Search Results (194)

Atrial fibrillation (AF) is a highly prevalent arrhythmia associated with stroke, heart failure and excess mortality. Yet, “silent” AF episodes remain undetected, leading to underestimation of disease burden. Additionally, paroxysms occur in an “unpredictable” way, and available clinical scores only stratify long-term AF risk with moderate discrimination, lacking the ability to evaluate near-term events. Artificial intelligence (AI) applied to sinus rhythm from short or continuous electrocardiogram (ECG) recordings shows that such predictive information is hidden in “plain sight.” This complementary approach seeks to uncover latent AF substrate and forecast imminent AF episodes. Deep-learning models trained on 10-s, 12-lead ECGs can identify individuals with prevalent or long- or near-term AF with areas under the curve (AUCs) up to 0.90, outperforming established clinical scores. Image-based AI-ECG models extend these capabilities to paper or scanned ECGs. Furthermore, AI algorithms applied to 24-h Holter and multi-day patch recordings achieve AUCs ≥0.80 for detecting occult AF or predicting it within 14 days, consistently surpassing risk scores like C₂HEST and HATCH. Short-term models utilizing heart-rate variability features further demonstrate that AF can be anticipated minutes to hours before onset, with accuracies around 90% in curated datasets. However, most AI-AF studies remain retrospective, single-system and focused on diagnostic yield rather than clinical outcomes like stroke or mortality. Moreover, few pragmatic trials have evaluated AI-guided AF screening and its translation into clinical benefit. Robust prospective trials and standardized evaluation frameworks are needed before AI-guided AF prediction can be routinely integrated into clinical decision-making. Full article

Background: Cardiac involvement in dengue has been increasingly recognized, yet the true burden and spectrum of arrhythmias remain uncertain due to heterogeneous and fragmented evidence. We conducted a systematic review and meta-analysis to estimate the proportion of cardiac arrhythmias in patients with dengue and to describe the distribution of major arrhythmia subtypes. Methods: We searched PubMed/MEDLINE, EMBASE, LILACS, Global Index Medicus, and Google Scholar from inception to November 2025 without language restrictions. Observational studies reporting the number of dengue patients evaluated for arrhythmias and the number with at least one rhythm disturbance were included. Random-effects generalized linear mixed models with a logit transformation were used to estimate pooled proportion with 95% confidence intervals (CIs). Subgroup analyses were performed by age group. Risk of bias was assessed using the Joanna Briggs Institute tool, and certainty of evidence was evaluated with GRADE. Results: Thirty-five studies, including 6948 patients, were analyzed. The pooled proportion of any arrhythmia was 24.48% (95% CI 17.54–33.07), with a higher proportion in adults (30.00%) than in children (10.73%). Sinus bradycardia (11.84%) and sinus tachycardia (10.63%) were the most frequent abnormalities. Atrioventricular block was uncommon (1.33%). Between-study heterogeneity was high for most outcomes. No significant small-study effects were detected. Conclusions: Cardiac arrhythmias occur in approximately one in four patients with dengue, predominantly as sinus rate abnormalities. While often transient, these findings support the role of baseline and risk-based ECG monitoring, particularly in hospitalized adults and patients with severe disease. Full article

An AI video–based assessment system is used to analyze the volleyball forearm pass under continuous wall-volley conditions in this study. A single 120 frames per second (FPS) high-speed camera captures the athlete from a rear-oblique view. A laptop executes a You Only Look Once (YOLO)-based pipeline to detect the ball and human keypoints, including the shoulders, elbows, wrists, hips, knees, and ankles. From the joint angles and ball–body relative positions, three cues are quantified. The first cue is the ready posture, characterized by straight arms, downward wrist flexion, an upper arm–trunk angle of approximately 90°, and a forward-leaning center of mass. The second cue is the ball–contact point located posterior to the wrist joint. The third cue is the variation in the center of mass synchronized with the rhythm of the ball. Five athletes performed ten trials, and the predictions were compared against manual annotations, achieving greater than 95% accuracy in criterion attainment. The system outputs criterion scores and key frames to provide immediate feedback. Deployment challenges, including occlusion, viewpoint, and illumination, are discussed, along with potential extensions such as multi-camera fusion and temporal tracking. Full article

Sleep disorders, such as insomnia, obstructive sleep apnea (OSA), narcolepsy, REM sleep behavior disorder, and circadian rhythm disturbances, represent a rapidly expanding global health burden that is strongly associated with cardiovascular, metabolic, neurological, and psychiatric diseases. Advancements in wearable sensing technologies and Internet of Medical Things (IoMT) infrastructures have expanded the possibilities for continuous, home-based sleep assessment beyond conventional polysomnography laboratories. These Sleep Health Internet of Things (S-HIoT) systems combine multimodal physiological sensing (EEG, ECG, SpO₂, respiratory effort and actigraphy) with wireless communication and cloud-based analytics for automated sleep-stage classification and disorder detection. Nonetheless, the digitization of sleep medicine brings about significant cybersecurity concerns. The constant transmission of sensitive biomedical information makes S-HIoT networks open to anomalous traffic flows, signal manipulation, replay attacks, spoofing, and data integrity violation. Existing studies mostly focus on analyzing physiological signals and network intrusion detection independently, resulting in a systemic vulnerability of cyber–physical sleep monitoring ecosystems. With the aim of addressing this empirical deficiency, this review integrates emerging advances (2022–2026) in the AI-assisted categorization of sleep phases and IoMT anomaly detector designs on the finer analysis of CNN, LSTM/BiLSTM, Transformer-based systems, and a component part of federated schemes and the lightweight, edge-deployable intruder assessor models available. The aim of this study is to uncover a gap in the literature: integrated architectures to trade off audiences of faithfulness of physiological modeling with communication-layer security. To counter it, we present a single framework to include CNN-based spatial feature extraction, Bidirectional Long Short-Term Memory (BiLSTM)-based temporal models and Random Forest-based ensemble classification using a dual task-learning approach. We propose a multi-objective optimization framework to jointly optimize the performance of sleep-stage prediction and that of network anomaly detection. Performance on publicly available datasets (Sleep-EDF and CICIoMT2024) confirms that hybrid integration can be tailored to achieve high accuracy [99.8% sleep staging; 98.6% anomaly detection] whilst being characterized by low inference latency (<45 ms), which is promising for feasibility in real-time deployment in view of targeting edge devices. This work presents a comprehensive framework for developing secure, intelligent, and clinically robust digital sleep health ecosystems by bridging chronobiological signal modeling with cybersecurity mechanisms. Furthermore, it highlights future research directions, including explainable AI, federated secure learning, adversarial robustness, and energy-aware edge optimization. Full article

The Chinese giant salamander (Andrias davidianus) is a nationally protected species in China, and its respiratory behavior serves as a key indicator of its physiological state, health status, and biological rhythm. However, research on intelligent monitoring of its respiratory behavior remains limited due to several challenges, including the species’ nocturnal habits, resulting in low image contrast and poor quality in dark environments; extremely subtle breathing movements; and high-cost manual annotation, leading to a scarcity of high-quality annotated visual data. These factors severely constrain the application of deep learning techniques in this field. To support research on respiratory behavior monitoring in the Chinese giant salamander, this study constructs and releases the CGS-BR dataset, which is the first vision-based dataset dedicated specifically to respiratory behavior detection in this species. The dataset was collected under controlled simulated breeding conditions and consists of 1732 images extracted from 215 high-definition video clips. Following a standardized procedure, each complete respiratory cycle is manually annotated into four stages: head-up, diving, exhalation, and inhalation. To validate the effectiveness of this dataset, this study selects YOLOv8n as the baseline model, which balances detection accuracy, speed, and parameter count, enabling efficient giant salamander respiratory detection under limited resources. By comparing it with several representative models, we provide a reliable evaluation of the dataset’s applicability. CGS-BR aims to provide fundamental data support for research on respiratory monitoring in the Chinese giant salamander, laying the foundation for subsequent applications in conservation management, captive breeding, health monitoring, and early disease warning. Full article

Background: Atrial fibrillation (AF) remains the most common cardiac arrhythmia, with pulmonary vein isolation (PVI) established as the cornerstone of interventional treatment. However, in patients with persistent AF (PersAF), the success rates of PVI alone tend to be limited. A promising additional target is the left atrial appendage (LAA). In recent years, cryoballoon (CB) technology has become a tool for achieving durable PVI. Its application for LAAI has been investigated as a potentially advantageous alternative to radiofrequency ablation, and a positive effect on long-term outcome has been reported. However, the available data is limited. This study sought to investigate the clinical impact of CB-based LAAI in addition to PVI. Methods: This is a prospective, interventional, single-centre study. Consecutive patients with symptomatic PersAF were prospectively enrolled. In total 23 patients with PersAF underwent PVI plus LAAI using the CB system. Percutaneous LAA closure was performed within 2–3 months in all patients by implanting an endocardial LAA-closure device. Prior to LAA closure, LAAI durability was systematically assessed by invasive remapping studies. Results: A total of 100% of PVs were successfully isolated using the CB only (n = 91/91). Concerning LAAIs, a total of 21/23 (91%) remained isolated at the end of the procedure. After the ablation procedure including LAAI, all patients were scheduled for TEE assessment and LAA closure. TEE was performed after a mean of 54 ± 19 days. In 6/23 (26%) patients, LAA thrombus formation was detected after LAAI. A total of 23/23 patients (100%) received LAAC after a mean of 72 ± 45 days. Durability of LAAI was assessed utilizing a spiral mapping catheter in 23/23 patients (100%). In a total of 17/23 (74%) patients, durable LAA isolation was detected. Durable PVI of all PVs was detected in 16/23 (70%) patients. During a mean follow-up of 13 ± 3.4 months, stable sinus rhythm was maintained in 15 (65%) patients. The LAA showed reconnection in 3/23 (13%) patients, with arrhythmia recurrence. During follow-up, one stroke (318 days after LAAC) and one device thrombus (56 days after LAAC) occurred. Conclusions: While CB-based LAAI may offer benefits in managing persistent AF, it presents a significant risk of thrombus formation in the LAA, even with appropriate OAC. Early closure of the LAA following LAAI appears promising in mitigating these risks, but further evidence is needed to establish clear best practices. Full article

Background/Objectives: Portable and wearable ECG technologies are increasingly used in adult cardiac monitoring. However, evidence supporting their feasibility and diagnostic performance in pediatric populations remains limited. This systematic review evaluates the diagnostic accuracy, usability, artifact susceptibility, and user acceptance of mobile ECG technologies in pediatric cardiology. Methods: A systematic literature search was performed in the Embase, PubMed, Scopus, and Web of Science databases. The review was conducted in accordance with the PRISMA 2020 guidelines and was registered in the PROSPERO database. Results: A total of 30 publications were included in the final analysis. Portable ECG devices demonstrated good feasibility diagnostic utility in children. Handheld systems provided high-quality tracings with strong agreement with standard 12-lead ECGs and higher adherence, as well as user satisfaction compared with conventional event recorders. However, automated rhythm classification frequently misidentified pediatric arrhythmias. Smartwatch-based ECG recordings showed high diagnostic accuracy when manually interpreted, but automated algorithms were unreliable, particularly for tachyarrhythmias and conduction abnormalities. Alternative electrode placement strategies improved smartwatch performance, and patient acceptance was consistently high. ECG patch monitoring, particularly with extended-wear devices, achieved the highest diagnostic yield, detecting arrhythmias often missed by short-duration Holter monitoring while maintaining comparable signal quality. Conclusions: Mobile ECG technologies represent a promising adjunct for pediatric rhythm surveillance, offering diagnostic performance comparable to standard modalities when interpreted by clinicians and improved usability and patient acceptance. Persistent limitations include the poor reliability of adult-oriented automated algorithms and the underrepresentation of younger children and the predominantly off-label use of these devices in pediatric populations, underscoring the need for pediatric-specific algorithm development and age-adapted device design. Full article

Background: Women with atrial fibrillation experience a higher lifetime risk of ischemic stroke, greater stroke severity, and worse functional outcomes than men. Preventive strategies focused on AF detection may therefore miss critical opportunities for early intervention in women. Methods: We developed a decision-analytic Markov model using real-world primary care data from Catalonia (Spain) to evaluate an artificial intelligence (AI) enabled strategy for upstream thromboembolic risk detection. The intervention combined electronic health record–based risk prediction, targeted digital rhythm screening, and individualized anticoagulation. Lifetime clinical and economic outcomes were estimated for adults aged ≥65 years, with pre-specified sex-stratified analysis. Results: Compared with usual care, the AI-enabled strategy reduced ischemic stroke, major adverse cardiovascular events, and long-term disability. Absolute reductions in stroke and disability were greater in women, reflecting higher baseline thromboembolic risk. Per 1000 high-risk women, the strategy prevented more strokes and generated larger quality-adjusted life-year gains than in men. From both healthcare payer and societal perspectives, the intervention was cost-saving in women, driven by reductions in stroke-related disability and long-term care. Conclusions: AI-enabled upstream thromboembolic risk detection may deliver particularly important benefits for older women and represents a promising approach to reduce sex-based inequities in stroke prevention. Full article

Photoplethysmography (PPG) has emerged as an attractive modality for non-invasive cardiovascular monitoring due to its low cost, unobtrusive nature, and ubiquity in consumer wearable devices. Despite its potential, existing PPG-based arrhythmia detection systems remain limited in scope: (i) most target only atrial fibrillation, (ii) temporal localization of abnormal segments is rarely provided, and (iii) deep learning models lack explainability, hindering adoption in clinical workflows. We present a comprehensive and fully integrated framework for multi-class arrhythmia detection, segmentation, and explainability based on PPG waveforms, Heart Rate Variability (HRV), and structured clinical metadata. The proposed system introduces a CLIP-style contrastive learning module aligning PPG waveforms with clinical variables and rhythm-state textual descriptions using BioBERT; a multitask U-Net architecture performing 4-class classification and 1D segmentation; a Retrieval-Augmented Generation (RAG) pipeline leveraging Gemini Flash large language models to produce guideline-grounded diagnostic reports; and a real-time Streamlit-based web platform supporting inference, visualization, and database storage. The system significantly improves classification accuracy (from 86.27% to 91.19%) and segmentation Dice (from 0.5815 to 0.7167). These results demonstrate the feasibility of a robust, multimodal, and explainable PPG-based arrhythmia monitoring system for real-world applications. Full article

Background: Children and adolescents with hearing loss frequently experience reduced participation in physical activity and impairments in balance and postural control, often associated with vestibular dysfunction and altered sensory integration. In this context, school-based motor interventions may represent an accessible strategy to support functional balance. The present study investigated the effects of a 12-week dance- and rhythm-based motor programme implemented within the school curriculum on static and dynamic balance in students with hearing loss. Methods: Twenty-five participants were randomly allocated to an experimental group (n = 15), which received the intervention in addition to standard curricular activities, or to a control group (n = 10), which continued with regular school-based physical activity only. Balance was assessed at baseline and post-intervention using stabilometric measures under eyes-open and eyes-closed conditions and the Pediatric Reach Test. Results: Stabilometric outcomes showed mixed patterns: improvements over time were observed in both groups under eyes-closed conditions, whereas under eyes-open conditions greater reductions in sway were detected in the control group. A significant Group × Time interaction emerged exclusively for backward reach performance and for the composite balance score, indicating a relative preservation of posterior dynamic balance and a more favourable multidimensional adaptation in the experimental group. Conclusions: These findings suggest that dance- and rhythm-oriented motor activities integrated into school settings may support specific, functionally relevant components of balance in students with hearing loss, although the results should be interpreted with caution due to the small sample size and the heterogeneity of the participants. Full article

Atrial fibrillation (AF) frequently coexists with chronic coronary syndrome (CCS), reflecting shared cardiovascular risk factors and structural remodeling pathways. Identifying CCS patients at increased likelihood of AF remains clinically relevant, particularly when arrhythmia is silent or paroxysmal. Background: We hypothesized that established clinical and angiographic risk scores used in CCS may capture cumulative cardiovascular burden and could therefore assist in AF risk stratification. The biomarker-based ABC-stroke score was incorporated as a biological reference framework reflecting myocardial stress and injury. Methods: This prospective, single-center proof-of-concept study included 131 consecutive patients undergoing invasive coronary angiography for suspected myocardial ischemia. Patients were classified according to rhythm status, irrespective of AF subtype. Coronary artery disease severity was quantified using the Gensini and SYNTAX (PCI and CABG) scores. Global cardiovascular risk was assessed using Framingham, ASCVD, SCORE2, and SCORE2-OP. Correlation analyses, ROC curves, and multivariable logistic regression were performed to evaluate associations between risk scores, coronary complexity, and AF. Results: Clinical and angiographic risk scores differed significantly according to rhythm status and AF phenotype. Patients with AF exhibited higher global cardiovascular risk and greater coronary anatomical complexity compared with those in sinus rhythm. SYNTAX PCI and SYNTAX CABG demonstrated moderate discriminative performance for AF detection (AUC 0.745 and 0.760, respectively), with SYNTAX CABG remaining independently associated with AF in multivariable analysis. Significant correlations were observed between traditional cardiovascular risk scores and SYNTAX-derived measures of coronary complexity, whereas correlations with the Gensini score were weaker. The ABC-stroke reference model showed a strong discriminative signal, consistent with its biological proximity to AF-related myocardial stress. Conclusions: Established clinical and angiographic risk scores used in CCS are associated with the presence and phenotype of AF. These findings suggest that routinely available coronary risk assessment tools may serve as practical instruments for identifying CCS patients at increased likelihood of AF, potentially facilitating targeted rhythm screening and earlier risk stratification. Full article

Accurate detection of cardiac arrhythmias from electrocardiograms remains challenging for rare rhythm classes due to class imbalance and morphological variability. We present a hybrid deep learning framework combining per-lead convolutional encoders with a cross-lead transformer that models relationships across different lead signals through self-attention, accepting variable lead configurations. To address minority-class scarcity, a generative adversarial network synthesizes physiologically plausible beat segments for underrepresented arrhythmias. Attention-based visualizations localize influential waveform regions aligned with clinically meaningful structures. Post-training pruning and INT8 quantization enable efficient deployment with minimal performance loss. Extensive experiments on the MIT-BIH Arrhythmia Database across sixteen heartbeat classes from two-lead recordings yield exceptional results over ten independent runs: accuracy of 99.67%, F1-score of 99.66%, and AUC of 99.8%. External validation on the ECG5000 single-lead dataset and the St Petersburg INCART twelve-lead dataset confirms robust generalizability with F1-scores of 97.6% and 98% respectively. Our framework delivers accurate, interpretable, stable, and deployable arrhythmia detection across diverse clinical settings. Full article

Sample-wise detection of P-, R-, and T-peaks in electrocardiograms (ECGs) is challenging because each peak type is sparsely represented (≈1:500 samples in a typical 10-s, 500-Hz ECG at 60 bpm), such that even a small number of false-positives (FPs) can markedly degrade positive predictive value (PPV) and limit the practicality of classifier-only approaches. This study proposes a lightweight ECG peak detection framework that combines binary classifiers with physiological temporal constraints (PTC) to address extreme sample-level class imbalance. Local morphological features are first evaluated using lightweight machine-learning models, among which XGBoost (XGB) exhibited the most stable score-ranking performance. Rather than directly thresholding classifier outputs, prediction scores are interpreted within the framework, which encodes physiological timing relationships. R-peaks are detected using score ranking combined with a refractory-period constraint, and the detected R-peaks serve as temporal landmarks for subsequent P- and T-peak detection within physiologically plausible time windows reflecting the P–QRS–T sequence. Quantitative evaluation was conducted using the Lobachevsky University Electrocardiography Database, hereafter referred to as LUDB. With a temporal tolerance of ±20 ms, the XGB-based system achieved an F1-score of 0.87 for R-peak detection (sensitivity 0.96, PPV 0.79), corresponding to approximately 9–10 true R-peaks with only 2–3 FP samples per 10-s segment. For P- and T-peaks, F1-scores of 0.70 and 0.69 were obtained, respectively. Additional evaluation on arrhythmic LUDB records demonstrated robust R-peak detection across rhythm types. In AF-related rhythms, where organized P waves are physiologically absent, the framework appropriately suppressed P-peak detections, with false-positive rates remaining below 0.31%. Qualitative application to ECG recordings from the PTB-XL database further demonstrated physiologically consistent behavior. These results indicate that reliable and interpretable ECG peak detection under extreme class imbalance can be achieved by integrating lightweight classifiers within the proposed framework, without reliance on complex deep learning architectures. Full article

Melatonin, an indoleamine crucial for regulating circadian rhythms, sleep–wake cycles, and immune–endocrine homeostasis, is present in biological fluids at extremely low concentrations, making its quantification analytically challenging. This narrative review provides a critical comparative assessment of current methodologies for melatonin determination across various biological matrices—plasma, urine, saliva, breast milk, and hair. The discussed techniques include immunoassays, colorimetric and spectrophotometric methods, chromatographic–mass spectrometric platforms (LC–MS/MS, UHPLC–MS/MS), and emerging biosensors. Each approach is evaluated regarding analytical sensitivity, specificity, reproducibility, cost, and clinical applicability. While immunoenzymatic and colorimetric techniques offer accessible, low-cost solutions for large-scale or preliminary studies, LC–MS/MS remains the benchmark for reference analysis, providing sub-picogram detection limits and multiplexing capability. However, its high cost, procedural complexity, and inter-laboratory variability limit routine implementation. New developments, including molecularly imprinted polymers, dispersive microextraction, and nanomaterial-based biosensors, suggest a shift toward hybrid, sustainable, and portable analytical platforms. By synthesizing recent methodological advances and identifying key limitations, this review aims to guide researchers and clinicians in selecting the most appropriate analytical approach for clinical, pharmacological, and circadian biomonitoring applications. Full article

Background/Objectives: Implantable loop recorders (ILRs) enable long-term electrocadiographic monitoring and are established diagnostic tools for syncope and atrial fibrillation (AF). However, their diagnostic yield and therapeutic impact in other clinical settings remain less well defined. We aimed to evaluate the diagnostic yield and clinical impact of ILR implantation across contemporary clinical indications. Methods: In this retrospective single-center study, 388 patients who underwent ILR implantation between 2011 and 2018 were included. Indications were categorized into seven groups: unexplained syncope, presyncope, cryptogenic stroke or transient ischemic attack (TIA), AF detection, AF recurrence after atrial flutter (AFL) ablation, risk stratification in structural or inherited heart disease, and palpitations. Results: Among 388 patients (median age 63 [51.8–71.8] years, 57.5% male; median follow-up 17.0 [IQR 6.4–32.4] months), ILRs were most frequently implanted for syncope (44.6%), AF (20.4%), and stroke/TIA (12.9%). ILR-detected arrhythmias occurred in 241 patients (62.1%), with the highest detection rates in AF (83.5%) and AFL (73.7%). Indication-fulfilling diagnoses were established in 155 patients (39.9%), most frequently in AF (73.4%) and AFL (71.1%), after a median of 4.4 months (IQR 2.4–12.5). Nearly three quarters (72.9%) of diagnoses were made within the first year. ILR findings prompted therapeutic interventions in 156 patients (40.2%), including pacemaker implantation in syncope and rhythm- or anticoagulation-based therapies in AF. AF and AFL independently predicted higher diagnostic yield, while diagnostic yield and AF history predicted ILR-triggered therapy. AF, AFL, stroke/TIA, and AF history were associated with shorter time to first arrhythmia detection. Arrhythmia-free survival differed significantly across indication groups (p < 0.0001) and was lowest in AF and AFL, which demonstrated the highest cumulative incidence of indication-fulfilling arrhythmias. Conclusions: ILRs provide substantial diagnostic and therapeutic value across a broad range of indications. Beyond established uses in syncope and AF, clinically relevant yields were observed in presyncope, risk stratification, and AFL post-ablation, supporting broader consideration of ILRs and optimized patient selection. Full article