UniECG: Understanding and Generating ECG in One Unified Model
This addresses the need for accurate ECG analysis and generation in medical applications, representing a domain-specific advancement.
The paper tackles the problem of unified models failing to correctly understand and generate ECG signals for medical diagnosis, proposing UniECG as the first unified model that concurrently performs evidence-based ECG interpretation and text-conditioned ECG generation, achieving autonomous task selection based on user input.
Recent unified models such as GPT-5 have achieved encouraging progress on vision-language tasks. However, these unified models typically fail to correctly understand ECG signals and provide accurate medical diagnoses, nor can they correctly generate ECG signals. To address these limitations, we propose UniECG, the first unified model for ECG capable of concurrently performing evidence-based ECG interpretation and text-conditioned ECG generation tasks. Through a decoupled two-stage training approach, the model first learns evidence-based interpretation skills (ECG-to-Text), and then injects ECG generation capabilities (Text-to-ECG) via latent space alignment. UniECG can autonomously choose to interpret or generate an ECG based on user input, significantly extending the capability boundaries of current ECG models. Our code and checkpoints will be made publicly available at https://github.com/PKUDigitalHealth/UniECG upon acceptance.