Search Results (564)

Electromyographic (EMG) signals encode complex spatiotemporal dynamics reflecting neuromuscular coordination and pharmacological modulation. This study introduces a unified Hankel–topological framework for reconstructing and analyzing long-duration EMG recordings acquired from pigs under pharmacological influence, and for quantifying their bioelectrical organization. The method couples low-rank Hankel representations—capturing temporal redundancy and smoothness—with topological continuity constraints that stabilize activity packets defined by 5 s silence intervals. Six pigs were recorded across four experimental sessions (24 h each; four channels), and envelope reconstruction was performed using an ADMM-based solver. Quantitative analysis revealed consistent post-drug reductions in the packet rate ($-24.9\%$), the mean duration ($-2.3$ s), the amplitude ($-0.16$ a.u.), the effective Hankel rank ($-3.0$), and topological diversity ($\Delta {\beta }_0=-1.2$; all $p<0.01$). Deeper channels exhibited stronger suppression (interaction $p<0.02$), suggesting depth-dependent neuromuscular effects. The proposed framework unifies dynamical, statistical, and topological perspectives on EMG structure and yields interpretable biomarkers of neuromuscular inhibition and recovery. More broadly, it provides a generalizable signal processing methodology for analyzing structured, noisy physiological time series beyond EMG. Full article

Multimodal epileptic seizure detection using physiological biosignals remains challenging due to signal noise, inter-subject variability, weak cross-modal alignment, and the limited interpretability of many machine learning models. To address these challenges, this study proposes a parameterized multimodal feature-fusion framework that unifies normalization, modality weighting, and nonlinear cross-modal interaction within a single mathematical representation. Four fusion parameters, the fusion exponent $\rho$, interaction weight $\left(\delta \right)$, normalization factor $\left(\lambda \right),$ and the cross-modal interaction term $\left(\eta \right)$, are introduced at the feature-fusion level, while all classifiers retain their original learning mechanisms. The framework is evaluated using synchronized EEG, ECG, EMG, and accelerometer signals from 120 subjects, segmented into 2 s windows at 512 Hz and analyzed using twelve classical and deep learning classifiers. Principal Component Analysis (PCA) applied to the fused feature space reveals improved class separability compared to unimodal representations, with EEG exhibiting the strongest intrinsic discrimination and peripheral modalities contributing complementary structure when fused. SHapley Additive exPlanations (SHAP) further identify entropy as the most influential feature across all modalities, followed by RMS and energy, yielding physiologically coherent attributions. Quantitative performance evaluation and ablation analysis confirm that the observed improvements arise from the proposed representation design rather than classifier-specific modifications. Unlike existing architecture-dependent fusion strategies, the proposed method introduces a mathematically parameterized feature-space formulation that enhances separability and interpretability without modifying classifier architectures, thereby establishing a representation-driven paradigm for explainable multimodal seizure detection. These results demonstrate that mathematically principled feature-space modeling can simultaneously enhance predictive performance and interpretability, providing a transparent and robust foundation for explainable multimodal seizure detection. Full article

BCI biosensors enable continuous monitoring of neural activity, but existing systems face challenges in scalability, latency, and reliable integration with cloud infrastructure. This work presents a cloud-aware, real-time cognitive grid architecture for multimodal BCI biosensors, validated at the system level through a full physical prototype. The system integrates the BioAmp EXG Pill for signal acquisition with an RP2040 microcontroller for local preprocessing using edge-resident TinyML deployment for on-device feature/inference feasibility coupled with environmental context sensors to augment signal context for downstream analytics talking to the external world via Wi-Fi/4G connectivity. A tiered data pipeline was implemented: SD card buffering for raw signals, Redis for near-real-time streaming, PostgreSQL for structured analytics, and AWS S3 with Glacier for long-term archival. End-to-end validation demonstrated consistent edge-level inference with bounded latency, while cloud-assisted telemetry and analytics exhibited variable transmission and processing delays consistent with cellular connectivity and serverless execution characteristics; packet loss remained below 5%. Visualization was achieved through Python 3.10 using Matplotlib GUI, Grafana 10.2.3 dashboards, and on-device LCD displays. Hybrid deployment strategies—local development, simulated cloud testing, and limited cloud usage for benchmark capture—enabled cost-efficient validation while preserving architectural fidelity and latency observability. The results establish a scalable, modular, and energy-efficient biosensor framework, providing a foundation for advanced analytics and translational BCI applications to be explored in subsequent work, with explicit consideration of both edge-resident TinyML inference and cloud-based machine learning workflows. Full article

Electrodermal activity (EDA) is a powerful anchor for assessing human sympathetic nervous system (SNS) arousal. However, EDA alone is only one facet of physiological response. Researchers have increasingly moved away from single-sensor analysis to multimodal wearable systems, integrating EDA with other signals such as heart rate variability (HRV), photoplethysmography (PPG), skin temperature (SKT), blood oxygen (SpO₂) and more. This critical shift in methodology is not yet reflected in current reviews of the literature. Existing surveys thoroughly cover EDA as a standalone measure, but the combination of sensor technologies has been largely unexamined. In this context, multimodal refers to integrating EDA with complementary biosignals (HRV, PPG, SKT, SpO₂, etc.) commonly captured by modern wearable platforms. This review provides a comprehensive analysis focused on multimodal systems for assessing SNS arousal. A total of 58 studies met the inclusion criteria. We map the landscape, from single signal methods to complex sensor-fusion, and highlight advances in multimodal sensor models, physiological modeling, and context-aware sensing. We also examine recent advances in signal processing and machine learning that enhance multimodal SNS arousal inference, outlining current capabilities and identifying open directions for future work. By providing a framework of this emerging field, this paper serves as a resource for all researchers aiming to build and deploy the next generation of context-aware SNS arousal-sensing technology. Full article

The interoperability of electronic health records in Colombia faces a critical gap between the regulatory mandates established by the Colombian regulatory framework and the actual technical capacity of healthcare institutions to implement them. This article presents PIRE (Electronic Records Interoperability Platform), an open-source architecture that demonstrates the viability of end-to-end FHIR systems in the Colombian context. The main objective was to develop a platform capable of integrating health data from biomedical devices into an FHIR server, preserving clinical semantics through LOINC terminologies. The methodology followed an iterative development approach, implementing a HAPI FHIR server on AWS, a normalization application in Flask, and clinical visualization modules aligned with the FHIR Core CO Implementation Guide. The Bioharness-3 device was used to capture metrics on heart rate, respiratory rate, activity, and posture. The platform achieved a data normalization latency of 104–438 ms per record and 100% semantic validation against the FHIR Core CO profiles, validating compliance with Colombian IHCE specifications. It is concluded that PIRE constitutes a reproducible reference model for healthcare institutions that wish to implement interoperability as a cost-effective solution. Full article

Electrocardiography (ECG) is a key biosensing technique for assessing cardiac function and autonomic activity. Accurate detection of R-peaks and precise calculation of R-R intervals (RRIs) are essential for heart rate variability (HRV) analysis; however, automated detection algorithms remain vulnerable to local misdetections, such as false positives or missed beats (false negatives), caused by noise, baseline fluctuations, or waveform variability. Conventional correction approaches based on filter or threshold adjustment may introduce new errors outside the target region, highlighting the need for an intuitive and localized manual correction capability. To address this issue, we developed a prototype graphical user interface (GUI)-based ECG viewer implemented in Fortran for high computational efficiency. The system enables interactive insertion and deletion of detected R-peaks, with recalculation of the RRI time series and automatic updating of related analyses, including power spectral density, histograms, Lorenz plots, and polar plots. Validation using synthetic ECG signals at four sampling frequencies (125–1000 Hz) and three display time scales (2, 5, and 10 s) demonstrated correction errors below 0.7% and stable update times within 20–30 ms. When applied to real ECG recordings from the MIT-BIH Arrhythmia Database (records 115, 122, and 209; MLII lead), the GUI-derived RRIs achieved accuracies exceeding 0.985 at a strict ±10 ms tolerance and reached 1.000 at ±20 ms or higher, including recordings with frequent atrial premature contractions. These results indicate that the proposed system provides reliable feedback for localized correction of R-peak misdetections without altering the underlying ECG signal. The proposed algorithm may support future research and experimental applications in biosignal processing. Full article

The development of reliable smartphone-based methods for vascular assessment is limited by the scarcity of large-scale, high-quality, real-world photoplethysmography (PPG) datasets. This work introduces two openly reusable smartphone camera-based PPG datasets curated from over one million unconstrained recordings, designed to support vascular morphology analysis and vascular aging research. The first dataset comprises approximately 5000 high-fidelity PPG heartbeat templates labeled into four morphological classes based on dicrotic notch characteristics, enabling assessment of arterial waveform structure beyond chronological age. The second dataset contains about 10,000 demographically balanced PPG samples curated for chronological age regression using rigorous subject-level balancing and correlation-based quality control. A standardized processing pipeline is presented, including beat alignment, ensemble averaging, and objective signal acceptance criteria to ensure morphological stability. To validate dataset utility, multiple machine learning models were benchmarked using raw signals, second derivatives, and compact Gaussian representations, achieving classification accuracy up to 90.08% and age prediction error below 10 years. By prioritizing real-world data quality, transparency, and reuse, this work provides a robust foundation for scalable, interpretable, and reproducible research in smartphone-based vascular assessment. Full article

Background: To assess associations between possible dysfunction of autonomic cardiovascular modulation and hemispheric localization, seizure frequency, disease duration, and antiseizure medication (ASM) in temporal lobe epilepsy (TLE). Methods: In this prospective observational study, cardiovascular autonomic modulation was monitored in 31 patients with TLE (12 patients with right TLE, 19 patients with left TLE). From 5 min time series of R–R intervals (RRI) and blood pressure (BP) recordings, we calculated autonomic parameters of sympathetic, parasympathetic, and total autonomic cardiovascular modulation. Data were compared to those of 30 healthy volunteers. Subgroup analyses were performed according to (1) disease localization (right vs. left hemispheric TLE), (2) seizure frequency (< vs. >1/month) and disease duration (< vs. >10 years), (3) number of ASMs, and (4) participants’ age (< vs. >30 years). Results: Between right TLE patients, left TLE patients, and controls, there were no significant differences in the assessed bio-signals. Parameters of sympathetic and total autonomic modulation were slightly lower in right TLE patients than in controls. Additionally, reduced vagal modulation was observed in right TLE patients taking three ASMs or not taking any ASMs at all (applicable to one patient) compared to healthy controls. In general, TLE patients with <1 seizure/month showed lower parameters of sympathetic modulation than healthy controls, with differences reaching statistical significance in left TLE patients. In contrast, parameters reflecting vagal tone showed insignificantly, yet consistently, lower values in left TLE patients with increasing seizure frequency. Alterations in autonomic cardiovascular modulation observed across age-matched subgroups were comparable. Conclusions: A trend towards lower values of sympathetic modulation in patients with right TLE supports previous findings suggesting right hemispheric mediation of sympathetic regulation. A decrease in parasympathetic modulation with increasing seizure frequency underscores the importance of sufficient seizure control in order to prevent autonomic complications. In contrast, the absence of significant associations between disease duration and autonomic alterations suggests that epilepsy exerts an early and clinically relevant effect on the autonomic nervous system. Due to comparable alterations in autonomic modulation in a patient without antiseizure medication and in patients undergoing polytherapy, ASM side effects may not account solely for the observed autonomic dysregulation of our TLE patients. Full article

Background/Objectives: Automatic evaluation of Parkinson’s disease (PD) progression is an emerging topic that deserves special attention from the research community. Unobtrusive, low-cost technology is essential for monitoring PD patients in remote areas. This paper proposes the use of phonological posteriors to create models that allow the progression of dysarthria level progression to be modelled based on speech recordings. Methods: Eighteen Gated Recurrent Units (GRUs) are used to estimate an equal number of phonological classes assigned to each phoneme pronounced in a given recording. Classification models of PD vs. healthy control (HC) subjects are trained with recordings of the PC-GITA corpus. This information is used in a separate corpus, with longitudinal recordings, to evaluate whether the progression of the dysarthria level, according to the modified Frenchay Dysarthria Assessment (mFDA), is related to abnormal production of specific phonemes. Results: Strident, dental, pause, back, and continuant phonological classes are the ones that better explain dysarthria level progression within time-frames of at least two years, therefore allowing possible monitoring of disease progression. Conclusions: Speech is a low-cost biosignal that can be used to automatically assess PD progression. In particular, this study shows that such an assessment makes it possible to evaluate dysarthria level progression and to find which phonological classes are contributing the most to such a progression. We believe that the findings reported in this paper provide objective evidence about possible abnormalities in broader speech-related processes like respiration, therefore contributing a better understanding of the relationship between speech production patterns and other speech-related processes affected when suffering from PD. Full article

Machine learning (ML), including deep learning, kernel-based classifiers, and ensemble methods, is increasingly used to support clinical diagnosis in medical imaging, biosignal interpretation, and electronic health record (EHR)-based decision support. Despite rapid progress, many diagnostic AI studies still rely on limited retrospective evaluation and single summary measures (e.g., accuracy or AUC), creating a gap between reported model performance and evidence required for safe clinical adoption. This review proposes TRIAGE, a clinically grounded evaluation framework designed to organize diagnostic AI testing as an evidence pipeline aligned with real clinical use cases (screening, triage, second reading, and confirmatory testing). We summarize core discrimination metrics derived from the confusion matrix (sensitivity, specificity, predictive values, likelihood ratios, diagnostic odds ratio, and F-scores) and highlight the importance of prevalence and spectrum effects for interpreting predictive value and clinical workload. We further review evaluation strategies for multi-class and multi-label diagnostic tasks using appropriate aggregation methods (micro, macro, and weighted averaging) and set-based measures such as Hamming loss, exact match ratio, and Jaccard/IoU. Because diagnostic deployment is threshold-dependent, we integrate representation curves (ROC, precision–recall, lift, and cumulative gain) with calibration assessment and clinical utility analysis, including calibration slope, Brier score, and decision-curve analysis. We also address robustness and fairness evaluation, leakage-resistant validation designs (patient-grouped splits, stratified and temporal validation, and external validation), computational constraints relevant to deployment (latency, throughput, and energy use), and statistically sound model comparison with multiplicity control. A structured TRIAGE checklist table summarizing the evaluation parameters described in this review is provided in the main text to support reproducible and clinically interpretable reporting. Full article

Background: Electrocardiography (ECG), particularly the 12-lead configuration, is a crucial method for identifying heart rhythm abnormalities. However, its effectiveness can be reduced by noise contamination. State-of-the-art denoising methods based on neural networks have demonstrated promising performance in denoising complex biosignals like ECG. However, most of these methods have focused on denoising single-lead ECG recordings. Methods: This research aims to leverage the inherent correlation among multi-lead ECG signals. Therefore, a multi-lead convolutional denoising autoencoder (ML-CDAE) model is proposed, to learn more effective representations, leading simultaneously to improved denoising performance and enhanced quality of 12-lead ECG recordings. Results: The findings indicate that ML-CDAE consistently outperforms a single-lead convolutional denoising autoencoder (SL-CDAE) and fully convolutional denoising autoencoder (FCN-DAE) model in denoising ECG signals corrupted by a mixture of physical noises. In particular, the mean squared error ($\mathrm{MSE}$) and signal-to-noise ratio improvement (${\mathrm{SNR}}_{\mathrm{imp}}$) are used as evaluation metrics to assess the performance. Conclusions: The strong correlation among multi-lead ECG signals can be leveraged not only to enhance the denoising performance of the ML-CDAE model but also to simultaneously denoise 12-lead ECG signals more successfully compared to both the SL-CDAE and FCN-DAE models. Full article

