BioFPT improved ECG analysis accuracy by 4.2% and reduced model parameters by 14.8% versus state-of-the-art methods across 94,000 subjects and 7 datasets.
BioFPT is a novel self-supervised learning framework for ECG analysis that improves accuracy and reduces computational complexity compared to existing models, particularly useful when labeled data is limited.
Absolute Event Rate: 0% vs 0%
Electrocardiogram (ECG) analysis represents a promising field for deep learning applications in clinical diagnostics. However, practical use of current methods is still constrained by their heavy reliance on large amounts of labeled data, as well as limitations in processing efficiency and signal quality. To address these challenges, we present BioFPT (Biosignal Feature Pyramid Transformer), a novel self-supervised learning framework designed for ECG signal. The proposed framework incorporates a Split Mask-Join (SMJ) transformation for a Pre-training strategy, complemented by an overlapping embedding mechanism that eliminates positional encoding requirements. The efficiency of the architectural design is enhanced through a Spatial Reduction Attention (SRA) transformer, which achieves a reduction in computational complexity without performance degradation. Comprehensive evaluation of seven public ECG datasets comprising over 94,000 sub jects demonstrates BioFPT's effectiveness, an accuracy improvement of 4.2% and a parameter reduction of 14.8% compared to state-of-the-art models. Furthermore, it maintains robust performance across diverse pathological conditions and signal qualities. The proposed architecture rep resents a significant advancement in self-supervised ECG analysis, particularly suitable for scenarios with limited labeled data availability. Moreover, its versatile architecture shows promise for broader applications across various biosignals.
Meng et al. (Thu,) reported a other. BioFPT improved ECG analysis accuracy by 4.2% and reduced model parameters by 14.8% versus state-of-the-art methods across 94,000 subjects and 7 datasets.