3.9 Article

Remote vital parameter monitoring in neonatology - robust, unobtrusive heart rate detection in a realistic clinical scenario

Journal

BIOMEDICAL ENGINEERING-BIOMEDIZINISCHE TECHNIK
Volume 61, Issue 6, Pages 631-643

Publisher

WALTER DE GRUYTER GMBH
DOI: 10.1515/bmt-2016-0025

Keywords

grid analysis; image post-processing algorithms; motion artifact compensation; photoplethys mography imaging; remote sensing; robust heart rate recognition; term and preterm infants; vital parameter monitoring

Ask authors/readers for more resources

Vital parameter monitoring of term and preterm infants during incubator care with self-adhesive electrodes or sensors directly positioned on the skin [e.g. photoplethysmography ( PPG) for oxygen saturation or electrocardiography (ECG)] is an essential part of daily routine care in neonatal intensive care units. For various reasons, this kind of monitoring contains a lot of stress for the infants. Therefore, there is a need to measure vital parameters (for instance respiration, temperature, pulse, oxygen saturation) without mechanical or conductive contact. As a non-contact method of monitoring, we present an adapted version of camera-based photoplethysmography imaging (PPGI) according to neonatal requirements. Similar to classic PPG, the PPGI camera detects small temporal changes in the term and preterm infant's skin brightness due to the cardiovascular rhythm of dermal blood perfusion. We involved 10 preterm infants in a feasibility study [five males and five females; mean gestational age: 26 weeks (24-28 weeks); mean biological age: 35 days (8-41 days); mean weight at the time of investigation: 960 g (670-1290 g)]. The PPGI camera was placed directly above the incubators with the infant inside illuminated by an infrared light emitting diode (LED) array (850 nm). From each preterm infant, 5-min video sequences were recorded and analyzed post hoc. As the measurement scenario was kept as realistic as possible, the infants were not constrained in their movements in front of the camera. Movement intensities were assigned into five classes (1: no visible motion to 5: heavy struggling). PPGI was found to be significantly sensitive to movement artifacts. However, for movement classes 1-4, changes in blood perfusion according to the heart rate (HR) were recovered successfully (Pearson correlation: r = 0.9759; r = 0.765 if class 5 is included). The study was approved by the Ethics Committee of the Universal Hospital of the RWTH Aachen University, Aachen, Germany (EK 254/13).

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

3.9
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available