Background: Pain remains one of the most debilitating and prevalent symptoms in cancer patients. However, assessment based solely on subjective self-report tools is limited by cognitive impairment and the heterogeneous nature of cancer pain. Since evidence on the ability of physiological biosignals to discriminate cancer pain intensity and pain phenotypes in real clinical settings remains limited, this study explored the potential of biosignals to discriminate between pain intensity and pain type. Methods: Electrodermal activity (EDA) and electrocardiogram (ECG) signals were recorded in cancer patients using the BITalino (r)evolution board (sampling frequency 1000 Hz). EDA was processed to extract skin conductance responses (SCRs) using continuous decomposition analysis (CDA) and trough-to-peak (TTP) methods. Heart rate variability (HRV) features were extracted in both time and frequency domains, including low frequency (LF), high frequency (HF), and the LF/HF ratio. Non-parametric Kruskal–Wallis tests were performed to compare biosignal parameters across pain intensity (Numeric Rating Scale, NRS: low 1–3; medium 4–6; and high 7–10) and pain types (nociceptive, neuropathic, mixed, and breakthrough cancer pain—BTCP). Results: Data from 61 patients were analyzed. For EDA, the maximum skin conductance response amplitude (MaxCDA) significantly differed across intensity groups (p = 0.037). Post hoc analysis showed a significant difference between the low- and high-intensity groups (p = 0.015), with the low-intensity group exhibiting a higher mean MaxCDA (0.063 µS) than the high-intensity group (0.024 µS). Several EDA parameters were significantly associated with pain type. The number of SCRs (TTP) (p = 0.015) and maximum SCR amplitude (TTP) (p = 0.040) were significantly lower in the mixed pain group compared with the nociceptive and neuropathic groups. No HRV parameters showed significant associations with pain intensity or pain type. BTCP did not significantly affect any biosignal parameters. Subgroup analyses showed that EDA features discriminating mixed pain were preserved in patients without bone metastases, BTCP, or high opioid burden, whereas no clinical variable modified the association between biosignals and pain intensity and type. Conclusions: In this investigation, selected EDA parameters were associated with cancer pain intensity and pain type, whereas heart rate variability measures did not show significant discrimination under the present methodological conditions. These findings suggest that EDA may provide complementary information on pain-related autonomic alterations in oncology patients. However, biosignals should not be considered standalone indicators of pain, and their interpretation requires integration with clinical variables and pharmacological context. Further studies adopting multimodal and longitudinal approaches are needed to clarify their role in automatic pain assessment in cancer care. Full article

