What does this research mean for the field?

An end-to-end deep learning approach can accurately reconstruct the ECG QRS complex solely from PPG signals, achieving a 3.67% R peak failure rate and a high correlation of pulse transit time. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.ESTABLISHES_NEW_DIRECTION.

June 5, 2020

Reconstructing QRS Complex From PPG by Transformed Attentional Neural Networks

Q: What is the clinical evidence from this study?

Study design: Other. Population: Continuous monitoring. Intervention: Transformed Attentional Neural Networks vs. Groundtruth QRS complex. Primary outcome: R peak failure rate and correlation of pulse transit time (ρ = 0.844).

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).

Structured PICO

Can a deep learning-based approach accurately reconstruct the QRS complex of an ECG solely from a PPG signal?

Population

Real dataset of photoplethysmogram (PPG) and electrocardiogram (ECG) recordings (specific patient characteristics and sample size not detailed in abstract)

Intervention

End-to-end deep learning-based approach (encoder-decoder architecture with sequence transformer network, attention network, and QRS complex-enhanced loss) to reconstruct QRS complex from PPG

Comparator

Groundtruth QRS complex from actual ECG recordings

Outcome

R peak failure rate of the reconstructed ECG and correlation of pulse transit time between reconstructed and groundtruth QRS complexsurrogate

A novel deep learning architecture can accurately reconstruct the ECG QRS complex from PPG signals, potentially enabling low-cost continuous cardiac monitoring.

Main Result

Effect estimate: ρ = 0.844

Abstract

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.

Bookmark

Cite This Study

Chiu et al. (Fri,) conducted a other in 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).

synapsesocial.com/papers/6a1a1f3d05af093a17f705a2 https://doi.org/https://doi.org/10.1109/jsen.2020.3000344

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: