Search Results (9)

Accurate detection of premature atrial contractions (PACs) and premature ventricular contractions (PVCs) in single-lead electrocardiograms (ECGs) is crucial for early identification of patients at risk for atrial fibrillation, cardiomyopathy, and other adverse outcomes. In this work, we present a fully convolutional one-dimensional U-Net that reframes beat classification as a segmentation task and directly detects normal beats, PACs, and PVCs from raw ECG signals. The architecture employs a ConvNeXt V2 encoder with simple decoder blocks and does not rely on explicit R-peak detection, handcrafted features, or fixed-length input windows. The model is trained on the Icentia11k database and an in-house single-lead ECG dataset that emphasizes challenging, noisy recordings, and is validated on the CPSC2020 database. Generalization is assessed across several benchmark and clinical datasets, including MIT-BIH Arrhythmia (ADB), MIT 11, AHA, NST, SVDB, CST STRIPS, and CPSC2020. The proposed method achieves near-perfect QRS detection (sensitivity and precision up to 0.999) and competitive PVC performance, with sensitivity ranging from 0.820 (AHA) to 0.986 (MIT 11) and precision up to 0.993 (MIT 11). PAC detection is more variable, with sensitivities between 0.539 and 0.797 and precisions between 0.751 and 0.910, yet the resulting F1-score of 0.72 on SVDB exceeds that of previously published approaches. Model interpretability is addressed using Layer-wise Gradient-weighted Class Activation Mapping (LayerGradCAM), which confirms physiologically plausible attention to QRS complexes for PVCs and to P-waves for PACs. Overall, the proposed framework provides a robust, interpretable, and hardware-efficient solution for joint PAC and PVC detection in noisy, single-lead ECG recordings, suitable for integration into Holter and wearable monitoring systems. Full article

We propose a dual-branch deep learning framework for reconstructing standard 12-lead electrocardiograms (ECGs) from a single-lead input. The model integrates waveform information from Lead I ECG signals with clinically interpretable metadata to enhance reconstruction fidelity and introduces predictive uncertainty estimation to improve interpretability and reliability. A publicly available dataset of 10,646 ECG records was utilized. The model combined Lead I signals with clinical metadata through two processing branches: a CNN–BiLSTM branch for time-series data and a fully connected branch for metadata. Monte Carlo dropout was applied during inference to generate uncertainty estimates. Reconstruction performance was evaluated using Pearson’s correlation coefficient and root mean square error. Metadata consistently contributed to performance improvements, particularly in the QRS complexes and T-wave segments, and the proposed framework outperformed U-Net when metadata were included. Predictive uncertainty showed moderate to strong positive correlations with reconstruction errors, especially in the chest leads, and heatmaps revealed waveform regions with reduced reliability in arrhythmic and morphologically atypical cases. To the best of our knowledge, this is the first study to incorporate predictive uncertainty into ECG reconstruction. These findings suggest that combining waveform data with metadata and uncertainty quantification offers a promising approach for developing more trustworthy and clinically useful wearable ECG systems. 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

The aim of this study is to address the challenge of 12-lead ECG delineation by different encoder–decoder architectures of deep neural networks (DNNs). This study compares four concepts for encoder–decoders based on a fully convolutional architecture (CED-Net) and its modifications with a recurrent layer (CED-LSTM-Net), residual connections between symmetrical encoder and decoder feature maps (CED-U-Net), and sequential residual blocks (CED-Res-Net). All DNNs transform 12-lead representative beats to three diagnostic ECG intervals (P-wave, QRS-complex, QT-interval) used for the global delineation of the representative beat (P-onset, P-offset, QRS-onset, QRS-offset, T-offset). All DNNs were trained and optimized using the large PhysioNet ECG database (PTB-XL) under identical conditions, applying an advanced approach for machine-based supervised learning with a reference algorithm for ECG delineation (ETM, Schiller AG, Baar, Switzerland). The test results indicate that all DNN architectures are equally capable of reproducing the reference delineation algorithm’s measurements in the diagnostic PTB database with an average P-wave detection accuracy (96.6%) and time and duration errors: mean values (−2.6 to 2.4 ms) and standard deviations (2.9 to 11.4 ms). The validation according to the standard-based evaluation practices of diagnostic electrocardiographs with the CSE database outlines a CED-Net model, which measures P-duration (2.6 ± 11.0 ms), PQ-interval (0.9 ± 5.8 ms), QRS-duration (−2.4 ± 5.4 ms), and QT-interval (−0.7 ± 10.3 ms), which meet all standard tolerances. Noise tests with high-frequency, low-frequency, and power-line frequency noise (50/60 Hz) confirm that CED-Net, CED-Res-Net, and CED-LSTM-Net are robust to all types of noise, mostly presenting a mean duration error < 2.5 ms when compared to measurements without noise. Reduced noise immunity is observed for the U-net architecture. Comparative analysis with other published studies scores this research within the lower range of time errors, highlighting its competitive performance. Full article

Business-based decision support systems have been proposed for a few decades in the e-commerce and textile industries. However, these Decision Support Systems (DSS) have not been so productive in terms of business decision delivery. In our proposed model, we introduce a content-based image retrieval model based on a DSS and recommendations system for the textile industry, either offline or online. We used the Fashion MNIST dataset developed by Zalando to train our deep learning model. Our proposed hybrid model can demonstrate how a DSS can be integrated with a system that can separate customers based on their personal characteristics in order to tailor recommendations of products using behavioral analytics, which is trained based on MBTI personality data and Deap EEG data containing numerous pre-trained EEG brain waves. With this hybrid, a DSS can also show product usage analytics. Our proposed model has achieved the maximum accuracy compared to other proposed state-of-the-art models due to its qualitative analysis. In the first section of our analysis, we used a deep learning algorithm to train our CBIR model based on different classifiers such as VGG-net, Inception-Net, and U-net which have achieved an accuracy of 98.2% with a 2% of minimized error rate. The result was validated using different performance metrics such as F-score, F-weight, Precision, and Recall. The second part of our model has been tested on different machine learning algorithms with an accuracy rate of 89.9%. Thus, the entire model has been trained, validated, and tested separately to gain maximum efficiency. Our proposal for a DSS system, which integrates several subsystems with distinct functional sets and several model subsystems, is what makes this study special. Customer preference is one of the major problems facing merchants in the textile industry. Additionally, it can be extremely difficult for retailers to predict customer interests and preferences to create products that fulfill those needs. The three innovations presented in this work are a conceptual model for personality characterization, utilizing an amalgamation of an ECG classification model, a suggestion for a textile image retrieval model using Denoising Auto-Encoder, and a language model based on the MBTI for customer rating. Additionally, we have proposed a section showing how blockchain integration in data pre-processing can enhance its security and AI-based software quality assurance in a multi-model system. Full article

Analyzing biomedical data is a complex task that requires specialized knowledge. The development of knowledge and technology in the field of deep machine learning creates an opportunity to try and transfer human knowledge to the computer. In turn, this fact influences the development of systems for the automatic evaluation of the patient’s health based on data acquired from sensors. Electrocardiography (ECG) is a technique that enables visualizing the electrical activity of the heart in a noninvasive way, using electrodes placed on the surface of the skin. This signal carries a lot of information about the condition of heart muscle. The aim of this work is to create a system for semantic segmentation of the ECG signal. For this purpose, we used a database from Lobachevsky University available on Physionet, containing 200, 10-second, and 12-lead ECG signals with annotations, and applied one-dimensional U-Net with the addition of squeeze-excitation blocks. The created model achieved a set of parameters indicating high performance (for the test set: accuracy—0.95, AUC—0.99, specificity—0.95, sensitivity—0.99) in extracting characteristic parts of ECG signal such as P and T-waves and QRS complex, regardless of the lead. Full article

