallel CNN network to encode multi-modal information, involving ECG, PCG and ECG-PCG coupling deep-coding features. To remove irrelevant information while preserving discriminative features, we add an autoencoder network to compress feature dimension. Final CAD classification is conducted by combining support vector machine and optimal multi-modal features. The experiment is validated on 199 simultaneously recorded ECG and PCG signals from non-CAD and CAD subjects, and achieves high performance with accuracy, sensitivity, specificity and f1-score of 98.49%, 98.57%,98.57% and 98.89%, respectively. The result demonstrates the superiority of the proposed multi-modal method in overcoming information shortages of single-modal signals and outperforming existing models in CAD detection. This study highlights the potential of multi-modal deep-coding information, and offers a wider insight to enhance CAD diagnosis. Full article

(1) Background: Arrhythmias, or irregular heart rhythms, are a prevalent cardiovascular condition and are diagnosed using electrocardiogram (ECG) signals. Advances in deep learning have enabled automated analysis of these signals. However, the effectiveness of deep learning models depends greatly on the quality of signal preprocessing. This study evaluated the impact of different windowing techniques applied to Fourier transform-preprocessed ECG signals on the classification accuracy of deep learning models. (2) Methods: We applied three windowing techniques—Hamming, Hann, and Blackman—to transform ECG signals into the frequency domain. A one-dimensional convolutional neural network was employed to classify the ECG signals into five arrhythmia categories based on features extracted from each windowed signal. (3) Results: The Blackman window yielded the highest classification accuracy, with improved signal-to-noise ratio and reduced spectral leakage compared to the Hamming and Hann windows. (4) Conclusions: The choice of windowing technique significantly influences the effectiveness of deep learning models in ECG classification. Future studies should explore additional preprocessing methods and their clinical applications. Full article

Background/Objective: Atrial fibrillation [AF] is the most common arrhythmia encountered in clinical practice and significantly increases the risk of stroke, peripheral embolism, and mortality. With the rapid advancement in artificial intelligence [AI] technologies, there is growing potential to enhance the tools used in AF detection and diagnosis. This scoping review aimed to synthesize the current knowledge on the application of AI, particularly machine learning [ML], in identifying and diagnosing AF in clinical settings. Methods: Following the PRISMA ScR guidelines, a comprehensive search was conducted using the MEDLINE, PubMed, SCOPUS, and EMBASE databases, targeting studies involving AI, cardiology, and diagnostic tools. Precisely 2635 articles were initially identified. After duplicate removal and detailed evaluation of titles, abstracts, and full texts, 30 studies were selected for review. Additional relevant studies were included to enrich the analysis. Results: AI models, especially ML-based models, are increasingly used to optimize AF diagnosis. Deep learning, a subset of ML, has demonstrated superior performance by automatically extracting features from large datasets without manual intervention. Self-learning algorithms have been trained using diverse data, such as signals from 12-lead and single-lead electrocardiograms, and photoplethysmography, providing accurate AF detection across various modalities. Conclusions: AI-based models, particularly those utilizing deep learning, offer faster and more accurate diagnostic capabilities than traditional methods with equal or superior reliability. Ongoing research is further enhancing these algorithms using larger datasets to improve AF detection and management in clinical practice. These advancements hold promise for significantly improving the early diagnosis and treatment of AF. Full article

Wearables with photoplethysmography (PPG) sensors are being increasingly used in clinical research as a non-invasive, inexpensive method for remote monitoring of physiological health. Ensuring the accuracy and reliability of PPG-derived measurements is critical, as inaccuracies can impact research findings and clinical decisions. This paper systematically compares heart rate (HR) and heart rate variability (HRV) measures from PPG against an electrocardiogram (ECG) monitor in free-living settings. Two devices with PPG and one device with an ECG sensor were worn by 25 healthy volunteers for 10 days. PPG-derived HR and HRV showed reasonable accuracy and reliability, particularly during sleep, with mean absolute error < 1 beat for HR and 6–15 ms for HRV. The relative error of HRV estimated from PPG varied with activity type and was higher than during the resting state by 14–51%. The accuracy of HR/HRV was impacted by the proportion of usable data, body posture, and epoch length. The multi-scale peak and trough detection algorithm demonstrated superior performance in detecting beats from PPG signals, with an F1 score of 89% during sleep. The study demonstrates the trade-offs of utilizing PPG measurements for remote monitoring in daily life and identifies optimal use conditions by recommending enhancements. Full article

