AUTHOR=Bikia Vasiliki , Lazaroska Marija , Scherrer Ma Deborah , Zhao Méline , Rovas Georgios , Pagoulatou Stamatia , Stergiopulos Nikolaos 

TITLE=Estimation of Left Ventricular End-Systolic Elastance From Brachial Pressure Waveform via Deep Learning

JOURNAL=Frontiers in Bioengineering and Biotechnology

VOLUME=Volume 9 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/bioengineering-and-biotechnology/articles/10.3389/fbioe.2021.754003

DOI=10.3389/fbioe.2021.754003

ISSN=2296-4185

ABSTRACT=Determination of left ventricular (LV) end-systolic elastance (E$_{es}$) is of utmost importance for assessing the cardiac systolic function and hemodynamical state \textcolor{blue}{in humans}. Yet, the clinical use of E$_{es}$ is not established due to \textcolor{blue}{the invasive nature and high costs of the existing measuring techniques}. The objective of this study is to introduce a method to assess cardiac contractility, using as a sole measurement an arterial blood pressure (BP) waveform. \textcolor{blue}{Particularly}, we aim to provide evidence on the potential in using the morphology of the brachial BP waveform and its time derivative for predicting LV E$_{es}$ via convolution neural networks (CNNs). The requirement of a \textcolor{blue}{broad} training dataset is addressed by the use of \textcolor{blue}{an in silico dataset (n = 3,748) which is generated by a validated one-dimensional mathematical model of the cardiovasculature}. We evaluated two CNN configurations: (i) a one-channel CNN (CNN$_{1}$) with only the raw brachial BP signal as an input, and (ii) a two-channel CNN (CNN$_{2}$) using as inputs both the brachial BP wave and its time derivative. Accurate predictions were yielded using both CNN configurations. For CNN$_{1}$, Pearson’s correlation coefficient (r) and RMSE were equal to 0.86 and 0.27 mmHg/mL, respectively. The performance was found to be greatly improved for CNN$_{2}$ (r = 0.97 and RMSE = 0.13 mmHg/mL). Moreover, all absolute errors \textcolor{blue}{from CNN$_{2}$} were found to be \textcolor{blue}{less than} 0.5 mmHg/mL. Importantly, the brachial BP wave appeared to be a promising source of information for estimating E$_{es}$. Predictions were found to be in good agreement with the reference E$_{es}$ values over an extensive range of LV contractility values and loading conditions. \textcolor{blue}{Therefore,} the proposed methodology could be easily transferred to the bedside and potentially facilitate the clinical use of E$_{es}$ for monitoring the contractile state of the heart in the real-life setting.