Authors:
Giovanna Sannino
1
;
Ivanoe De Falco
2
and
Giuseppe De Pietro
2
Affiliations:
1
ICAR and University of Naples Parthenope, Italy
;
2
ICAR, Italy
Keyword(s):
Blood Pressure, Wearable Sensors, Heart Rate Variability, Plethysmography, Regression, Genetic Programming.
Abstract:
The hypothesis underlying this paper is that a nonlinear relationship exists between Electrocardiography (ECG) and Heart Related Variability (HRV) parameters, plethysmography (PPG), and blood pressure (BP) values. If this hypothesis is true, rather than continuously measuring the patient’s BP, a wearable wireless PPG sensor can be applied to patient’s finger, an ECG sensor to his/her chest, HRV parameter values can be computed and, through regression, both systolic and diastolic BP values can be indirectly measured. Genetic Programming (GP) automatically both evolves the structure of the mathematical model and finds the most important parameters in it. Therefore, it is perfectly suited to perform regression task. As far as it can be found in the scientific literature of this field, until now nobody has ever investigated the use of GP to relate parameters derived from HRV analysis and PPG to BP values. Therefore, in this paper we have carried out preliminary experiments on the use of
GP in facing this regression task. GP has been able to find a mathematical model expressing a nonlinear relationship between heart activity, and thus ECG and HRV parameters, PPG and BP values. The approximation error involved by the use of this method is lower than 2 mmHg for both systolic and diastolic BP values.
(More)