Synthesizing ECG from BCG: a Physiological Semantics Enhanced Multiband Diffusion Generative Approach.

The ballistocardiogram (BCG) is an unobtrusive measurement that shows promise for long-term, home-based cardiovascular monitoring and early disease screening. However, the lack of standardized clinical interpretations for BCG waveforms, compared to electrocardiogram (ECG) signals, limits its direct application in diagnostic decision-making. Although the ECG synthesis from BCG provides a viable solution, the significant differences in semantic density and spectral distribution between the two types of signals pose challenges to this process. Here, we propose physiological semantics-enhanced multiband diffusion (PSEM-Diff), a novel method using physiological semantics alignment and a diffusion model to achieve precise translation from BCG to ECG signals. The PSEM-Diff model integrates the prior knowledge of ECG physiological semantics (including the temporal characteristics of P-QRS-T waveform sequences and the correlation between J waves and R waves) into the BCG pre-encoding through the attention distillation and adopts the decoupled multiband diffusion to preserve the precise waveform details across different bands of ECG. We validated the proposed PSEM-Diff using datasets that included healthy individuals and patients with several cardiovascular diseases. The experimental results show that the synthesized ECG has a higher fidelity to the ground truth than other state-of-the-art methods. Further, detection for atrial fibrillation (AFib) and other arrhythmias indicates a diagnostic consistency with the ground-truth ECG, demonstrating the potential of PSEM-Diff for cardiovascular monitoring and telemedicine applications.