Synthesis of Standard 12-Lead ECG from Single-Lead ECG Using Shifted Diffusion Models

As the primary tool for monitoring cardiac health, a standard 12-lead ECG device is specialized medical equipment that is challenging to integrate into daily life. Meanwhile, existing portable ECG monitoring devices can only capture single-lead ECG, which is insufficient for health diagnosis. To address this issue, we propose a novel shifted diffusion model algorithm that utilizes a single-lead ECG to generate a standard 12-lead ECG. Our algorithm uses the detected single-lead ECG as the condition and employs the diffusion model to synthesize corresponding other 11-lead ECG. The extra shift is utilized in the forward process so that the model can learn better. Our approach has been tested on three datasets, yielding promising results.