Classification of Fibrillation Organisation Using Electrocardiograms to Guide Mechanism-Directed Treatments

Detection of regular rotational activity during cardiac arrhythmia using the Helmholtz decomposition for directed graphs

We introduce DGM-CURL, a novel method to detect reentry in cardiac activation based on the Helmholtz Decomposition for directed graphs. DGM-CURL is an extension to our open-source diagnostic framework Directed Graph Mapping (DGM). We compare DGM-CURL to two existing methods, Phase Mapping (PM), and Directed Cycle Search (DGM-CYCLE). Four datasets are explored: (1) simulated two-dimensional functional reentry, (2) simulated three-dimensional anatomical reentry, (3) clinical electroanatomical atrial tachycardia (AT) mapping data, and (4) experimental rat ventricular fibrillation (VF) optical mapping data. Results indicate general agreement between all three methods. Applying DGM-CURL on networks created by looking at differences in local activation times between nodes, we find that high curl values identify graph nodes that balance the inflow and outflow of these differences, indicating areas of reentry. We stress the importance of using multiple algorithms to detect rotational activity as each method is prone to errors. Using a combined approach decreases the susceptibility to errors and offers a more complete picture of the dynamics of rotational drivers in cardiac arrhythmias.

[A lightweight classification network for single-lead atrial fibrillation based on depthwise separable convolution and attention mechanism]

OBJECTIVES

To design a deep learning model that balances model complexity and performance to enable its integration into wearable ECG monitoring devices for automated diagnosis of atrial fibrillation.

METHODS

This study was performed based on data from 84 patients with atrial fibrillation, 25 patients with atrial fibrillation, and 18 subjects without obvious arrhythmia collected from the publicly available datasets LTAFDB, AFDB, and NSRDB, respectively. A lightweight attention network based on depthwise separable convolution and fusion of channel-spatial information, namely DSC-AttNet, was proposed. Depthwise separable convolution was introduced to replace standard convolution and reduce model parameters and computational complexity to realize high efficiency and light weight of the model. The multilayer hybrid attention mechanism was embedded to compute the attentional weights of the channels and spatial information at different scales to improve the feature expression ability of the model. Ten-fold cross-validation was performed on LTAFDB, and external independent testing was conducted on AFDB and NSRDB datasets.

RESULTS

DSC-AttNet achieved a ten-fold average accuracy of 97.33% and a precision of 97.30% on the test set, both of which outperformed the other 4 comparison models as well as the 3 classical models. The accuracy of the model on the external test set reached 92.78%, better than those of the 3 classical models. The number of parameters of DSC-AttNet was 1.01M, and the computational volume was 27.19G, both smaller than the 3 classical models.

CONCLUSIONS

This proposed method has a smaller complexity, achieves better classification performance, and has a better generalization ability for atrial fibrillation classification.

Automated atrial fibrillation and ventricular fibrillation recognition using a multi-angle dual-channel fusion network

Atrial fibrillation (AFIB) and ventricular fibrillation (VFIB) are two common cardiovascular diseases that cause numerous deaths worldwide. Medical staff usually adopt long-term ECGs as a tool to diagnose AFIB and VFIB. However, since ECG changes are occasionally subtle and similar, visual observation of ECG changes is challenging. To address this issue, we proposed a multi-angle dual-channel fusion network (MDF-Net) to automatically recognize AFIB and VFIB heartbeats in this work. MDF-Net can be seen as the fusion of a task-related component analysis (TRCA)-principal component analysis (PCA) network (TRPC-Net), a canonical correlation analysis (CCA)-PCA network (CPC-Net), and the linear support vector machine-weighted softmax with average (LS-WSA) method. TRPC-Net and CPC-Net are employed to extract deep task-related and correlation features, respectively, from two-lead ECGs, by which multi-angle feature-level information fusion is realized. Since the convolution kernels of the above methods can be directly extracted through TRCA, CCA and PCA technologies, their training time is faster than that of convolutional neural networks. Finally, LS-WSA is employed to fuse the above features at the decision level, by which the classification results are obtained. In distinguishing AFIB and VFIB heartbeats, the proposed method achieved accuracies of 99.39 % and 97.17 % in intra- and inter-patient experiments, respectively. In addition, this method performed well on noisy data and extremely imbalanced data, in which abnormal heatbeats are much less than normal heartbeats. Our proposed method has the potential to be used as a diagnostic tool in the clinic.