The early and accurate identification of breast cancer is a significant healthcare issue, largely because the traditional machine learning approaches rely on handcrafted features that are unable to fully capture the spatial and textural complexity found in mammograms. Even with the advancements made possible through deep learning and improvements in diagnostic performance, most computational-aided diagnosis (CAD) systems based on Convolutional Neural Networks (CNNs) still only rely on single-domain features, normally spatial features, while neglecting some important spectral and spatial–spectral features, leading to limitations in generalisability, redundancy, and loss of performative interpretability. Inspired by these limitations, this research proposes MERGE, a novel CAD framework that combines spatial, spectral, and spatial–spectral information—all part of a single multistage architecture taking advantage of three fine-tuned CNN models (ResNet-50, Xception, and Inception). This system utilises Discrete Stationary Wavelet Transform (DSWT) to enhance spectral–spatial features; Discrete Cosine Transform (DCT) to fuse the features optimally, resulting in enhanced spatial and spatial–spectral representations; and, finally, Non-Negative Matrix Factorisation (NNMF) for reduced-dimensional features. Finally, the Linear Discriminant Analysis (LDA), support vector machine (SVM), and k-nearest neighbours (KNN) classifiers provide a robust diagnosis. Using the INBreast and MIAS datasets in evaluations of the experimental research design, evaluation metrics of accuracy, sensitivity, specificity, and AUC were around 99%, with performance surpassing state-of-the-art paradigms. The findings of the suggested MERGE indicate significant promise as a dependable and effective diagnostic tool, enhancing the consistency and interpretability of breast cancer screening results. Full article

This paper presents a compact mixed-mode first-order universal filter based on a single voltage differencing current conveyor (VDCC), which can function in all four possible operation modes, i.e., voltage mode (VM), trans-admittance mode (TAM), current mode (CM), and trans-impedance mode (TIM). The proposed configuration requires only two grounded resistors and one floating capacitor, which contributes to a low component count, facilitates integration, and allows for the electronic tunability of the pole frequency through the transconductance gain of the VDCC. This work also demonstrates two practical biomedical applications: an electrocardiogram (ECG) acquisition system utilizing the VM low-pass filter for noise suppression and a bioimpedance (BioZ) measurement system employing the proposed configuration-based CM oscillator circuit as a sinusoidal excitation source. The performance validation confirms the accuracy of impedance extraction and the preservation of waveforms using tissue-equivalent models. The results demonstrate that the proposed VDCC-based filter offers a compact, power-efficient, and versatile analog signal-processing solution suitable for modern biomedical instrumentation. Full article

This paper presents Nexus, a proof-of-concept low-cost, modular, and reprogrammable multichannel data logger aimed at validating the architectural feasibility of an open and scalable acquisition platform for scientific instrumentation. The system was conceived to address common limitations of commercial data loggers, such as high cost, restricted configurability, and limited autonomy, by relying exclusively on widely available components and open hardware/software resources, thereby facilitating reproducibility and adoption in resource-constrained academic and industrial environments. The proposed architecture supports up to six interchangeable acquisition modules, enabling the integration of up to 20 analog channels with heterogeneous resolutions (24-bit, 12-bit, and 10-bit ADCs), as well as digital acquisition through multiple communication interfaces, including I²C (two independent buses), SPI (two buses), and UART (three interfaces). Quantitative validation was performed using representative acquisition configurations, including a 24-bit ADS1256 stage operating at sampling rates of up to 30 kSPS, 12-bit microcontroller-based stages operating at approximately 1 kSPS, and 10-bit operating at 100 SPS, consistent with stable real-time acquisition and visualization under proof-of-concept constraints. SPI communication was configured with an effective clock frequency of 2 MHz, ensuring deterministic data transfer across the tested acquisition modules. A hybrid data management strategy is implemented, combining high-capacity local storage via USB 3.0 solid-state drives, optional cloud synchronization, and a 7-inch touchscreen human–machine interface based on Raspberry Pi OS for system control and visualization. Power continuity is addressed through an integrated smart uninterruptible power supply, which provides telemetry, automatic source switching, and limited backup operation during power interruptions. As a proof of concept, the system was functionally validated through architectural and interface-level tests, demonstrating stable communication across all supported protocols and reliable acquisition of synthetic and biosignal-like waveforms. The results confirm the feasibility of the proposed modular architecture and its ability to integrate heterogeneous acquisition, storage, and interface subsystems within a unified open-source platform. While not intended as a finalized commercial product, Nexus establishes a validated foundation for future developments in modular data logging, embedded intelligence, and application-specific instrumentation. Full article