Bioelectrical signal measurements play a crucial role in clinical diagnosis and continuous health monitoring. Conventional wet electrodes, however, present limitations as they are conductive gel for skin irritation and/or have inflexibility. Here, we developed a cost-effective and user-friendly stretchable dry electrode constructed with a flexible network of Ag/AgCl nanowires embedded in polydimethylsiloxane (PDMS). We compared the performance of the stretched Ag/AgCl nanowire electrode with commonly used commercial wet electrodes to measure electrocardiogram (ECG), electromyogram (EMG), and electroencephalogram (EEG) signals. All the signal-to-noise ratios (SNRs) of the as-fabricated or stretched (50% tensile strain) Ag/AgCl nanowire electrodes are higher than that measured by commercial wet electrodes as well as other dry electrodes. The evaluation of ECG signal quality through waveform segmentation, the signal quality index (SQI), and heart rate variability (HRV) reveal that both the as-fabricated and stretched Ag/AgCl nanowire electrode produce high-quality signals similar to those obtained from commercial wet electrodes. The stretchable electrode exhibits high sensitivity and dependability in measuring EMG and EEG data, successfully capturing EMG signals associated with muscle activity and clearly recording α-waves in EEG signals during eye closure. Our stretchable dry electrode shows enhanced comfort, high sensitivity, and convenience for curved surface biosignal monitoring in clinical contexts. Full article

Fetal heart monitoring, as a crucial part of fetal monitoring, can accurately reflect the fetus’s health status in a timely manner. To address the issues of high computational cost, inability to observe fetal heart morphology, and insufficient accuracy associated with the traditional method of calculating the fetal heart rate using a four-channel maternal electrocardiogram (ECG), a method for extracting fetal QRS complexes from a single-channel non-invasive fetal ECG based on a multi-feature fusion neural network is proposed. Firstly, a signal entropy data quality detection algorithm based on the blind source separation method is designed to select maternal ECG signals that meet the quality requirements from all channel ECG data, followed by data preprocessing operations such as denoising and normalization on the signals. After being segmented by the sliding window method, the maternal ECG signals are calculated as data in four modes: time domain, frequency domain, time–frequency domain, and data eigenvalues. Finally, the deep neural network using three multi-feature fusion strategies—feature-level fusion, decision-level fusion, and model-level fusion—achieves the effect of quickly identifying fetal QRS complexes. Among the proposed networks, the one with the best performance has an accuracy of 95.85% and sensitivity of 97%. Full article

Pregnancy monitoring is always essential for pregnant women and fetuses. According to the report of WHO (World Health Organization), there were an estimated 287,000 maternal deaths worldwide in 2020. Regular hospital check-ups, although well established, are a burden for pregnant women because of frequent travelling or hospitalization. Therefore, home-based, long-term, non-invasive health monitoring is one of the hot research areas. In recent years, with the development of wearable sensors and related data-processing technologies, pregnancy monitoring has become increasingly convenient. This article presents a review on recent research in wearable sensors, physiological data processing, and artificial intelligence (AI) for pregnancy monitoring. The wearable sensors mainly focus on physiological signals such as electrocardiogram (ECG), uterine contraction (UC), fetal movement (FM), and multimodal pregnancy-monitoring systems. The data processing involves data transmission, pre-processing, and application of threshold-based and AI-based algorithms. AI proves to be a powerful tool in early detection, smart diagnosis, and lifelong well-being in pregnancy monitoring. In this review, some improvements are proposed for future health monitoring of pregnant women. The rollout of smart wearables and the introduction of AI have shown remarkable potential in pregnancy monitoring despite some challenges in accuracy, data privacy, and user compliance. Full article

Electrocardiographic signals (ECG) are ubiquitous, which justifies the research of their optimal storage and transmission. However, proposals for non-uniform signal sampling must take into account the priority of diagnostic data accuracy and record integrity, as well as robustness to noise and interference. In this study, two novel methods are introduced, each utilizing a distinct neural network architecture for optimizing non-uniform sampling of ECG signal. A transformer model refines each time point selection through an iterative process using gradient descent optimization, with the goal of minimizing the mean squared error between the original and resampled signals. It adaptively modifies time points, which improves the alignment between both signals. In contrast, the Temporal Convolutional Network model trains on the original signal, and gradient descent optimization is utilized to improve the selection of time points. Evaluation of both strategies’ efficacy is performed by calculating signal distances at lower and higher sampling rates. First, a collection of synthetic data points that resembled the P-QRS-T wave was used to train the model. Then, the ECG-ID database for real data analysis was used. Filtering to remove baseline wander followed by evaluation and testing were carried out in the real patient data. The results, in particular MSE = 0.0005, RMSE = 0.0216, and Pearson’s CC = 0.9904 for 120 sps in the case of the transformer patient data model, provide viable paths for maintaining the precision and dependability of ECG-based diagnostic systems at much lower sampling rate. Outcomes indicate that both techniques are effective at improving the fidelity between the original and modified ECG signals. Full article

This paper is concerned with an end-to-end electrocardiogram (ECG) signal transformation from a continuous-wave (CW) radar signal using a specialized deep learning model. For this purpose, the presented deep learning model is designed using convolutional neural networks (CNNs) and bidirectional long short-term memory (Bi-LSTM) with a maximum-overlap discrete wavelet transform (MODWT) layer and an adaptive neuro-fuzzy network (ANFN) layer. The proposed method has the advantage of developing existing deep networks and machine learning to reconstruct signals through CW radars to acquire ECG biological information in a non-contact manner. The fully connected (FC) layer of the CNN is replaced by an ANFN layer suitable for resolving black boxes and handling complex nonlinear data. The MODWT layer is activated via discrete wavelet transform frequency decomposition with maximum-overlap to extract ECG-related frequency components from radar signals to generate essential information. In order to evaluate the performance of the proposed model, we use a dataset of clinically recorded vital signs with a synchronized reference sensor signal measured simultaneously. As a result of the experiment, the performance is evaluated by the mean squared error (MSE) between the measured and reconstructed ECG signals. The experimental results reveal that the proposed model shows good performance in comparison to the existing deep learning model. From the performance comparison, we confirm that the ANFN layer preserves the nonlinearity of information received from the model by replacing the fully connected layer used in the conventional deep learning model. Full article

