Key result
An end-to-end deep learning approach reconstructed the ECG QRS complex from PPG signals with a 3.67% R peak failure rate and high correlation of pulse transit time (ρ = 0.844).
Why the study?
Translating PPG into the ECG QRS complex could enable continuous monitoring, but directly decoding it is difficult due to signal offsets from different devices and personal differences.
Can a deep learning-based approach accurately reconstruct the QRS complex of an ECG solely from a PPG signal?
Can a deep learning-based approach accurately reconstruct the QRS complex of an ECG solely from a PPG signal?
Effect estimate: ρ = 0.844
A novel deep learning architecture can accurately reconstruct the ECG QRS complex from PPG signals, potentially enabling low-cost continuous cardiac monitoring.
Technology that translates photoplethysmogram (PPG) into the QRS complex of electrocardiogram (ECG) would be transformative for people who require continuously monitoring. However, directly decoding the QRS complex of ECG from PPG is challenging because PPG signals usually have different offsets due to 1) different devices, and 2) personal differences, which makes the alignment difficult. In this paper, we make the first attempt to reconstruct the QRS complex of ECG only from the recording of PPG by an end-to-end deep learning-based approach. Specifically, we propose a novel encoder-decoder architecture containing three components: 1) a sequence transformer network which automatically calibrates the offset, 2) an attention network, which dynamically identifies regions of interest, and 3) a new QRS complex-enhanced loss for better reconstruction. The experiment results on a real dataset demonstrate the effectiveness of the proposed method: 3.67% R peak failure rate of the reconstructed ECG and high correlation of pulse transit time between the reconstructed QRS complex and the groundtruth QRS complex (ρ = 0.844), which creates a new opportunity for low-cost clinical studies via the waveform-level reconstruction of the QRS complex of ECG from PPG.
No takes yet. Share an insight, caveat, or question.
Chiu et al. (2020) studied Continuous monitoring. Transformed Attentional Neural Networks vs. Groundtruth QRS complex was evaluated on R peak failure rate and correlation of pulse transit time (ρ = 0.844). An end-to-end deep learning approach reconstructed the ECG QRS complex from PPG signals with a 3.67% R peak failure rate and high correlation of pulse transit time (ρ = 0.844).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: