Artificial Intelligence-based Method for Carotid-to-Femoral Pulse Wave Velocity Estimation from Photoplethysmogram Signal

Abstract

Cardiovascular diseases (CVDs) are the primary cause of death in the world. The development of easy-to-use and non-invasive monitoring and predicting CVDs' diagnosis methods is crucial. Among the key parameters in the cardiovascular system is the 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. In this work, we propose an artificial intelligence-based method for the prediction of (PWV) non-invasively using distal photoplethysmogram PPG waveforms. Functionally, PPG offers a simple, reliable, low-cost technique to measure blood volume change and hence assess the cardiovascular function. Here, we identify features from the timings of fiducial points that are extracted from the PPG, its first, second, and third derivative waveforms. The results based on virtual data-set show an acceptable estimation of the arterial stiffness index, carotid-to-femoral pulse wave velocity with mean absolute percentage error less than 2.5%.