Beat-ssl: Capturing Local ECG Morphology through Heartbeat-level Contrastive Learning with Soft Targets
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917218102542336 |
|---|---|
| author | Rizqyawan, Muhammad Ilham Macfarlane, Peter Hadjidemetriou, Stathis Deligianni, Fani |
| author_facet | Rizqyawan, Muhammad Ilham Macfarlane, Peter Hadjidemetriou, Stathis Deligianni, Fani |
| contents | Obtaining labelled ECG data for developing supervised models is challenging. Contrastive learning (CL) has emerged as a promising pretraining approach that enables effective transfer learning with limited labelled data. However, existing CL frameworks either focus solely on global context or fail to exploit ECG-specific characteristics. Furthermore, these methods rely on hard contrastive targets, which may not adequately capture the continuous nature of feature similarity in ECG signals. In this paper, we propose Beat-SSL, a contrastive learning framework that performs dual-context learning through both rhythm-level and heartbeat-level contrasting with soft targets. We evaluated our pretrained model on two downstream tasks: 1) multilabel classification for global rhythm assessment, and 2) ECG segmentation to assess its capacity to learn representations across both contexts. We conducted an ablation study and compared the best configuration with three other methods, including one ECG foundation model. Despite the foundation model's broader pretraining, Beat-SSL reached 93% of its performance in multilabel classification task and surpassed all other methods in the segmentation task by 4%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_16147 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Beat-ssl: Capturing Local ECG Morphology through Heartbeat-level Contrastive Learning with Soft Targets Rizqyawan, Muhammad Ilham Macfarlane, Peter Hadjidemetriou, Stathis Deligianni, Fani Machine Learning Obtaining labelled ECG data for developing supervised models is challenging. Contrastive learning (CL) has emerged as a promising pretraining approach that enables effective transfer learning with limited labelled data. However, existing CL frameworks either focus solely on global context or fail to exploit ECG-specific characteristics. Furthermore, these methods rely on hard contrastive targets, which may not adequately capture the continuous nature of feature similarity in ECG signals. In this paper, we propose Beat-SSL, a contrastive learning framework that performs dual-context learning through both rhythm-level and heartbeat-level contrasting with soft targets. We evaluated our pretrained model on two downstream tasks: 1) multilabel classification for global rhythm assessment, and 2) ECG segmentation to assess its capacity to learn representations across both contexts. We conducted an ablation study and compared the best configuration with three other methods, including one ECG foundation model. Despite the foundation model's broader pretraining, Beat-SSL reached 93% of its performance in multilabel classification task and surpassed all other methods in the segmentation task by 4%. |
| title | Beat-ssl: Capturing Local ECG Morphology through Heartbeat-level Contrastive Learning with Soft Targets |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2601.16147 |