Search Results (672)

Background/Objectives: Heart rate variability (HRV) has been widely investigated as a predictor of disease and mortality across diverse patient populations; however, there remains no consensus on the optimal set or combination of time and frequency domain nor on nonlinear features for reliable prediction across clinical contexts. Given the relevance of the COVID-19 pandemic and the unique clinical profiles of these patients, this retrospective observational study explored the potential of HRV analysis for early prediction of in-hospital mortality using ECG signals recorded during the initial moments of ICU admission in COVID-19 patients. Methods: HRV indices were extracted from four ECG leads (I, II, III, and aVF) using sliding windows of 2, 5, and 7 min across observation intervals of 15, 30, and 60 min. The raw data posed significant challenges in terms of structure, synchronization, and signal quality; thus, from an original set of 381 records from 321 patients, after data pre-processing steps, a final dataset of 82 patients was selected for analysis. To manage data complexity and evaluate predictive performance, two feature selection methods, four feature reduction techniques, and five classification models were applied to identify the optimal approach. Results: Among the feature aggregation methods, compiling feature means across patient windows (Method D) yielded the best results, particularly for longer observation intervals (e.g., using LDA, the best AUC of $0.82\pm 0.13$ was obtained with Method D versus $0.63\pm 0.09$ with Method C using 5 min windows). Linear Discriminant Analysis (LDA) was the most consistent classification algorithm, demonstrating robust performance across various time windows and further improvement with dimensionality reduction. Although Gradient Boosting and Random Forest also achieved high AUCs and F1-scores, their performance outcomes varied across time intervals. Conclusions: These findings support the feasibility and clinical relevance of using short-term HRV as a noninvasive, data-driven tool for early risk stratification in critical care, potentially guiding timely therapeutic decisions in high-risk ICU patients and thereby reducing in-hospital mortality. Full article

Ergonomic risk classification during manual lifting tasks is crucial for the prevention of workplace injuries. This study addresses the challenge of classifying lifting task risk levels (low, medium, and high risk, labeled as 0, 1, and 2) using multi-modal time-series data comprising raw facial landmarks and bio-signals (electrocardiography [ECG] and electrodermal activity [EDA]). Classifying such data presents inherent challenges due to multi-source information, temporal dynamics, and class imbalance. To overcome these challenges, this paper proposes a Multi-Adaptive Functional Neural Network (Multi-AdaFNN), a novel method that integrates functional data analysis with deep learning techniques. The proposed model introduces a novel adaptive basis layer composed of micro-networks tailored to each individual time-series feature, enabling end-to-end learning of discriminative temporal patterns directly from raw data. The Multi-AdaFNN approach was evaluated across five distinct dataset configurations: (1) facial landmarks only, (2) bio-signals only, (3) full fusion of all available features, (4) a reduced-dimensionality set of 12 selected facial landmark trajectories, and (5) the same reduced set combined with bio-signals. Performance was rigorously assessed using 100 independent stratified splits (70% training and 30% testing) and optimized via a weighted cross-entropy loss function to manage class imbalance effectively. The results demonstrated that the integrated approach, fusing facial landmarks and bio-signals, achieved the highest classification accuracy and robustness. Furthermore, the adaptive basis functions revealed specific phases within lifting tasks critical for risk prediction. These findings underscore the efficacy and transparency of the Multi-AdaFNN framework for multi-modal ergonomic risk assessment, highlighting its potential for real-time monitoring and proactive injury prevention in industrial environments. Full article

Ventricular arrhythmias (VAs) are critical cardiovascular diseases that require rapid and accurate detection. Conventional approaches relying on multi-lead ECG or deep learning models have limitations in computational cost, interpretability, and real-time applicability on wearable devices. To address these issues, a lightweight and interpretable framework based on multiple complex networks was proposed for the detection of life-threatening VAs using short-term single-lead ECG signals. The input signals were decomposed using the fixed-frequency-range empirical wavelet transform, and sub-bands were subsequently analyzed through multiscale visibility graphs, recurrence networks, cross-recurrence networks, and joint recurrence networks. Eight topological features were extracted and input into an XGBoost classifier for VA identification. Ten-fold cross-validation results on the MIT-BIH VFDB and CUDB databases demonstrated that the proposed method achieved a sensitivity of 99.02 ± 0.53%, a specificity of 98.44 ± 0.43%, and an accuracy of 98.73 ± 0.02% for 10 s ECG segments. The model also maintained robust performance on shorter segments, with 97.23 ± 0.76% sensitivity, 98.85 ± 0.95% specificity, and 96.62 ± 0.02% accuracy on 2 s segments. The results outperformed existing feature-based and deep learning approaches while preserving model interpretability. Furthermore, the proposed method supports mobile deployment, facilitating real-time use in wearable healthcare applications. Full article

