Search Results (225)

Stroke is a significant global health concern characterized by the abrupt disruption of cerebral blood flow, leading to neurological impairment. Accurate and timely diagnosis—enabled by imaging modalities such as computed tomography (CT) and magnetic resonance imaging (MRI)—is essential for differentiating stroke types and initiating interventions like thrombolysis, thrombectomy, or surgical management. In parallel, recent advancements in wearable technology, particularly smart clothing, offer new opportunities for stroke prevention, real-time monitoring, and rehabilitation. These garments integrate various sensors, including electrocardiogram (ECG) electrodes, electroencephalography (EEG) caps, electromyography (EMG) sensors, and motion or pressure sensors, to continuously track physiological and functional parameters. For example, ECG shirts monitor cardiac rhythm to detect atrial fibrillation, smart socks assess gait asymmetry for early mobility decline, and EEG caps provide data on neurocognitive recovery during rehabilitation. These technologies support personalized care across the stroke continuum, from early risk detection and acute event monitoring to long-term recovery. Integration with AI-driven analytics further enhances diagnostic accuracy and therapy optimization. This narrative review explores the application of smart clothing in conjunction with traditional imaging to improve stroke management and patient outcomes through a more proactive, connected, and patient-centered approach. 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

The electrocardiogram (ECG) remains a cornerstone of modern cardiology, providing rapid, non-invasive, and widely accessible diagnostic insights. While ECG interpretation is an essential skill for clinicians, certain patterns can be subtle or atypical, posing diagnostic challenges. In our previous review (doi.org/10.3390/jpm12111754), we explored several uncommon ECG syndromes with significant clinical implications. However, the spectrum of electrocardiographic abnormalities extends far beyond those initially discussed. In this second installment, we expand our discussion of rare and underrecognized ECG syndromes, including Long QT, Jervell and Lange-Nielsen, Romano–Ward, Andersen–Tawil, Timothy, Short QT, and Twiddler’s syndromes, as well as Noonan, Barlow’s, Bundgaard, BRASH, Carvajal, Naxos, and Danon disease. We highlight their clinical context, characteristic findings, and implications for diagnosis and management. These conditions range from acute, life-threatening emergencies requiring immediate intervention to chronic electrical disorders necessitating long-term monitoring and risk stratification. By broadening our focus, we aim to enhance awareness and recognition of these entities, ultimately improving patient outcomes through timely and accurate diagnosis. Full article

Medical students face significant challenges retaining complex information, such as interpreting ECGs for coronary artery occlusions, amidst demanding curricula. While artificial intelligence (AI) is increasingly used for medical image analysis, this study explored using generative AI (DALLE-3) to create mnemonic-based images to enhance human learning and retention of medical images, in particular, electrocardiograms (ECGs). This study is among the first to investigate generative AI as a tool not for automated diagnosis but as a human-centered educational aid designed to enhance long-term retention in complex visual tasks like ECG interpretation. We conducted a comparative study with 275 first-year medical students across six campuses; an experimental group (n = 40) received a lecture supplemented with AI-generated mnemonic ECG images, while control groups (n = 235) received standard lectures with traditional ECG diagrams. Student achievement and retention were assessed by course examinations, and student preference and engagement were measured using the Situational Interest Survey for Multimedia (SIS-M). Control groups showed a significant decline in scores on the relevant exam question over time, whereas the experimental group’s scores remained stable, indicating improved long-term retention. Experimental students also reported significantly higher situational interest in the mnemonic-based images over traditional images. AI-generated mnemonic images can effectively improve long-term retention of complex ECG interpretation skills and enhance student engagement and preference, highlighting generative AI’s potential as a valuable cognitive tool in image analysis during medical education. Full article

Background: Premature ventricular complexes (PVCs) are common arrhythmias that can range from benign to clinically significant. While PVCs have been extensively studied in the general population, gender-specific differences in their characteristics, prevalence, and clinical impact remain underexplored. This study aims to investigate the unique features of PVCs in women and their potential implications for diagnosis and management. Methods: We analyzed a cohort of female patients diagnosed with PVCs, assessing their electrocardiographic patterns, symptomatology, and clinical outcomes. Data were collected from medical records, including Holter monitoring, electrocardiograms (ECGs), and echocardiographic findings. The study also evaluated the association between PVC burden and underlying cardiac conditions. Results: This study analyzed 161 patients (59 females, 91 males) with PVCs, revealing significant sex-based differences. Males were older, had higher BMI, and smoked more, while females experienced more presyncope. ECGs showed greater QRS fragmentation in males. TTE and CMR found males had larger ventricles, lower EF, and more myocardial fibrosis (LGE: 59.34% vs. 37.93%). Patients with LGE were older and had worse clinical outcomes, including higher ICD implantation and hospitalization rates. Despite these structural differences, treatment efficacy was similar across groups. Conclusion: This study highlights key differences in PVC characteristics among women, underscoring the need for gender-specific approaches in clinical evaluation and management. Recognizing these distinctions may aid in early diagnosis, reduce unnecessary interventions, and improve patient outcomes. Further research is warranted to explore the long-term implications of PVCs in women and optimize therapeutic strategies. Full article

