A machine learning approach using spectrogram representations of peripheral pulse wave signals achieved an R2 ≥ 0.90 for estimating carotid-to-femoral pulse wave velocity.
Does a spectrogram-based machine learning approach using peripheral pulse wave signals accurately estimate carotid-to-femoral pulse wave velocity in an in silico model?
A novel machine learning approach using spectrograms of peripheral pulse wave signals accurately estimates carotid-to-femoral pulse wave velocity in an in silico model, offering a potential non-invasive tool for assessing arterial stiffness.
Carotid-to-femoral pulse wave velocity (cf-PWV) is considered a critical index to evaluate arterial stiffness. For this reason, estimating Carotid-to-femoral pulse wave velocity (cf-PWV) is essential for diagnosing and analyzing different cardiovascular diseases. Despite its broader adoption in the clinical routine, the measurement process of carotid-to-femoral pulse wave velocity is considered a demanding task for clinicians and patients making it prone to inaccuracies and errors in the estimation. A smart non-invasive, and peripheral measurement of carotid-to-femoral pulse wave velocity could overcome the challenges of the classical assessment process and improve the quality of patient care. This paper proposes a novel methodology for the carotid-to-femoral pulse wave velocity estimation based on the use of the spectrogram representation from single non-invasive peripheral pulse wave signals photoplethysmography (PPG) or blood pressure (BP). This methodology was tested using three feature extraction methods based on the semi-classical signal analysis (SCSA) method, the Law’s mask for texture energy extraction, and the central statistical moments. Finally, each feature method was fed into different machine learning models for the carotid-to-femoral pulse wave velocity estimation. The proposed methodology obtained an R 2 0. 90 for all the peripheral signals for the noise-free case using the MLP model, and for the different noise levels added to the original signal, the SCSA-based features with the MLP model presented an R 2 0. 91 for all the peripheral signals at the level of noise. These results provide evidence of the capacity of spectrogram representation for efficiently assessing the carotid-to-femoral pulse wave velocity estimation using different feature methods. Future work will be done toward testing the proposed methodology for in-vivo signals.
Vargas et al. (Fri,) conducted a other in Healthy (virtual subjects) (n=4,374). Spectrogram representation of peripheral pulse wave signals with machine learning was evaluated on Carotid-to-femoral pulse wave velocity (cf-PWV) estimation accuracy (R2). A machine learning approach using spectrogram representations of peripheral pulse wave signals achieved an R2 ≥ 0.90 for estimating carotid-to-femoral pulse wave velocity.