Accurate sleep staging and sleep-disordered breathing (SDB) severity prediction are critical for the early diagnosis and management of sleep disorders. However, real-world polysomnography (PSG) data often suffer from modality heterogeneity, label scarcity, and non-independent and identically distributed (non-IID) characteristics across institutions, posing significant challenges for model generalization and clinical deployment. To address these issues, we propose a federated multi-task learning (FMTL) framework that simultaneously performs sleep staging and SDB severity classification from seven multimodal physiological signals, including EEG, ECG, respiration, etc. The proposed framework is built upon a hybrid deep neural architecture that integrates convolutional layers (CNN) for spatial representation, bidirectional GRUs for temporal modeling, and multi-head self-attention for long-range dependency learning. A shared feature extractor is combined with task-specific heads to enable joint diagnosis, while the FedAvg algorithm is employed to facilitate decentralized training across multiple institutions without sharing raw data, thereby preserving privacy and addressing non-IID challenges. We evaluate the proposed method across three public datasets (APPLES, SHHS, and HMC) treated as independent clients. For sleep staging, the model achieves accuracies of 85.3% (APPLES), 87.1% (SHHS_rest), and 79.3% (HMC), with Cohen’s Kappa scores exceeding 0.71. For SDB severity classification, it obtains macro-F1 scores of 77.6%, 76.4%, and 79.1% on APPLES, SHHS_rest, and HMC, respectively. These results demonstrate that our unified FMTL framework effectively leverages multimodal PSG signals and federated training to deliver accurate and scalable sleep disorder assessment, paving the way for the development of a privacy-preserving, generalizable, and clinically applicable digital sleep monitoring system. Full article

In recent decades, flexible electronics have witnessed remarkable advancements in multiple fields, encompassing wearable electronics, human–machine interfaces (HMI), clinical diagnosis, and treatment, etc. Nevertheless, conventional rigid electronic devices are fundamentally constrained by their inherent non-stretchability and poor conformability, limitations that substantially impede their practical applications. In contrast, conductive hydrogels (CHs) for electronic skin (E-skin) and healthcare monitoring have attracted substantial interest owing to outstanding features, including adjustable mechanical properties, intrinsic flexibility, stretchability, transparency, and diverse functional and structural designs. Considerable efforts focus on developing CHs incorporating various conductive materials to enable multifunctional wearable sensors and flexible electrodes, such as metals, carbon, ionic liquids (ILs), MXene, etc. This review presents a comprehensive summary of the recent advancements in CHs, focusing on their classifications and practical applications. Firstly, CHs are categorized into five groups based on the nature of the conductive materials employed. These categories include polymer-based, carbon-based, metal-based, MXene-based, and ionic CHs. Secondly, the promising applications of CHs for electrophysiological signals and healthcare monitoring are discussed in detail, including electroencephalogram (EEG), electrocardiogram (ECG), electromyogram (EMG), respiratory monitoring, and motion monitoring. Finally, this review concludes with a comprehensive summary of current research progress and prospects regarding CHs in the fields of electronic skin and health monitoring applications. Full article

Background: Cardiovascular diseases are the leading cause of global mortality, with 80% of coronary heart disease in patients over 65. Understanding aging cardiovascular structures is crucial. Photon-counting computed tomography (PCCT) offers improved spatial and temporal resolution and better signal-to-noise ratio, enabling texture analysis in clinical routines. Detecting structural changes in aging left-ventricular myocardium may help predict cardiovascular risk. Methods: In this retrospective, single-center, IRB-approved study, 90 patients underwent ECG-gated contrast-enhanced cardiac CT using dual-source PCCT (NAEOTOM Alpha, Siemens). Patients were divided into two age groups (50–60 years and 70–80 years). The left ventricular myocardium was segmented semi-automatically, and radiomics features were extracted using pyradiomics to compare myocardial texture features. Epicardial adipose tissue (EAT) density, thickness, and other clinical parameters were recorded. Statistical analysis was conducted with R and a Python-based random forest classifier. Results: The study assessed 90 patients (50–60 years, n = 54, and 70–80 years, n = 36) with a mean age of 63.6 years. No significant differences were found in mean Agatston score, gender distribution, or conditions like hypertension, diabetes, hypercholesterolemia, or nicotine abuse. EAT measurements showed no significant differences. The Random Forest Classifier achieved a training accuracy of 0.95 and a test accuracy of 0.74 for age group differentiation. Wavelet-HLH_glszm_GrayLevelNonUniformity was a key differentiator. Conclusions: Radiomics texture features of the left ventricular myocardium outperformed conventional parameters like EAT density and thickness in differentiating age groups, offering a potential imaging biomarker for myocardial aging. Radiomics analysis of left ventricular myocardium offers a unique opportunity to visualize changes in myocardial texture during aging and could serve as a cardiac risk predictor. Full article

