Key result
ECGMatch outperforms state-of-the-art models in multi-label cardiovascular disease prediction using only 1% labeled data.
Why the study?
Label scarcity, co-occurrence of multiple cardiovascular diseases, and poor performance on unseen datasets hinder deep learning-based ECG diagnostic models, leaving a unified framework an open challenge.
The proposed ECGMatch model provides a robust semi-supervised framework for multi-label cardiovascular disease prediction from ECGs, addressing label scarcity and unseen dataset challenges.
Answers are grounded in this paper and cite their sources.
May enhance ECG-based multi-label CVD prediction with scarce labels; leaves open prospective clinical validation before adoption.
Electrocardiography (ECG) is a non-invasive tool for predicting cardiovascular diseases (CVDs). Current ECG-based diagnosis systems show promising performance owing to the rapid development of deep learning techniques. However, the label scarcity problem, the co-occurrence of multiple CVDs and the poor performance on unseen datasets greatly hinder the widespread application of deep learning-based models. Addressing them in a unified framework remains a significant challenge. To this end, we propose a multi-label semi-supervised model (ECGMatch) to recognize multiple CVDs simultaneously with limited supervision. In the ECGMatch, an ECGAugment module is developed for weak and strong ECG data augmentation, which generates diverse samples for model training. Subsequently, a hyperparameter-efficient framework with neighbor agreement modeling and knowledge distillation is designed for pseudo-label generation and refinement, which mitigates the label scarcity problem. Finally, a label correlation alignment module is proposed to capture the co-occurrence information of different CVDs within labeled samples and propagate this information to unlabeled samples. Extensive experiments on four datasets and three protocols demonstrate the effectiveness and stability of the proposed model, especially on unseen datasets. As such, this model can pave the way for diagnostic systems that achieve robust performance on multi-label CVDs prediction with limited supervision.
No takes yet. Share an insight, caveat, or question.
Zhou et al. (2023) studied Cardiovascular diseases (n=83,601). ECGMatch (semi-supervised learning framework) vs. State-of-the-art semi-supervised learning models was evaluated on Multi-label classification performance (e.g., Hamming loss, MAP). The proposed ECGMatch framework outperformed state-of-the-art semi-supervised learning models in multi-label cardiovascular disease prediction across multiple datasets, particularly in cross-dataset evaluations using only 1% labeled data.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: