A Geometric Deep Learning approach to blood pressure regression

Rita Fioresi, Ferdinando Zanchetta, Angelica Simonetti, Andrea Malagoli, Giovanni Faglioni

Keywords: geometric deep learning, graph neural networks

TL;DR: We develop and test a new Geometric Deep Learning (GDL) approach to infer BP data

Abstract:

A correct measurement of the Blood Pressure (BP) is crucial in monitoring the health
status of a patient and in diagnosis of cardiac vascular diseases. In this proof of concept,
we develop and test a new Geometric Deep Learning (GDL) approach to infer BP data from
other biological parameters: the photoplethysmogram and the electrocardiogram (ECG).
Our findings suggest that such a GDL approach shows great promise compared with many
state of the art models that are used in the field.