Search Results (470)

Background/Objectives: Chronological age (CA) is commonly used in clinical decision-making, yet it may not accurately reflect biological aging. Recent advances in artificial intelligence (AI) allow estimation of electrocardiogram (ECG)-derived heart age, which may serve as a non-invasive biomarker for physiological aging. This study aimed to develop and validate a deep learning model to predict ECG-heart age in individuals with no structural heart disease. Methods: We trained a convolutional neural network (DenseNet-121) using 12-lead ECGs from 292,484 individuals (mean age: 51.4 ± 13.8 years; 42.3% male) without significant cardiac disease. Exclusion criteria included missing age data, age <18 or >90 years, and structural abnormalities. CA was used as the target variable. Model performance was evaluated using the coefficient of determination (R²), Pearson correlation coefficient (PCC), mean absolute error (MAE), and root mean square error (RMSE). External validation was conducted using 1191 independent ECGs. Results: The model demonstrated strong predictive performance (R² = 0.783, PCC = 0.885, MAE = 5.023 years, RMSE = 6.389 years). ECG-heart age tended to be overestimated in younger adults (≤30 years) and underestimated in older adults (≥70 years). External validation showed consistent performance (R² = 0.703, PCC = 0.846, MAE = 5.582 years, RMSE = 7.316 years). Conclusions: The proposed AI-based model accurately estimates ECG-heart age in individuals with structurally normal hearts. ECG-derived heart age may serve as a reliable biomarker of biological aging and support future risk stratification strategies. Full article

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

Left ventricular systolic dysfunction (LVSD) is associated with increased mortality and is sometimes reversible when found early. Artificial intelligence (AI)-enabled electrocardiogram (ECG) has emerged as an efficient screening tool for LVSD, but has not been validated in left bundle branch block (LBBB) patients. The clinical significance of developing an AI prediction model for LBBB patients lies in the fact that LBBB can be a cause, consequence, or both of LVSD. This pilot study was designed to develop an AI model for LVSD detection in the LBBB population using a limited dataset. ECG data from 508 patients with sinus rhythm and LBBB were labeled based on an LVSD threshold of 35%. To enhance the performance of a model derived from such a small and skewed dataset, we combined an autoencoder-based anomaly detection model with a convolutional neural network (CNN). We used a lead-wise ensemble technique for the final classification. Experimental results showed an accuracy of 0.81, precision of 0.87, recall of 0.56, and an area under the receiver operating characteristic curve of 0.75 in LVSD prediction among LBBB patients. Despite the limited dataset size, our study findings suggest the potential of deep learning techniques in detecting LVSD in patients with LBBB. Full article

Background/Objectives: Atrial fibrillation (AF) is a very common arrhythmia and the main cause of embolic events. Early diagnosis and treatment are crucial to prevent thromboembolic events. Although DOACs are an important advance in AF management, optimization is required. This study aims to evaluate the newly available evidence and experts’ opinions on the clinical care of AF patients and to develop a set of practical recommendations to improve the management of patients with AF. Methods: A questionnaire was developed on the topics of AF diagnosis, stroke prevention, rate and rhythm control, and management of comorbidities, based on the scientific committee’s judgment and a rapid literature review. The level of agreement of the panelists with each statement was evaluated using the Likert 5-point scale. The results of the questionnaire were discussed in a final meeting and practical recommendations were made. Results: Thirty-five Spanish panelists, all experts in AF management, answered the questionnaire. Most of the statements (78%) reached the levels of agreement or unanimity. Discrepancy (9%) and rejection (13%) were also reported. Conclusions: This study underscores the importance of a 12-lead electrocardiogram to diagnose AF, with wearable devices serving as useful tools; catheter ablation as a superior strategy for restoring and maintaining sinus rhythm compared to pharmacotherapy; the importance of comorbidity management to reduce incidence and recurrence of AF; adherence and persistence as critical factors for the efficacy and safety of anticoagulation; and the preference for DOACs, particularly apixaban and edoxaban, for stroke prevention in patients ≥75 years old or with chronic kidney disease. Full article

Background/Objectives: Heart failure (HF) is a growing global health burden, yet early detection remains challenging due to the limitations of traditional diagnostic tools such as electrocardiograms (ECGs). Recent advances in deep learning offer new opportunities to identify left ventricular systolic dysfunction (LVSD), a key indicator of HF, from ECG data. This study validates AiTiALVSD, our previously developed artificial intelligence (AI)-enabled ECG Software as a Medical Device, for its accuracy, transparency, and robustness in detecting LVSD. Methods: This retrospective single-center cohort study involved patients suspected of LVSD. The AiTiALVSD model, based on a deep learning algorithm, was evaluated against echocardiographic ejection fraction values. To enhance model transparency, the study employed Testing with Concept Activation Vectors (TCAV), clustering analysis, and robustness testing against ECG noise and lead reversals. Results: The study involved 688 participants and found AiTiALVSD to have a high diagnostic performance, with an AUROC of 0.919. There was a significant correlation between AiTiALVSD scores and left ventricular ejection fraction values, confirming the model’s predictive accuracy. TCAV analysis showed the model’s alignment with medical knowledge, establishing its clinical plausibility. Despite its robustness to ECG artifacts, there was a noted decrease in specificity in the presence of ECG noise. Conclusions: AiTiALVSD’s high diagnostic accuracy, transparency, and resilience to common ECG discrepancies underscore its potential for early LVSD detection in clinical settings. This study highlights the importance of transparency and robustness in AI-ECG, setting a new benchmark in cardiac care. Full article

There is a lack of studies on the effectiveness of polar-transformed spectrograms in the visualization and prediction of cardiac arrhythmias from electrocardiogram (ECG) data. In this study, single-lead ECG waveforms were converted into two-dimensional rectangular time–frequency spectrograms and polar time–frequency spectrograms. Three pre-trained convolutional neural network (CNN) models (ResNet50, MobileNet, and DenseNet121) served as baseline networks for model development and testing. Prediction performance and visualization quality were evaluated across various image resolutions. The trade-offs between image resolution and model capacity were quantitatively analyzed. Polar-transformed spectrograms demonstrated superior delineation of R-R intervals at lower image resolutions (e.g., 96 × 96 pixels) compared to conventional spectrograms. For deep-learning-based classification of cardiac arrhythmias, polar-transformed spectrograms achieved comparable accuracy to conventional spectrograms across all evaluated resolutions. The results suggest that polar-transformed spectrograms are particularly advantageous for deep CNN predictions at lower resolutions, making them suitable for edge computing applications where the reduced use of computing resources, such as memory and power consumption, is desirable. Full article

The use of temporary mechanical circulatory support in refractory heart failure cardiogenic shock (HFCS) has risen, leading to potential complications. Post-Cardiac Injury Syndrome (PCIS) from Impella insertion is rare but may result from subclavian artery manipulation and aortic irritation. We report the first case of pericarditis (PCIS) caused by Impella 5.5 insertion in an HFCS patient awaiting heart transplantation. The patient developed chest pain, tachycardia, and hypotension post-Impella insertion. Laboratory results and electrocardiograms confirmed PCIS. Treatment with Ibuprofen and Colchicine was successful. He received a heart transplant 14 days later. This case emphasizes recognizing iatrogenic pericarditis after Impella insertion and the need to avoid additional myocardial strain. Full article

We introduce a novel technique for the sonification/auditory representation of a 12-lead electrocardiogram (ECG), the standard diagnostic method for the detection of ST elevation myocardial infarction (STEMI). Our approach to ST elevation sonification conveys the detailed variation of the ST segment to enable differentiated, correct interpretation and severity without consulting a visual display. We present a variety of novel sonification designs and discuss their benefits and limitations. As part of an emergency training program, a cohort of 44 medical students (5th academic year) participated in a classification study in which the diagnostic accuracy of the participants was determined with regard to audibly presented ECG sequences of different STEMI severity levels. Regarding the classification of sonified ECG sequences, the discrimination of isoelectricity (IE, the healthy class) from all other (STEMI) classes combined yielded a perfect classification of all 660 classification instances (sensitivity = specificity = 1). With respect to the individual classification of all five classes (IE, inferior/anterior, and moderate/severe STEMI), an overall accuracy of 0.82 (0.79, 0.85) and an intraclass coefficient of $\kappa =0.77$ were estimated. Full article

Cockpit noise, as a critical environmental factor affecting flight safety, may impair pilots’ cognitive functions, leading to a decreased operational performance and decision-making errors, thereby posing potential threats to aviation safety. In order to reveal the relationship between the cockpit noise sound pressure level and pilot physiological indicators, and provide a scientific basis for cockpit noise airworthiness standards, this experiment takes pilot trainees as the research subject. Based on the principle of multimodal data synchronization, a sound field reconstruction system is used to reconstruct the cockpit sound field. Electroencephalogram (EEG), electrocardiogram (ECG), and electrodermal activity (EDA) measurements are carried out in different sound pressure level noise operating environments. The results show that with the increase in the sound pressure level, the significant suppression of α-wave activity in the occipital and parietal regions suggests that the cortical resting state is lifted and visual attention is enhanced; the enhancement of the β-wave in the frontal regions reflects the enhancement of alertness and prefrontal executive control, and the suppression of θ-wave activity in the frontal and temporal regions may indicate that cognitive tuning is suppressed, which reflects the brain’s rapid adaptive response to external noise stimuli in a high-noise environment; noise exposure triggers sustained sympathetic nerve hyperactivity, which is manifested by a significant acceleration of the heart rate and a significant increase in the mean value of skin conductance when the noise sound pressure level exceeds 70 dB(A). The correlation analysis between physiological indicators shows that cockpit noise has a multi-system synergistic effect on human physiological indicators. The experimental results indicate that noise has a significant impact on EEG, ECG, and EDA indicators. Full article

Background/Objectives: Accurate and efficient diagnosis of heart disease through electrocardiogram (ECG) analysis remains a critical challenge in clinical practice due to noise interference, morphological variability, and the complexity of overlapping cardiac signals. Methods: This study presents a comprehensive deep learning (DL) framework that integrates advanced ECG signal segmentation with transfer learning-based classification, aimed at improving diagnostic performance. The proposed ECG segmentation algorithm introduces a distinct and original approach compared to prior research by integrating adaptive preprocessing, histogram-based lead separation, and robust point-tracking techniques into a unified framework. While most earlier studies have addressed ECG image processing using basic filtering, fixed-region cropping, or template matching, our method uniquely focuses on automated and precise reconstruction of individual ECG leads from noisy and overlapping multi-lead images—a challenge often overlooked in previous work. This innovative segmentation strategy significantly enhances signal clarity and enables the extraction of richer and more localized features, boosting the performance of DL classifiers. The dataset utilized in this work of 12 lead-based standard ECG images consists of four primary classes. Results: Experiments conducted using various DL models—such as VGG16, VGG19, ResNet50, InceptionNetV2, and GoogleNet—reveal that segmentation notably enhances model performance in terms of recall, precision, and F1 score. The hybrid VGG19 + SVM model achieved 98.01% and 100% accuracy in multi-class classification, along with average accuracies of 99% and 97.95% in binary classification tasks using the original and reconstructed datasets, respectively. Conclusions: The results highlight the superiority of deep, feature-rich models in handling reconstructed ECG signals and confirm the value of segmentation as a critical preprocessing step. These findings underscore the importance of effective ECG segmentation in DL applications for automated heart disease diagnosis, offering a more reliable and accurate solution. Full article

The analysis of electrocardiogram (ECG) signals is profoundly affected by the presence of electromyographic (EMG) noise, which can lead to substantial misinterpretations in healthcare applications. To address this challenge, we present ECGDnet, an innovative architecture based on Transformer technology, specifically engineered to denoise multi-channel ECG signals. By leveraging multi-head self-attention mechanisms, positional embeddings, and an advanced sequence-to-sequence processing architecture, ECGDnet effectively captures both local and global temporal dependencies inherent in cardiac signals. Experimental validation on real-world datasets demonstrates ECGDnet’s remarkable efficacy in noise suppression, achieving a Signal-to-Noise Ratio (SNR) of 19.83, a Normalized Mean Squared Error (NMSE) of 0.9842, a Reconstruction Error (RE) of 0.0158, and a Pearson Correlation Coefficient (PCC) of 0.9924. These results represent significant improvements from traditional deep learning approaches while maintaining complex signal morphology and effectively mitigating noise interference. Full article

Heart attack is a leading cause of mortality, necessitating timely and precise diagnosis to improve patient outcomes. However, timely diagnosis remains a challenge due to the complex and nonlinear relationships between clinical indicators. Machine learning (ML) and deep learning (DL) models have the potential to predict cardiac conditions by identifying complex patterns within data, but their “black-box” nature restricts interpretability, making it challenging for healthcare professionals to comprehend the reasoning behind predictions. This lack of interpretability limits their clinical trust and adoption. The proposed approach addresses this limitation by integrating predictive modeling with Explainable AI (XAI) to ensure both accuracy and transparency in clinical decision-making. The proposed study enhances heart attack prediction using the University of California, Irvine (UCI) dataset, which includes various heart analysis parameters collected through electrocardiogram (ECG) sensors, blood pressure monitors, and biochemical analyzers. Due to class imbalance, the Synthetic Minority Over-sampling Technique (SMOTE) was applied to enhance the representation of the minority class. After preprocessing, various ML algorithms were employed, among which Artificial Neural Networks (ANN) achieved the highest performance with 96.1% accuracy, 95.7% recall, and 95.7% F1-score. To enhance the interpretability of ANN, two XAI techniques, specifically SHapley Additive Explanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME), were utilized. This study incrementally benchmarks SMOTE, ANN, and XAI techniques such as SHAP and LIME on standardized cardiac datasets, emphasizing clinical interpretability and providing a reproducible framework for practical healthcare implementation. These techniques enable healthcare practitioners to understand the model’s decisions, identify key predictive features, and enhance clinical judgment. By bridging the gap between AI-driven performance and practical medical implementation, this work contributes to making heart attack prediction both highly accurate and interpretable, facilitating its adoption in real-world clinical settings. Full article

