Machine Learning Approaches for PPG-based Blood Pressure Monitoring: Validation against Invasive Arterial Line Measurements

Jorge, João; Proença, Martin; Aguet, Clémentine; Van Zaen, Jérôme; Bonnier, Guillaume; Renevey, Philippe; Lemkaddem, Alia; Schoettker, Patrick; Lemay, Mathieu

Machine Learning Approaches for PPG-based Blood Pressure Monitoring: Validation against Invasive Arterial Line Measurements

Files

2020_Jorge et al_Machine Learning Approaches for PPG-based Blood Pressure Monitoring Validation against Invasive Arterial Line Measurements.pdf (233.25 KB)

Author

Jorge, João

Proença, Martin

Aguet, Clémentine

Van Zaen, Jérôme

Bonnier, Guillaume

Renevey, Philippe

Lemkaddem, Alia

Schoettker, Patrick

Lemay, Mathieu

Full item page

Abstract

Arterial blood pressure is a physiological parameter of major importance to medical applications. CSEM has developed pioneering techniques for blood pressure estimation based on optical signals such as photoplethysmographic pulse wave analysis (known as oBPM®), which enable continuous non-occlusive blood pressure monitoring. Recently, CSEM explored data-driven approaches using machine learning to enhance the performance of these techniques. The novel methods were tested in the clinical setting and found to outperform previous approaches by up to 15%.

Publication Reference

CSEM Scientific and Technical Report 2020, p. 90

Year

2020

URI

https://hdl.handle.net/20.500.12839/1780

Collections

Technical Marketing Material