University of Brescia (Coppola et al.)
Self-supervised foundation model for 12-lead ECGs, pretrained on 9.1 million recordings covering 164 cardiovascular conditions across adult and pediatric cohorts, including single-lead settings. Uses a HuBERT-style Transformer encoder and can be fine-tuned with a simple output layer for diagnosis and event-prediction tasks. Released in small, base, and large (~183M parameter) configurations by researchers at the University of Brescia.
Architecture
Transformer
HuBERT-style self-supervised transformer encoder (small/base/large configurations)
Framework
PyTorch
Added to catalog
2026-07-10
CC BY-NC 4.0
License for model weights only. Associated code may be licensed seperately, check code source for specific terms.
800,035 12-lead ECG-report pairs from 161,352 subjects at Beth Israel Deaconess Medical Center.
Multi-Country 12-lead ECG Pretraining Corpus (HuBERT-ECG)
9.1 million ECG recordings across multiple countries, incl. MIMIC-IV-ECG; unique patient count not stated
Overall diagnostic classification (avg., Large)