Key result
W-Net model reconstructs arterial blood pressure from PPG with ~0.995 correlation to invasive signals.
Why the study?
Existing methods for reconstructing ABP waveforms from PPG focus on systolic, diastolic, and mean arterial pressure similarities without evaluating global similarity.
Does a W-Net deep learning model accurately reconstruct arterial blood pressure waveforms from photoplethysmogram signals?
Does a W-Net deep learning model accurately reconstruct arterial blood pressure waveforms from photoplethysmogram signals?
Effect estimate: Pearson correlation 0.995
A W-Net deep learning architecture can accurately reconstruct continuous arterial blood pressure waveforms from non-invasive photoplethysmogram signals, offering a potential non-invasive continuous monitoring method.
May enable non-invasive continuous ABP monitoring; leaves open prospective clinical validation before adoption.
The continuous prediction of arterial blood pressure (ABP) waveforms via non-invasive methods is of great significance for the prevention and treatment of cardiovascular disease. Photoplethysmography (PPG) can be used to reconstruct ABP signals due to having the same excitation source and high signal similarity. The existing methods of reconstructing ABP signals from PPG only focus on the similarities between systolic, diastolic, and mean arterial pressures without evaluating their global similarity. This paper proposes a deep learning model with a W-Net architecture to reconstruct ABP signals from PPG. The W-Net consists of two concatenated U-Net architectures, the first acting as an encoder and the second as a decoder to reconstruct ABP from PPG. Five hundred records of different lengths were used for training and testing. The experimental results yielded high values for the similarity measures between the reconstructed ABP signals and their reference ABP signals: the Pearson correlation, root mean square error, and normalized dynamic time warping distance were 0.995, 2.236 mmHg, and 0.612 mmHg on average, respectively. The mean absolute errors of the SBP and DBP were 2.602 mmHg and 1.450 mmHg on average, respectively. Therefore, the model can reconstruct ABP signals that are highly similar to the reference ABP signals.
No takes yet. Share an insight, caveat, or question.
Tang et al. (2022) studied this question. W-Net deep learning model vs. Reference arterial blood pressure signals was evaluated on Pearson correlation between reconstructed and reference ABP signals (Pearson correlation 0.995). The W-Net deep learning model reconstructed arterial blood pressure signals from photoplethysmograms with high similarity to reference signals, achieving an average Pearson correlation of 0.995.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: