A Reliable Deep Learning Model for ECG Interpretation: Mitigating Overconfidence and Direct Uncertainty Quantification
Symmetry · 20.05.2025 · 17 (5) · 794
DOI: 10.3390/sym17050794 ↗Kurz gefasst
Fachartikel in der Zeitschrift Symmetry, online erschienen am 20.05.2025. Verfasst von Xuedong Li und 5 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Scientific Research Fund of Chengdu University of Information Technology, Research Project of Key R&D Programs in Tibet Autonomous Region, National Key Research and Development Plan of China, Key Project of Cyberspace Security Governance.
Abstract (Originalsprache)
Electrocardiogram (ECG) interpretation using deep learning models holds immense potential for improving cardiac diagnosis. However, existing models often suffer from overconfident predictions and lack the capability to directly quantify uncertainty, leading to unreliable clinical guidance. To address this challenge, we propose a model for uncertainty-aware ECG interpretation. The model employs a deep convolutional architecture with max-pooling residual modules to capture both local and global spatiotemporal features from raw ECG signals. The architectural design respects the symmetry inherent in ECG waveforms—such as periodicity and morphological consistency across cardiac cycles—enabling the network to extract clinically relevant features more effectively. Then, unlike conventional models that rely on softmax-based probability outputs, our approach parameterizes class distributions using the Dirichlet distribution, while Subjective Logic translates these parameters into interpretable belief masses and uncertainty scores. We evaluate the model on the PhysioNet Challenge 2017 dataset, our model achieves an accuracy of 86.12%, an F1 score of 83.14%, a Precision-Recall Area Under the Curve (PR-AUC) of 85.25%, and a Receiver Operating Characteristic Area Under the Curve (ROC-AUC) of 92.87%—outperforming baseline models in three out of four metrics. Critically, the model reduces overconfidence to 0.59% (compared to 12–22% in softmax-based baselines), aligning prediction confidence with true accuracy. By progressively increasing the uncertainty threshold u, the model dynamically filters low-confidence predictions, leading to consistently improved performance—reaching up to 93.59% accuracy, 93.22% F1 score, 89.17% PR-AUC, and 95.10% ROC-AUC at u = 0.1. These results validate the model’s capacity for reliable ECG interpretation while leveraging physiological signal symmetry for enhanced feature extraction.
Förderung
- Scientific Research Fund of Chengdu University of Information Technology
- Research Project of Key R&D Programs in Tibet Autonomous Region
- National Key Research and Development Plan of China, Key Project of Cyberspace Security Governance
- Key Research and Development Project of Chengdu
- Key Research and Development Support Program Project of Chengdu
Zitieren
APA
Li, X., Zheng, Q., Zhang, S., Fu, S., Chen, Y., & Ye, K. (2025). A Reliable Deep Learning Model for ECG Interpretation: Mitigating Overconfidence and Direct Uncertainty Quantification. Symmetry, 17(5), 794. https://doi.org/10.3390/sym17050794
Vancouver
Li X, Zheng Q, Zhang S, Fu S, Chen Y, Ye K. A Reliable Deep Learning Model for ECG Interpretation: Mitigating Overconfidence and Direct Uncertainty Quantification. Symmetry. 2025;17(5):794. doi:10.3390/sym17050794
BibTeX
@article{Li2025,
author = {Li, Xuedong and Zheng, Qingxiao and Zhang, Shibin and Fu, Shipeng and Chen, Yingke and Ye, Ke},
title = {A Reliable Deep Learning Model for ECG Interpretation: Mitigating Overconfidence and Direct Uncertainty Quantification},
journal = {Symmetry},
year = {2025},
volume = {17},
number = {5},
pages = {794},
doi = {10.3390/sym17050794}
}
EUVIMED