Sleep apnea (SA) is a prevalent disorder characterized by recurrent events of nocturnal apnea. Polysomnography (PSG) represents the gold standard for SA diagnosis. This laboratory-based procedure is complex and costly, and less cumbersome wearable devices have been proposed for SA detection and monitoring. A novel textile multi-sensor monitoring belt recording electrocardiogram (ECG) and breathing frequency (BF) measured by thorax excursion was developed and tested in a sleep laboratory for validation purposes. The aim of the current study was to evaluate the diagnostic performance of ECG-derived heart rate variability and BF-derived breathing rate variability and their combination for the detection of sleep apnea in a population of patients with a suspicion of SA. Fifty-one patients with a suspicion of SA were recruited in the sleep laboratory of the Cantonal Hospital St. Gallen. Patients were equipped with the monitoring belt and underwent a single overnight laboratory-based PSG. In addition, some patients further tested the monitoring belt at home. The ECG and BF signals from the belt were compared to PSG signals using the Bland-Altman methodology. Heart rate and breathing rate variability analyses were performed. Features derived from these analyses were used to build a support vector machine (SVM) classifier for the prediction of SA severity. Model performance was assessed using receiver operating characteristics (ROC) curves. Patients included 35 males and 16 females with a median age of 49 years (range: 21 to 65) and a median apnea-hypopnea index (AHI) of 33 (IQR: 16 to 58). Belt-derived data provided ECG and BF signals with a low bias and in good agreement with PSG-derived signals. The combined ECG and BF signals improved the classification accuracy for SA (area under the ROC curve: 0.98; sensitivity and specificity greater than 90%) compared to single parameter classification based on either ECG or BF alone. This novel wearable device combining ECG and BF provided accurate signals in good agreement with the gold standard PSG. Due to its unobtrusive nature, it is potentially interesting for multi-night assessments and home-based patient follow-up. Full article

Introduction: Accurately detecting arousal events during sleep is essential for evaluating sleep quality and diagnosing sleep disorders, such as sleep apnea/hypopnea syndrome. While the American Academy of Sleep Medicine guidelines associate arousal events with electroencephalogram (EEG) signal variations, EEGs are often not recorded during home sleep testing (HST) using wearable devices or smartphone applications. Objectives: The primary objective of this study was to explore the potential of alternatively relying on combinations of easily measurable physiological signals during HST for arousal detection where EEGs are not recorded. Methods: We conducted a data-driven retrospective study following an incremental device-agnostic analysis approach, where we simulated a limited-channel setting using polysomnography data and used deep learning to automate the detection task. During the analysis, we tested multiple signal combinations to evaluate their potential effectiveness. We trained and evaluated the model on the Multi-Ethnic Study of Atherosclerosis dataset. Results: The results demonstrated that combining multiple signals significantly improved performance compared with single-input signal models. Notably, combining thoracic effort, heart rate, and a wake/sleep indicator signal achieved competitive performance compared with the state-of-the-art DeepCAD model using electrocardiogram as input with an average precision of 61.59% and an average recall of 56.46% across the test records. Conclusions: This study demonstrated the potential of combining easy-to-record HST signals to characterize the autonomic markers of arousal better. It provides valuable insights to HST device designers on signals that improve EEG-free arousal detection. Full article

There are two widely used methods to measure the cardiac cycle and obtain heart rate measurements: the electrocardiogram (ECG) and the photoplethysmogram (PPG). The sensors used in these methods have gained great popularity in wearable devices, which have extended cardiac monitoring beyond the hospital environment. However, the continuous monitoring of ECG signals via mobile devices is challenging, as it requires users to keep their fingers pressed on the device during data collection, making it unfeasible in the long term. On the other hand, the PPG does not contain this limitation. However, the medical knowledge to diagnose these anomalies from this sign is limited by the need for familiarity, since the ECG is studied and used in the literature as the gold standard. To minimize this problem, this work proposes a method, PPG2ECG, that uses the correlation between the domains of PPG and ECG signals to infer from the PPG signal the waveform of the ECG signal. PPG2ECG consists of mapping between domains by applying a set of convolution filters, learning to transform a PPG input signal into an ECG output signal using a U-net inception neural network architecture. We assessed our proposed method using two evaluation strategies based on personalized and generalized models and achieved mean error values of 0.015 and 0.026, respectively. Our method overcomes the limitations of previous approaches by providing an accurate and feasible method for continuous monitoring of ECG signals through PPG signals. The short distances between the infer-red ECG and the original ECG demonstrate the feasibility and potential of our method to assist in the early identification of heart diseases. Full article