Building Continuous Arterial Blood Pressure Prediction Models Using Recurrent Networks

Costas Sideris, Haik Kalantarian, Ebrahim Nemati, Majid Sarrafzadeh

2016 · 55 citations · 19 references

Concepts

Abstract

This paper presents a methodology for developing highly-accurate, continuous Arterial Blood Pressure (ABP) models using only Photoplethysmography (PPG). In contrast to prior approaches, we develop a system that exhibits dynamic temporal behavior which leads to increased accuracy in modeling ABP. We validate our approach using data from patients in the intensive care unit (ICU). We show that it is possible to build highly accurate, continuous blood pressure models using only finger pulse oximeters. Our methodology achieves accurate systolic blood pressure estimation with a root mean square error 2.58 ± 1.23 across the patient sample used. Furthermore, the continuous ABP signal is estimated with a root mean square error of 6.042 ± 3.26 and correlation coefficient of 0.95 ± 0.045. Our method enables designing robust Remote Health Monitoring Systems (RMS) for Heart Failure patients without requiring traditional blood pressure monitors.

References

19