ECG foundation models benefit from contrastive learning and state space architectures

Researchers have conducted a systematic study on pretraining strategies and scaling for electrocardiography (ECG) foundation models. They evaluated five different self-supervised learning objectives, finding that contrastive predictive coding and JEPA yielded the most transferable representations. The study also demonstrated that increasing pretraining data up to 11 million samples consistently improved performance for most objectives. Furthermore, structured state space models showed superior performance compared to transformers and CNNs, suggesting their inductive biases are key for effective ECG representation learning. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Suggests structured state space models and contrastive learning are key for effective ECG representation learning, potentially guiding future medical AI development.

RANK_REASON The cluster contains an academic paper detailing a systematic study of pretraining strategies and model architectures for ECG foundation models. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• ECG
• contrastive predictive coding
• JEPA
• structured state space models
• transformers
• CNNs

• paper
• model release