On the assessment of arterial compliance from carotid pressure waveform.

In a progressively aging population, it is of utmost importance to develop reliable, noninvasive, and cost-effective tools to estimate biomarkers that can be indicative of cardiovascular risk. Various pathophysiological conditions are associated to changes in the total arterial compliance (CT), and thus, its estimation via an accurate and simple method is valuable. Direct noninvasive measurement of CT is not feasible in the clinical practice. Previous methods exist for indirect estimation of CT, which, however, require noninvasive, yet complex and expensive, recordings of the central pressure and flow. Here, we introduce a novel, noninvasive method for estimating CT from a single carotid waveform measurement using regression analysis. Features were extracted from the carotid wave and were combined with demographic data. A prediction pipeline was adopted for estimating CT using, first, a feature-based regression analysis and, second, the raw carotid pulse wave. The proposed methodology was appraised using the large human cohort (N = 2,256) of the Asklepios study. Accurate estimates of CT were yielded for both prediction schemes, namely, r = 0.83 and normalized root mean square error (nRMSE) = 9.58% for the feature-based model, and r = 0.83 and nRSME = 9.67% for the model that used the raw signal. The major advantage of this method pertains to the simplification of the technique offering easily applicable and convenient CT monitoring. Such an approach could offer promising applications, ranging from fast and cost-efficient hemodynamical monitoring by the physician to integration in wearable technologies.NEW & NOTEWORTHY This article introduces a novel artificial intelligence method to estimate total arterial compliance (CT) via exploiting the information provided by an uncalibrated carotid blood pressure waveform as well as typical clinical variables. The major finding of this study is that CT, which is usually acquired using both pressure and flow waveforms, can be accurately derived by the use of the pressure wave alone. This method could potentially facilitate easily applicable and convenient monitoring of CT.