This paper presents a methodology for extracting and simulating arterial pulse waveform signals from Fabry–Perot interferometric measurements, emphasizing a practical approach for noninvasive cardiovascular assessment. A key novelty of this work is the presentation of a complete Python-based processing pipeline, which is made publicly available as open-source code on GitHub (git version 2.39.5). To the authors’ knowledge, no such repository for demodulating these specific interferometric signals to obtain a raw arterial pulse waveform previously existed. The proposed system utilizes accessible Python-based preprocessing steps, including outlier removal, Butterworth high-pass filtering, and min–max normalization, designed for robust signal quality even in settings with common physiological artifacts. Key features such as the rate of change, the Hilbert transform of the rate of change (envelope), and detected extrema guide the signal reconstruction, offering a computationally efficient pathway to reveal its periodic and phase-dependent dynamics. Visual analyses highlight amplitude variations and residual noise sources, primarily attributed to sensor bandwidth limitations and interpolation methods, considerations critical for real-world deployment. Despite these practical challenges, the reconstructed arterial pulse waveform signals provide valuable insights into arterial motion, with the methodology’s performance validated on measurements from three subjects against synchronized ECG recordings. This demonstrates the viability of Fabry–Perot sensors as a potentially cost-effective and readily implementable tool for noninvasive cardiovascular diagnostics. The results underscore the importance of precise yet practical signal processing techniques and pave the way for further improvements in interferometric sensing, bio-signal analysis, and their translation into clinical practice. Full article

Background: Early identification of left ventricular ejection fraction (LVEF) levels during the progression of hypertension is essential to prevent cardiac deterioration. However, achieving a non-invasive, cost-effective, and definitive assessment is challenging. It has prompted us to develop a comprehensive machine learning framework for the automatic quantitative estimation of LVEF levels from electrocardiography (ECG) signals. Methods: We enrolled 200 hypertensive patients from Zhongshan City, Guangdong Province, China, from 1 November 2022 to 1 January 2025. Participants underwent 24 h Holter monitoring and echocardiography for LVEF estimation. We developed a comprehensive machine learning framework that initiated with preprocessed ECG signal in one-hour intervals to extract CMSE-based heart rate variability (HRV) features, then utilized machine learning models such as linear regression (LR), Support Vector Machines (SVMs), and random forests (RFs) with recursive feature elimination for optimal LVEF estimation. Results: The LR model, notably during early night interval (20:00–21:00), achieved a RMSE of 4.61% and a MAE of 3.74%, highlighting its superiority. Compared with other similar studies, key CMSE parameters (Scales 1, 5, Slope 1–5, and Area 1–5) can effectively enhance regression models’ estimation performance. Conclusion: Our findings suggest that CMSE-derived circadian HRV features from Holter ECG could serve as a non-invasive, cost-effective, and interpretable solution for LVEF assessment in community settings. From a machine learning interpretable perspective, the proposed method emphasized CMSE’s clinical potential in capturing autonomic dynamics and cardiac function fluctuations. Full article