Muscle fiber characteristics and expression level of Troponin T3, Toll-like receptor 2, and Toll-like receptor 4 genes in chicken meat with white striping

Background and Aim

The poultry industry faces an emerging muscular defect in chicken meat called white striping (WS). The biological processes associated with WS myopathy are immune system activation, angiogenesis, hypoxia, cell death, and striated muscle contraction. We examined the Troponin T3 (TNNT3), Toll-like receptor 2 (TLR2), and Toll-like receptor 4 (TLR4) genes based on their functions related to muscle contraction and the innate immune system. This study aimed to determine the muscle fiber characteristics (MFCs) and expression level of TNNT3, TLR2, and TLR4 genes in white striping chicken meat (WSCM).

Materials and Methods

A total of 428 breast samples were randomly collected from a commercial poultry processing plant. The samples were classified into four levels: 0 (normal), 1 (moderate WS), 2 (severe WS), and 3 (extreme WS). Five samples per group were selected to evaluate MFCs, including total number of muscle fibers, muscle fiber diameter, cross-sectional area, endomysium thickness, and perimysium thickness. Five samples per group were selected for ribonucleic acid (RNA) isolation to evaluate the messenger RNA (mRNA) expression levels of TNNT3, TLR2, and TLR4 genes related to WS.

Results

Statistical analysis revealed that the total number of fibers, endomysium thickness, and perimysium thickness significantly differed between groups (p < 0.05). Muscle fiber diameter and cross-sectional area did not significantly differ (p > 0.05). The expression of the TNNT3 gene did not significantly differ among groups (p > 0.05). Toll-like receptor 2 and TLR4 mRNA expression significantly differed among groups (p < 0.05).

Conclusion

These detailed MFCs will provide baseline information to observe WS in chicken meat. Toll-like receptor 2 and TLR4 genes may play a role in the occurrence of WS in chicken meat through non-specific immune reactions.

Artificial intelligence-enabled electrocardiogram to distinguish cavotricuspid isthmus dependence from other atrial tachycardia mechanisms. EUROPEAN HEART JOURNAL. DIGITAL HEALTH 2022;3:405-414. [PMID: 36712163 PMCID: PMC9708023 DOI: 10.1093/ehjdh/ztac042]

Aims

Accurately determining atrial arrhythmia mechanisms from a 12-lead electrocardiogram (ECG) can be challenging. Given the high success rate of cavotricuspid isthmus (CTI) ablation, identification of CTI-dependent typical atrial flutter (AFL) is important for treatment decisions and procedure planning. We sought to train a convolutional neural network (CNN) to classify CTI-dependent AFL vs. non-CTI dependent atrial tachycardia (AT), using data from the invasive electrophysiology (EP) study as the gold standard.

Methods and results

We trained a CNN on data from 231 patients undergoing EP studies for atrial tachyarrhythmia. A total of 13 500 five-second 12-lead ECG segments were used for training. Each case was labelled CTI-dependent AFL or non-CTI-dependent AT based on the findings of the EP study. The model performance was evaluated against a test set of 57 patients. A survey of electrophysiologists in Europe was undertaken on the same 57 ECGs. The model had an accuracy of 86% (95% CI 0.77-0.95) compared to median expert electrophysiologist accuracy of 79% (range 70-84%). In the two thirds of test set cases (38/57) where both the model and electrophysiologist consensus were in agreement, the prediction accuracy was 100%. Saliency mapping demonstrated atrial activation was the most important segment of the ECG for determining model output.

Conclusion

We describe the first CNN trained to differentiate CTI-dependent AFL from other AT using the ECG. Our model matched and complemented expert electrophysiologist performance. Automated artificial intelligence-enhanced ECG analysis could help guide treatment decisions and plan ablation procedures for patients with organized atrial arrhythmias.