EXGnet achieved average five-fold accuracies of 98.76% and 96.93%, and F1-scores of 97.91% and 95.53% on Chapman and Ningbo ECG arrhythmia datasets, with explainable AI guidance enhancing trustworthin
Does the EXGnet explainable AI framework provide accurate and interpretable single-lead ECG arrhythmia classification?
EXGnet provides a highly accurate and interpretable deep learning framework for single-lead ECG arrhythmia detection, suitable for deployment on resource-constrained edge devices.
Absolute Event Rate: 0% vs 0%
Deep learning has significantly propelled the performance of Electrocardiogram (ECG) arrhythmia classification, yet its clinical adoption remains hindered by challenges in interpretability and deployment on resource-constrained edge devices. To bridge this gap, we propose EXGnet, an innovative and reliable ECG arrhythmia classification network tailored for single-lead signals, specifically designed to balance high accuracy, explainability, and edge compatibility. EXGnet integrates explainable artificial intelligence (XAI) supervision during training via a normalized cross-correlation based loss, directing the model’s attention to clinically relevant ECG regions, similar to a cardiologist’s focus. This supervision is driven by automatically generated ground truth, derived through an innovative heart rate variability-based approach, without the need for manual annotation. To enhance classification accuracy without compromising deployment simplicity, we incorporate quantitative ECG features during training. These enrich the model with multi-domain knowledge but are excluded during inference, keeping the model lightweight for edge deployment. Additionally, we introduce an innovative multiresolution block to efficiently capture both short- and long-term signal features while maintaining computational efficiency. Rigorous evaluation on the Chapman and Ningbo benchmark datasets validates the supremacy of EXGnet, which achieves average five-fold accuracies of 98.762% and 96.932%, and F1-scores of 97.910% and 95.527%, respectively. Comprehensive ablation studies and both quantitative and qualitative interpretability assessment confirm that the XAI guidance is pivotal, demonstrably enhancing the model’s focus and trustworthiness. Overall, EXGnet sets a new benchmark by combining high-performance arrhythmia classification with interpretability, paving the way for more trustworthy and accessible portable ECG based health monitoring systems. • Integrate interpretability into ECG classification through supervised training with attention-based loss. • Automate relevance region identification using heart rate variability without manual annotations. • Incorporate diagnostic features during training to enrich the learning without affecting deployment. • Capture essential heart signal patterns across time with multiresolution signal processing. • Deliver consistent, interpretable classification results validated on clinical benchmark datasets.
Showrav et al. (Sun,) reported a other. EXGnet achieved average five-fold accuracies of 98.76% and 96.93%, and F1-scores of 97.91% and 95.53% on Chapman and Ningbo ECG arrhythmia datasets, with explainable AI guidance enhancing trustworthin.