Cardiovascular diseases remain one of the leading causes of mortality worldwide, highlighting the importance of effective monitoring and early diagnosis. While electrocardiography (ECG) is the standard technique for evaluating the heart’s electrical activity and detecting rhythm and conduction abnormalities, it alone is insufficient for identifying certain conditions, such as valvular disorders. Phonocardiography (PCG) allows the recording and analysis of heart sounds and improves the diagnostic accuracy when combined with ECG. In this study, ECG and PCG signals were simultaneously acquired from a resting adult subject using a compact system comprising an analog front-end (model AD8232, manufactured by Analog Devices, Wilmington, MA, USA) for ECG acquisition and a digital stethoscope built around a condenser electret microphone (model HM-9250, manufactured by HMYL, Anqing, China). Both the ECG electrodes and the microphone were positioned on the chest to ensure the spatial alignment of the signals. An adaptive segmentation algorithm was developed to segment PCG and ECG signals based on their morphological and temporal features. This algorithm identifies the onset and peaks of S1 and S2 heart sounds in the PCG and the Q, R, and S waves in the ECG, enabling the extraction of the systolic time intervals such as EMAT, PEP, LVET, and LVST parameters proven useful in the diagnosis and monitoring of cardiovascular diseases. Based on the segmented signals, the measured averages (EMAT = 74.35 ms, PEP = 89.00 ms, LVET = 244.39 ms, LVST = 258.60 ms) were consistent with the reference standards, demonstrating the reliability of the developed method. The proposed algorithm was validated on synchronized ECG and PCG signals from multiple subjects in an open-source dataset (BSSLAB Localized ECG Data). The systolic intervals extracted using the proposed method closely matched the literature values, confirming the robustness across different recording conditions; in detail, the mean Q–S1 interval was 40.45 ms (≈45 ms reference value, mean difference: −4.85 ms, LoA: −3.42 ms and −6.09 ms) and the R–S1 interval was 14.09 ms (≈15 ms reference value, mean difference: −1.2 ms, LoA: −0.55 ms and −1.85 ms). In conclusion, the results demonstrate the potential of the joint ECG and PCG analysis to improve the long-term monitoring of cardiovascular diseases. Full article

The electrocardiogram (ECG) signal plays a crucial role in medical diagnosis, home care, and exercise intensity assessment. However, traditional ECG monitoring devices are difficult to blend with users’ daily routines due to their lack of portability, poor wearability, and inconvenient electrode usage methods. Therefore, utilizing reusable and cost-effective flexible bioelectrodes (with a signal-to-noise ratio of 33 dB), a miniaturized wearable system (MWS) is proposed for unconstrained ECG monitoring, which holds a size of 65 × 52 × 12 mm³ and a weight of 69 g. Given these compelling features, this system enables reliable and high-quality ECG signal monitoring in individuals’ daily activities, including sitting, walking, and cycling, with the acquired signals exhibiting distinguishable QRS characteristics. Furthermore, an exercise intensity classification model was developed based on ECG characteristics and a fully connected neural network (FCNN) algorithm, with an evaluation accuracy of 98%. These results exhibit the promising potential of the MWS in tracking individuals’ physiological signals and assessing exercise intensity. Full article

Traditional relaxation techniques such as meditation and slow breathing often rely on subjective self-assessment, making it difficult to objectively monitor physiological changes. Electrocardiograms (ECG), which are commonly used by clinicians, provide one-dimensional signals to interpret cardiovascular activity. In this study, we introduce a visual interpretation framework that transforms heart rate variability (HRV) time series into fuzzy recurrence plots (FRPs). Unlike ECGs’ linear traces, FRPs are two-dimensional images that reveal distinctive textural patterns corresponding to autonomic changes. These visually rich patterns make it easier for even non-experts with minimal training to track changes in relaxation states. To enable automated detection, we propose a multi-domain feature fusion framework suitable for wearable systems. HRV data were collected from 60 participants during spontaneous and slow-paced breathing sessions. Features were extracted from five domains: time, frequency, non-linear, geometric, and image-based. Feature selection was performed using the Fisher discriminant ratio, correlation filtering, and greedy search. Among six evaluated classifiers, support vector machine (SVM) achieved the highest performance, with 96.6% accuracy and 100% specificity using only three selected features. Our approach offers both human-interpretable visual feedback through FRP and accurate automated detection, making it highly promising for objectively monitoring real-time stress and developing biofeedback systems in wearable devices. Full article

The electrocardiogram (ECG) is one of the vital physiological signals for human health. Lightweight neural network (NN) models integrated into a low-resource wearable device can benefit the user with a low-power, real-time edge computing system for continuous and daily monitoring. This work introduces a novel edge-computing wearable device for real-time beat-by-beat ECG arrhythmia classification. The proposed wearable integrates the light AI model into a 32-bit ARM^® Cortex^™-based custom printed circuit board (PCB). The work analyzes the performance of artificial neural network (ANN), convolutional neural network (CNN), and long short-term memory (LSTM) models for real-time wearable implementation. The wearable is capable of real-time QRS detection and feature extraction from raw ECG data. The QRS detection algorithm offers high reliability with a 99.5% F1 score and R-peak position error (RPE) of 6.3 ms for R-peak-to-R-peak intervals. The proposed method implements a combination of top time series, spectral, and signal-specific features for model development. Lightweight, pretrained models are deployed on the custom wearable and evaluated in real time using mock data from the MIT-BIH dataset. We propose an LSTM model that provides efficient performance over accuracy, inference latency, and memory consumption. The proposed model offers 98.1% accuracy, with 98.2% sensitivity and 99.5% specificity while testing in real time on the wearable. Real-time inferencing takes 20 ms, and the device consumes as low as 5.9 mA of power. The proposed method achieves efficient performance in real-time testing, which indicates the wearable can be effectively used for real-time continuous arrhythmia detection. Full article

Accurate classification of electrocardiogram (ECG) signals is vital for reliable arrhythmia diagnosis and informed clinical decision-making, yet real-world datasets often suffer severe class imbalance that degrades recall and F1-score. To address these limitations, we introduce MAK-Net, a hybrid deep learning framework that combines: (1) a four-branch multiscale convolutional module for comprehensive feature extraction across diverse waveform morphologies; (2) an efficient channel attention mechanism for adaptive weighting of clinically salient segments; (3) bidirectional gated recurrent units (BiGRU) to capture long-range temporal dependencies; and (4) Kolmogorov–Arnold Network (KAN) layers with learnable spline activations for enhanced nonlinear representation and interpretability. We further mitigate imbalance by synergistically applying focal loss and the Synthetic Minority Oversampling Technique (SMOTE). On the MIT-BIH arrhythmia database, MAK-Net attains state-of-the-art performance—0.9980 accuracy, 0.9888 F1-score, 0.9871 recall, 0.9905 precision, and 0.9991 specificity—demonstrating superior robustness to imbalanced classes compared with existing methods. These findings validate the efficacy of multiscale feature fusion, attention-guided learning, and KAN-based nonlinear mapping for automated, clinically reliable arrhythmia detection. Full article

In fiber Bragg grating (FBG) sensing demodulation systems, high-precision peak detection is a core requirement for demodulation algorithms. However, practical spectral signals are often susceptible to environmental noise interference, which leads to significant degradation in the accuracy of traditional demodulation methods. This study proposes a self-adaptive K-SVD (SAK-SVD) denoising algorithm based on adaptive window parameter optimization, establishing a closed-loop iterative feedback mechanism through dual iterations between dictionary learning and parameter adjustment. This approach achieves a synergistic enhancement of noise suppression and signal fidelity. First, a dictionary learning framework based on K-SVD is constructed for initial denoising, and the peak feature region is extracted by differentiating the denoised signals. By constructing statistics on the number of sign changes, an adaptive adjustment model for the window size is established. This model dynamically tunes the window parameters in dictionary learning for iterative denoising, establishing a closed-loop architecture that integrates denoising evaluation with parameter optimization. The performance of SAK-SVD is evaluated through three experimental scenarios, demonstrating that SAK-SVD overcomes the rigid parameter limitations of traditional K-SVD in FBG spectral processing, enhances denoising performance, and thereby improves wavelength demodulation accuracy. For denoising undistorted waveforms, the optimal mean absolute error (MAE) decreases to 0.300 pm, representing a 25% reduction compared to the next-best method. For distorted waveforms, the optimal MAE drops to 3.9 pm, achieving a 63.38% reduction compared to the next-best method. This study provides both theoretical and technical support for high-precision fiber-optic sensing under complex working conditions. Crucially, the SAK-SVD framework establishes a universal, adaptive denoising paradigm for fiber Bragg grating (FBG) sensing. This paradigm has direct applicability to Raman spectroscopy, industrial ultrasound-based non-destructive testing, and biomedical signal enhancement (e.g., ECG artefact removal), thereby advancing high-precision measurement capabilities across photonics and engineering domains. Full article

ECG monitoring is central to the early detection of cardiac abnormalities. We compared 28 manually selected signal-specific features with 159 automatically extracted signal-independent descriptors from the MIT BIH Arrhythmia Database. ANOVA reduced features to the 10 most informative attributes, which were evaluated alone and in combination with the signal-specific features using Random Forest, SVM, and deep neural networks (CNN, RNN, ANN, LSTM) under an interpatient 80/20 split. Merging the two feature groups delivered the best results: a 128-layer CNN achieved 100% accuracy. Power profiling revealed that deeper models improve accuracy at the cost of runtime, memory, and CPU load, underscoring the trade-off faced in edge deployments. The proposed hybrid feature strategy provides beat-by-beat classification with a reduction in the number of features, enabling real-time ECG screening on wearable and IoT devices. Full article