Ongoing advancements in machine learning show great promise for automating medical data interpretation, potentially saving valuable time in life-threatening situations. One such area is the analysis of electrocardiograms (ECGs). In this study, we investigate the effectiveness of using a DenseNet121 encoder with three decoder architectures: Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), and a Transformer-based approach. We utilize these models to generate automated ECG reports from the publicly available PTB-XL dataset. Our results show that the DenseNet121 encoder paired with a GRU decoder yields higher performance than previously achieved. It achieves a METEOR (Metric for Evaluation of Translation with Explicit Ordering) score of 72.19%, outperforming the previous best result of 55.53% from a ResNet34-based model that used LSTM and Transformer components. We also discuss several important design choices, such as how to initialize decoders, how to use attention mechanisms, and how to apply data augmentation. These findings offer valuable insights into creating more robust and reliable deep learning tools for ECG interpretation. Full article

Atrial fibrillation (AF) is a type of cardiac arrhythmia with a worldwide prevalence of more than 37 million among the adult population. This elusive disease is a major risk factor for ischemic stroke, along with increased rates of significant morbidity and eventual mortality. It is clinically diagnosed using medical-grade electrocardiogram (ECG) sensors in ambulatory settings. The recent emergence of consumer-grade wearables equipped with photoplethysmography (PPG) sensors has exhibited considerable promise for non-intrusive continuous monitoring in free-living conditions. However, the scarcity of large-scale public PPG datasets acquired from wearable devices hinders the development of intelligent automatic AF detection algorithms unaffected by motion artifacts, saturated ambient noise, inter- and intra-subject differences, or limited training data. In this work, we present a deep learning framework that leverages convolutional layers with a bidirectional long short-term memory (CNN-BiLSTM) network and an attention mechanism for effectively classifying raw AF rhythms from normal sinus rhythms (NSR). We derive and feed heart rate variability (HRV) and pulse rate variability (PRV) features as auxiliary inputs to the framework for robustness. A larger teacher model is trained using the MIT-BIH Arrhythmia ECG dataset. Through transfer learning (TL), its learned representation is adapted to a compressed student model (32x smaller) variant by using knowledge distillation (KD) for classifying AF with the UMass and MIMIC-III datasets of PPG signals. This results in the student model yielding average improvements in accuracy, sensitivity, F1 score, and Matthews correlation coefficient of 2.0%, 15.05%, 11.7%, and 9.85%, respectively, across both PPG datasets. Additionally, we employ Gradient-weighted Class Activation Mapping (Grad-CAM) to confer a notion of interpretability to the model decisions. We conclude that through a combination of techniques such as TL and KD, i.e., pre-trained initialization, we can utilize learned ECG concepts for scarcer PPG scenarios. This can reduce resource usage and enable deployment on edge devices. Full article

Artificial intelligence (AI) is transforming cardiovascular medicine by enabling the analysis of high-dimensional biomedical data with unprecedented precision. Initially employed to automate human tasks such as electrocardiogram (ECG) interpretation and imaging segmentation, AI’s true potential lies in uncovering hidden disease data patterns, predicting long-term cardiovascular risk, and personalizing treatments. Unlike human cognition, which excels in certain tasks but is limited by memory and processing constraints, AI integrates multimodal data sources—including ECG, echocardiography, cardiac magnetic resonance (CMR) imaging, genomics, and wearable sensor data—to generate novel clinical insights. AI models have demonstrated remarkable success in early dis-ease detection, such as predicting heart failure from standard ECGs before symptom on-set, distinguishing genetic cardiomyopathies, and forecasting arrhythmic events. However, several challenges persist, including AI’s lack of contextual understanding in most of these tasks, its “black-box” nature, and biases in training datasets that may contribute to disparities in healthcare delivery. Ethical considerations and regulatory frameworks are evolving, with governing bodies establishing guidelines for AI-driven medical applications. To fully harness the potential of AI, interdisciplinary collaboration among clinicians, data scientists, and engineers is essential, alongside open science initiatives to promote data accessibility and reproducibility. Future AI models must go beyond task automation, focusing instead on augmenting human expertise to enable proactive, precision-driven cardiovascular care. By embracing AI’s computational strengths while addressing its limitations, cardiology is poised to enter an era of transformative innovation beyond traditional diagnostic and therapeutic paradigms. Full article

The advent of Tiny Machine Learning (TinyML) has unlocked the potential to deploy machine learning models on resource-constrained edge devices, revolutionizing real-time monitoring in Internet of Medical Things (IoMT) applications. This study introduces a novel approach to real-time electrocardiogram (ECG) anomaly detection by integrating TinyML with edge Artificial Intelligence (AI) on low-power embedded systems. We demonstrate the feasibility and effectiveness of deploying optimized models on edge devices, such as the Raspberry Pi and Arduino, to detect ECG anomalies, including arrhythmias. The proposed workflow encompasses data preprocessing, feature extraction, and model inference, all executed directly on the edge device, eliminating the need for cloud resources. To address the constraints of memory and power consumption in wearable devices, we applied advanced optimization techniques, including model pruning and quantization, achieving an optimal balance between accuracy and resource utilization. The optimized model achieved an accuracy of 92.3% while reducing the power consumption to 0.024 mW, enabling continuous, long-term health monitoring with minimal energy requirements. This work highlights the potential of TinyML to advance edge AI for real-time medical applications. Full article

Background: Heart rate variability (HRV) is a key biomarker reflecting autonomic nervous system (ANS) function and neurocardiac regulation. Reduced HRV has been associated with cardiovascular risk, neurodegenerative disorders, and autonomic dysfunction. In Parkinson’s disease (PD), HRV impairments indicate altered autonomic balance, which may be modifiable through structured exercise interventions. This study investigates the effects of aerobic exercise on HRV in patients with PD and evaluates autonomic adaptations to rehabilitation. Methods: A total of 110 patients with PD (55 male, 55 female) participated in a supervised three-month aerobic exercise program. HRV was assessed pre- and post-intervention using electrocardiogram (ECG) recordings. Time-domain and frequency-domain HRV metrics, including standard deviation of RR intervals (SDRR), very-low-frequency (VLF), low-frequency (LF), high-frequency (HF) power, and LF/HF ratio, were analyzed. Principal Component Analysis (PCA) and clustering techniques were applied to identify subgroups of HRV responders based on autonomic adaptation. Results: Significant improvements in HRV were observed post-intervention, with a reduction in LF/HF ratio (p < 0.05), indicating improved autonomic balance. Cluster analysis identified four distinct HRV response subgroups: Strong Responders, Moderate Responders, Mixed/Irregular Responders, and Low Responders. These findings highlight individual variability in autonomic adaptations to exercise. PCA revealed that key HRV parameters contribute differently to autonomic regulation, emphasizing the complexity of HRV changes in PD rehabilitation. Conclusions: This study demonstrates that aerobic exercise induces beneficial autonomic adaptations in PD patients, as reflected by HRV changes. The identification of response subgroups suggests the need for personalized rehabilitation strategies to optimize autonomic function. Further research is warranted to explore the long-term impact of HRV-guided rehabilitation interventions in PD management. Full article

Arrhythmia is an irregularity in the rhythm of the heartbeat, and it is the primary method for detecting cardiac abnormalities. The electrocardiogram (ECG) identifies arrhythmias and is one of the methods used to diagnose cardiac issues. Traditional arrhythmia detection methods are time-consuming, error-prone, and often subjective, making it difficult for doctors to discern between distinct patterns of arrhythmia. To understand ECG signals, this study presents a multi-class classifier and an autoencoder with long short-term memory (LSTM) network layers for extracting signal properties on a dataset from the Massachusetts Institute of Technology and Boston’s Beth Israel Hospital (MIT-BIH). The suggested model had an accuracy rate of 98.57% on the arrhythmia dataset and 97.59% on the supraventricular dataset. In contrast to other deep learning models, the proposed model eliminates the problem of the gradient disappearing in classification tasks. Full article

Pennsylvania started newborn screening for Pompe disease (PD) in 2016. As a result, the prevalence of PD has increased with early detection, primarily of late-onset Pompe disease (LOPD). No clear guidelines exist regarding if and when to initiate enzyme replacement therapy (ERT) in patients identified through a newborn screen (NBS). To help define the natural history and indications for starting ERT, we present the long-term follow-up data of 45 patients identified through NBS from 2016 to 2021. These patients were evaluated at regular intervals through our multi-disciplinary clinic at the Children’s Hospital of Philadelphia (CHOP) with physical examinations, physical therapy evaluations, muscle biomarkers including creatine kinase (CK), aspartate aminotransferase (AST), alanine aminotransferase (ALT), and hexosaminidase 4 levels (Hex4), as well as cardiac evaluation at certain points in time. We found that newborn screening of acid alpha-glucosidase (GAA) enzyme detected primarily LOPD. One case of infantile-onset PD (IOPD) was detected. Muscle biomarkers in LOPD were elevated at birth and showed a general downward trend over time. NBS GAA levels and initial CK levels helped to differentiate LOPD cases from unaffected infants (carriers, pseudodeficiency alleles), while Hex4 was not a meaningful discriminator. On repeat NBS, there was a significant difference between mean GAA levels for the unaffected vs. compound heterozygote groups and unaffected vs. homozygote groups for the common splice site pathogenic variant (c.-32-13T>G). Echocardiogram and electrocardiogram (EKG) are essentially normal at the first evaluation in LOPD. One LOPD patient was started on ERT at age 4.5 months. Continued data collection on these patients is critical for developing management guidelines, including timing of ERT and improved genotype–phenotype correlation. Full article

Monitoring nociception under general anesthesia remains challenging due to the complexity of pain pathways and the limitations of single-parameter methods. In this study, we introduce a multimodal approach that integrates electroencephalogram (EEG), photoplethysmography (PPG), and electrocardiogram (ECG) signals to predict nociception. We collected data from patients undergoing general anesthesia at two hospitals and developed and compared two deep learning models: a Multilayer Perceptron (MLP) and a Long Short-Term Memory (LSTM) network. Both models were trained on expert anesthesiologists’ assessments of nociception. We evaluated normalization strategies for offline and online usage and found that Min–Max normalization was most effective for our dataset. Our results demonstrate that the MLP model accurately captured nociceptive changes in response to painful surgical stimuli, whereas the LSTM model provided smoother predictions but with lower sensitivity to rapid changes. These findings underscore the potential of multimodal, deep learning-based solutions to improve real-time nociception monitoring in diverse clinical settings. Full article

In recent years, smart devices have proven their effectiveness in monitoring mental health issues and have played a crucial role in providing therapy. The ability to embed sensors in fabrics opens new horizons for mental healthcare, addressing the growing demand for innovative solutions in monitoring and therapy. The objective of this review is to understand mental health, its impact on the human body, and the latest advancements in the field of smart textiles (sensors, electrodes, and smart garments) for monitoring physiological signals such as respiration rate (RR), electroencephalogram (EEG), electrodermal activity (EDA), electrocardiogram (ECG), and cortisol, all of which are associated with mental health disorders. Databases such as Web of Science (WoS) and Scopus were used to identify studies that utilized smart textiles to monitor specific physiological parameters. Research indicates that smart textiles provide promising results compared to traditional methods, offering enhanced comfort for long-term monitoring. Full article

(1) Left ventricular assist device (LVAD) implantation is increasingly used as a treatment option for patients with advanced heart failure (HF). There is a need to provide patients with LVAD with long-term care, preferably at home. The implementation of home-based telerehabilitation (HTR) and telecare offers new opportunities in this field. Purpose: The purpose of this study was to assess the feasibility and safety of HTR and telecare in HF patients with implanted LVAD and evaluate patients’ acceptance of and adherence to HTR. (2) The study enrolled 30 HF patients with recently implanted LVAD (21 Heart Mate III, 9 Heart Ware) (29 males, mean 59 years) who underwent a 12-week telecare and HTR program based on walking, respiratory, and resistance training, five times weekly. HTR was telemonitored with a device adjusted to register electrocardiogram (ECG) recordings and to transmit data via a mobile phone network to the monitoring center. The moments of automatic ECG registration were pre-set and coordinated with exercise. The influence on physical capacity was assessed by comparing changes in peak oxygen consumption (pVO₂; [mL/kg/min]) and workload duration (t; [s]) during the cardiopulmonary exercise test. (3) HTR resulted in a significant physical capacity improvement in pVO₂ 12.5 ± 2.9 vs. 15.1 ± 3.0 (p < 0.001), and workload duration t 628 ± 204 vs. 728 ± 222 (p < 0.001) during the cardiopulmonary exercise test. There were neither deaths nor adverse events during HTR. Patients accepted HTR, including the need for interactive everyday collaboration with the medical team. All patients completed HTR. (4) HTR is a feasible and safe form of rehabilitation that is well-accepted by patients. The adherence to HTCR was high. Full article