Atrial substrate modification after pulmonary vein isolation (PVI) of paroxysmal atrial fibrillation (pAF) can be assessed non-invasively by analyzing P-wave duration in the electrocardiogram (ECG). However, whether right (RA) and left atrium (LA) contribute equally to this phenomenon remains unknown. The present study splits fundamental P-wave features to investigate the different RA and LA contributions to P-wave duration. Recordings of 29 pAF patients undergoing first-ever PVI were acquired before and after PVI. P-wave features were calculated: P-wave duration ($PWD$), duration of the first ($PW{D}_{on\text{-}peak}$) and second ($PW{D}_{peak\text{-}off}$) P-wave halves, estimating RA and LA conduction, respectively. P-wave onset ($P{W}_{on}\text{-}R$) or offset ($P{W}_{off}\text{-}R$) to R-peak interval, measuring combined atrial/atrioventricular and single atrioventricular conduction, respectively. Heart-rate fluctuation was corrected by scaling. Pre- and post-PVI results were compared with Mann–Whitney U-test. $PWD$ was correlated with the remaining features. Only $PWD$ (non-scaling: $\Delta =-9.84\%$, $p=0.0085$, scaling: $\Delta =-17.96\%$, $p=0.0442$) and $PW{D}_{peak\text{-}off}$ (non-scaling: $\Delta =-22.03\%$, $p=0.0250$, scaling: $\Delta =-27.77\%$, $p=0.0268$) were decreased. Correlation of all features with $PWD$ was significant before/after PVI ($p<0.0001$), showing the highest value between $PWD$ and $P{W}_{on}\text{-}R$ (${\rho }_{max}=0.855$). $PWD$ correlated more with $PW{D}_{on\text{-}peak}$ ($\rho =$ 0.540–0.805) than $PW{D}_{peak\text{-}off}$ ($\rho =$ 0.419–0.710). $PWD$ shortening after PVI of pAF stems mainly from the second half of the P-wave. Therefore, noninvasive estimation of LA conduction time is critical for the study of atrial substrate modification after PVI and should be addressed by splitting the P-wave in order to achieve improved estimations. Full article

The reporting of U wave abnormalities is clinically important, but the measurement of this small electrocardiographic (ECG) feature is extremely difficult, especially in challenging recording conditions, such as stress exercise, due to contaminating noise. Furthermore, it is widely stated that ECG U waves are rarely observable at heart rates greater than 90 bpm. The aims of the study were (i) to assess the ability of multi-beat averaging to reveal the presence of U waves in ECGs contaminated by noise following exercise and (ii) to quantify the effect of exercise on U wave amplitude. The multi-beat averaging algorithm was applied to recover U waves in 20 healthy subjects in pre- and post-exercise recordings. Average beats were generated from 30 beat epochs. The prevalence of U waves and their amplitudes were measured in pre- and post-exercise recordings and changes in amplitude due to exercise were quantified. U waves were present in all subjects in pre-exercise recordings. Following exercise, U waves could not be seen in standard ECG but were observable in all 20 subjects by multi-beat averaging and despite significantly increased mean (±SD) heart rate (63 ± 8 bpm vs. 100 ± 9 bpm, p < 0.0001). Furthermore, U waves were observable in all subjects with heart rates greater than 90 bpm. U waves significantly increased in amplitude following exercise (38 ± 15 μV vs. 80 ± 48 μV, p = 0.0005). Multi-beat averaging is effective at recovering U waves contaminated by noise due to exercise. U waves were measurable in all subjects, dispelling the myth that U waves are rarely seen at elevated heart rates. U waves exhibit increased amplitudes at elevated heart rates following exercise. Full article

Electrocardiogram (ECG) signal analysis is a critical task in diagnosing the presence of any cardiac disorder. There are limited studies on detecting P-waves in various atrial arrhythmias, such as atrial fibrillation (AFIB), atrial flutter, junctional rhythm, and other arrhythmias due to P-wave variability and absence in various cases. Thus, there is a growing need to develop an efficient automated algorithm that annotates a 2D printed version of P-waves in the well-known ECG signal databases for validation purposes. To our knowledge, no one has annotated P-waves in the MIT-BIH atrial fibrillation database. Therefore, it is a challenge to manually annotate P-waves in the MIT-BIH AF database and to develop an automated algorithm to detect the absence and presence of different shapes of P-waves. In this paper, we present the manual annotation of P-waves in the well-known MIT-BIH AF database with the aid of a cardiologist. In addition, we provide an automatic P-wave segmentation for the same database using a fully convolutional neural network model (U-Net). This algorithm works on 2D imagery of printed ECG signals, as this type of imagery is the most commonly used in developing countries. The proposed automatic P-wave detection method obtained an accuracy and sensitivity of 98.56% and 98.78%, respectively, over the first 5 min of the second lead of the MIT-BIH AF database (a total of 8280 beats). Moreover, the proposed method is validated using the well-known automatically and manually annotated QT database (a total of 11,201 and 3194 automatically and manually annotated beats, respectively). This results in accuracies of 98.98 and 98.9%, and sensitivities of 98.97 and 97.24% for the automatically and manually annotated QT databases, respectively. Thus, these results indicate that the proposed automatic method can be used for analyzing long-printed ECG signals on mobile battery-driven devices using only images of the ECG signals, without the need for a cardiologist. Full article