Open access
Jul 2026
A unified 12-lead ECG-language model for interpretation and clinical-endpoint prediction
DeepECG-Tok is presented, which reframes ECG interpretation as a unified instruction-following problem and establishes discrete ECG tokenization as a foundation for general-purpose models that generate clinically useful interpretations and answer diverse questions directly from cardiac waveforms.
R. Banerjee, J. Beaulieu, N. Dostie et al.
· medRxiv · 0 citations