A multilayer perceptron model estimated carotid-to-femoral pulse wave velocity from distal PPG waveforms with high accuracy, achieving an R2 of ~0.98 and MAPE <1.71% at the radial artery level.
A multilayer perceptron-based model can accurately estimate carotid-to-femoral pulse wave velocity from distal PPG waveforms in an in-silico setting, offering a potential non-invasive method to assess arterial stiffness.
Cardiovascular diseases (CVDs) are the primary cause of death in the world. The development of easy-to-use and non-invasive monitoring CVDs’ diagnosis methods is crucial. Among the key parameters in the cardiovascular system is arterial stiffness. An increase in arterial stiffness is considered a primary risk factor for CVDs. Although arterial stiffness can be assessed non-invasively by measuring the carotid-to-femoral pulse wave velocity (cf−PWV), which is considered as a gold standard for arterial stiffness measurement, the clinical process of assessing this parameter is very intrusive and complicated. This paper investigated the potential of estimating (cf−PWV) from distal photoplethysmogram (PPG) waveforms using regression technique based on a multilayer perceptron. Functionally, PPG offers a simple, reliable, low-cost technique to measure blood volume change and hence assess cardiovascular function. In this work, we identify and select features from the timing fiducial points-based PPG, its first, second, and third derivative waveforms. The in-silico validation shows promising results and satisfactory accuracy. It demonstrates good estimation performances with an R 2 (correlation coefficient) around 0.95 and MAPE (mean absolute percentage error) less than 2.22% based on features extracted from PPG at the brachial artery level, an R 2 around 0.98 and MAPE less than 1.71% based on features extracted from PPG at the radial artery level and R 2 around 0.97 and MAPE less than 1.88% based on features extracted from PPG at the digital artery level.
Bahloul et al. (Tue,) conducted a other in Arterial stiffness. Multilayer perceptron-based cf-PWV estimation using PPG signal was evaluated on Estimation accuracy of carotid-to-femoral pulse wave velocity (R2 and MAPE). A multilayer perceptron model estimated carotid-to-femoral pulse wave velocity from distal PPG waveforms with high accuracy, achieving an R2 of ~0.98 and MAPE <1.71% at the radial artery level.