Non-contact heart rate monitoring utilizing camera photoplethysmography in the neonatal intensive care unit - a pilot study.

BACKGROUND: Presently the heart rate is monitored in the Neonatal Intensive Care Unit with contact sensors: electrocardiogram or pulse oximetry. These techniques can cause injuries and infections, particularly in very premature infants with fragile skin. Camera based plethysmography was recently demonstrated in adults as a contactless method to determine heart rate. AIM: To investigate the feasibility of this technique for NICU patients and identify challenging conditions. STUDY DESIGN AND PARTICIPANTS: Video recordings using only ambient light were made of 19 infants at two NICUs in California and The Netherlands. Heart rate can be derived from these recordings because each cardiovascular pulse wave induces minute pulsatile skin color changes, invisible to the eye but measurable with a camera. RESULTS: In all infants the heart beat induced photoplethysmographic signal was strong enough to be measured. Low ambient light level and infant motion prevented successful measurement from time to time. CONCLUSIONS: Contactless heart rate monitoring by means of a camera using ambient light was demonstrated for the first time in the NICU population and appears feasible. Better hardware and improved algorithms are required to increase robustness.

Robust pulse rate from chrominance-based rPPG.

Remote photoplethysmography (rPPG) enables contactless monitoring of the blood volume pulse using a regular camera. Recent research focused on improved motion robustness, but the proposed blind source separation techniques (BSS) in RGB color space show limited success. We present an analysis of the motion problem, from which far superior chrominance-based methods emerge. For a population of 117 stationary subjects, we show our methods to perform in 92% good agreement ( ±1.96σ) with contact PPG, with RMSE and standard deviation both a factor of 2 better than BSS-based methods. In a fitness setting using a simple spectral peak detector, the obtained pulse-rate for modest motion (bike) improves from 79% to 98% correct, and for vigorous motion (stepping) from less than 11% to more than 48% correct. We expect the greatly improved robustness to considerably widen the application scope of the technology.