Determination of Aortic Characteristic Impedance and Total Arterial Compliance From Regional Pulse Wave Velocities Using Machine Learning: An in-silico Study.

Vasiliki Bikia,Georgios Rovas,Nikolaos Stergiopulos,Stamatia Pagoulatou

doi:10.3389/fbioe.2021.649866

Abstract

In-vivo assessment of aortic characteristic impedance (Zao) and total arterial compliance (CT) has been hampered by the need for either invasive or inconvenient and expensive methods to access simultaneous recordings of aortic pressure and flow, wall thickness, and cross-sectional area. In contrast, regional pulse wave velocity (PWV) measurements are non-invasive and clinically available. In this study, we present a non-invasive method for estimating Zao and CT using cuff pressure, carotid-femoral PWV (cfPWV), and carotid-radial PWV (crPWV). Regression analysis is employed for both Zao and CT. The regressors are trained and tested using a pool of virtual subjects (n = 3,818) generated from a previously validated in-silico model. Predictions achieved an accuracy of 7.40%, r = 0.90, and 6.26%, r = 0.95, for Zao, and CT, respectively. The proposed approach constitutes a step forward to non-invasive screening of elastic vascular properties in humans by exploiting easily obtained measurements. This study could introduce a valuable tool for assessing arterial stiffness reducing the cost and the complexity of the required measuring techniques. Further clinical studies are required to validate the method in-vivo.

Highlights

Aging and vascular pathologies lead to changes in the elastic properties and the hemodynamics of the arterial network (Laurent et al, 2001; Mitchell et al, 2010; Vlachopoulos et al, 2010; Redheuil et al, 2011)
The impedance computed in the ascending aorta is defined as input impedance (Zin), and is a machine learning (ML)-Assessment of Arterial Elasticity global systemic parameter, which encompasses all effects of wave travel and reflections of the arterial part which is distal to the point of measurement
We demonstrated that the combination of in-silico data with ML modeling allows for validating a methodology for predicting aortic hemodynamics and cardiac contractility (Bikia et al, 2020b)

Summary

Introduction

Aging and vascular pathologies lead to changes in the elastic properties and the hemodynamics of the arterial network (Laurent et al, 2001; Mitchell et al, 2010; Vlachopoulos et al, 2010; Redheuil et al, 2011). These changes have been shown to be highly associated with increased cardiovascular risk or mortality (Mitchell et al, 2010; Vlachopoulos et al, 2010). All of the above frequency and time domain methods require pressure and flow in the aorta, which can be obtained only invasively (pressure) or are not easy in clinical practice (flow)

Methods

Results

Discussion

Conclusion