Background: Post-traumatic stress disorder (PTSD) is a serious psychiatric condition that can lead to severe anxiety, depression, and cardiovascular complications if left untreated. Early and accurate diagnosis is critical. This study aims to develop and evaluate an artificial intelligence-based classification system using electrocardiogram (ECG) signals for the detection of PTSD. Methods: Raw ECG signals were transformed into time–frequency images using Continuous Wavelet Transform (CWT) to generate 2D scalogram representations. These images were classified using deep learning-based convolutional neural networks (CNNs), including AlexNet, GoogLeNet, and ResNet50. In parallel, statistical features were extracted directly from the ECG signals and used in traditional machine learning (ML) classifiers for performance comparison. Four different segment lengths (5 s, 10 s, 15 s, and 20 s) were tested to assess their effect on classification accuracy. Results: Among the tested models, ResNet50 achieved the highest classification accuracy of 94.92%, along with strong MCC, sensitivity, specificity, and precision metrics. The best performance was observed with 5-s signal segments. Deep learning (DL) models consistently outperformed traditional ML approaches. The area under the curve (AUC) for ResNet50 reached 0.99, indicating excellent classification capability. Conclusions: This study demonstrates that CNN-based models utilizing time–frequency representations of ECG signals can effectively classify PTSD with high accuracy. Segment length significantly influences model performance, with shorter segments providing more reliable results. The proposed method shows promise for non-invasive, ECG-based diagnostic support in PTSD detection. Full article

Background and Objectives: Major depressive disorder (MDD) is a prevalent psychiatric illness increasingly recognized as a systemic condition with implications for cardiovascular diseases. Growing evidence indicates that individuals with MDD have an elevated risk of cardiovascular mortality, underscoring the need for reliable, non-invasive biomarkers to assess cardiac risk. While underlying mechanisms remain unclear, electrocardiogram (ECG)-based markers offer a promising, non-invasive means of evaluation. Among these, the electrical risk score (ERS), a composite derived from specific ECG parameters, has emerged as a predictor of adverse cardiac outcomes. This study aimed to investigate the association between ERS and MDD, and whether ERS correlates with depression severity and illness duration. Materials and Methods: In this retrospective cross-sectional study, 12-lead ECGs were evaluated to calculate the ERS based on six ECG parameters: heart rate, corrected QT interval, Tp-e interval, frontal QRS-T angle, QRS transition zone, and presence of left ventricular hypertrophy according to Sokolow–Lyon criteria. The Hamilton Depression Rating Scale (HAM-D) was utilized. Results: The study included 102 patients with MDD and 62 healthy controls. No significant differences were observed in baseline or laboratory parameters between the groups. However, heart rate, Tp-e interval, frontal QRS-T angle, and ERS were significantly higher in the depression group. ROC analysis identified ERS as the strongest predictor of depression. ERS was significantly higher in patients with severe depression compared to those with mild symptoms and showed a positive correlation with both disease duration and HAM-D score. Conclusions: Here, we show that the ECG-derived ERS is significantly elevated in patients with MDD and is associated with increased cardiac risk. ERS outperformed conventional ECG parameters in identifying individuals with depression and demonstrated positive associations with both illness duration and symptom severity. These findings suggest that ERS may serve as a practical, non-invasive biomarker for assessing cardiovascular vulnerability in this population. Full article

At the core of AI-driven electrocardiogram diagnosis lies the precise localization of the QRS complex. While QRS detection methods for multiple leads have been researched adequately in the last few decades, their multi-lead strategies still need to be designed manually. Therefore, a QRS detector that can fuse multiple leads automatically is still worth investigating. Methods: The proposed QRS detector comprises a leads-distillation module (LDM) and a QRS detection module. The LDM can distill multi-lead signals into single-lead ones. This procedure minimizes the weight proportions assigned to noisy leads, enabling the network to generate a novel signal that facilitates the recognition of QRS waves. The QRS detection module, utilizing U-Net, is capable of discerning QRS complexes from the novel signal. Results: Our method demonstrates outstanding performance with a parameter count of only 5216. It achieves an excellent F1 score of 99.83 on the MITBIHA database and 99.77 on the INCART database, specifically in the inter-patient pattern. In the cross-database pattern, our approach maintains a strong performance with an F1 score of 99.22 on the INCART database and an F1 score of 99.09 on the MITBIHA database. Conclusion: Our method provides a novel idea for universal multi-lead QRS detection. It possesses advantages, such as reduced computational parameters, enhanced precision, and heightened compatibility. Significance: Our method canceled the repeated deployment of the QRS detection function to different lead configurations in the electrocardiogram (ECG) diagnostic system. Moreover, the scaling operation may become a simple tool to decrease the computational load of the network. Full article