Wang, X., Gao, H., Ma, C., Zhu, T., Yang, F., Liu, C., Fu, H. (2025). Uncertainty-Inspired Multi-Task Learning in Arbitrary Scenarios of ECG Monitoring. IEEE Journal of Biomedical and Health Informatics, 1–14. https://doi.org/10.1109/jbhi.2025.3545927
Abstract:
As the scenarios for electrocardiogram (ECG) monitoring become increasingly diverse, particularly with the development of wearable ECG, the influence of ambiguous factors in diagnosis has been amplified. Reliable ECG information must be extracted from abundant noises and confusing artifacts.
To address this issue, we suggest an uncertainty-inspired model for beat-level diagnosis (UI-Beat). The base architecture of UI-Beat separates heartbeat localization and event diagnosis in two branches to address the problem of heterogeneous data sources. The beat-level identification is optimized while cross-source learning and information interaction between heartbeat localization and event detection. To disentangle the epistemic and aleatoric uncertainty within one stage in a deterministic neural network, we propose a new method derived from uncertainty formulation, and realize it by introducing the class-biased transformation. Then the disentangled uncertainty can be utilized to screen out noise and identify ambiguous heartbeat synchronously. Above all, an uncertainty-based cross-lead fusion strategy for arbitrary ECG is designed.
The results indicate that UI-Beat can significantly improve the performance of noise (non-ECG episodes and QRS-like artifacts) detection. For multi-lead ECG analysis, UI-Beat is approaching the performance upper bound in heartbeat localization, and achieving a significant performance improvement in heartbeat classification through uncertainty-based cross-lead fusion compared to single-lead prediction and other state-of-the-art methods.
Considering the characteristic of one-stage ECG analysis within one model, it is suggested that the proposed UI-Beat has the potential to be employed as a general model for arbitrary scenarios of ECG monitoring, with the capacity to remove invalid episodes, and realize heartbeat-level diagnosis with confidence provided.
License type:
Publisher Copyright
Funding Info:
This work was supported by the National Natural Science Foundation of China (62171123 and 62211530112), the National Key Research and Development Program of China (2023YFC3603600).