Lead-agnostic Self-supervised Learning for Local and Global Representations of Electrocardiogram
This work addresses the need for more robust and generalizable ECG analysis models in healthcare, though it appears incremental by building on existing self-supervised learning approaches.
The paper tackled the problem of self-supervised learning for electrocardiogram (ECG) signals by proposing a method that learns both local and global representations and uses random lead masking to handle arbitrary lead sets, resulting in improved performance on downstream tasks like cardiac arrhythmia classification and patient identification.
In recent years, self-supervised learning methods have shown significant improvement for pre-training with unlabeled data and have proven helpful for electrocardiogram signals. However, most previous pre-training methods for electrocardiogram focused on capturing only global contextual representations. This inhibits the models from learning fruitful representation of electrocardiogram, which results in poor performance on downstream tasks. Additionally, they cannot fine-tune the model with an arbitrary set of electrocardiogram leads unless the models were pre-trained on the same set of leads. In this work, we propose an ECG pre-training method that learns both local and global contextual representations for better generalizability and performance on downstream tasks. In addition, we propose random lead masking as an ECG-specific augmentation method to make our proposed model robust to an arbitrary set of leads. Experimental results on two downstream tasks, cardiac arrhythmia classification and patient identification, show that our proposed approach outperforms other state-of-the-art methods.