ECGBERT: Understanding Hidden Language of ECGs with Self-Supervised Representation Learning
This addresses the challenge of limited labeled medical data for ECG analysis, though it is incremental by adapting NLP methods to a new domain.
The paper tackles the problem of ECG signal analysis requiring large labeled datasets by introducing ECGBERT, a self-supervised representation learning approach that achieves state-of-the-art results on tasks like atrial fibrillation detection and heartbeat classification.
In the medical field, current ECG signal analysis approaches rely on supervised deep neural networks trained for specific tasks that require substantial amounts of labeled data. However, our paper introduces ECGBERT, a self-supervised representation learning approach that unlocks the underlying language of ECGs. By unsupervised pre-training of the model, we mitigate challenges posed by the lack of well-labeled and curated medical data. ECGBERT, inspired by advances in the area of natural language processing and large language models, can be fine-tuned with minimal additional layers for various ECG-based problems. Through four tasks, including Atrial Fibrillation arrhythmia detection, heartbeat classification, sleep apnea detection, and user authentication, we demonstrate ECGBERT's potential to achieve state-of-the-art results on a wide variety of tasks.