AUTHOR=Nishidate Izumi , Yasui Riku , Nagao Nodoka , Suzuki Haruta , Takara Yohei , Ohashi Kaoru , Ando Fuminori , Noro Naoki , Kokubo Yasuaki 

TITLE=RGB camera-based simultaneous measurements of percutaneous arterial oxygen saturation, tissue oxygen saturation, pulse rate, and respiratory rate

JOURNAL=Frontiers in Physiology

VOLUME=13

YEAR=2022

URL=https://www.frontiersin.org/journals/physiology/articles/10.3389/fphys.2022.933397

DOI=10.3389/fphys.2022.933397

ISSN=1664-042X

ABSTRACT=<p>We propose a method to perform simultaneous measurements of percutaneous arterial oxygen saturation (<italic>SpO</italic><sub>2</sub>), tissue oxygen saturation (<italic>StO</italic><sub>2</sub>), pulse rate (<italic>PR</italic>), and respiratory rate (<italic>RR</italic>) in real-time, using a digital red–green–blue (RGB) camera. Concentrations of oxygenated hemoglobin (<italic>C</italic><sub>HbO</sub>), deoxygenated hemoglobin (<italic>C</italic><sub>HbR</sub>), total hemoglobin (<italic>C</italic><sub>HbT</sub>), and <italic>StO</italic><sub>2</sub> were estimated from videos of the human face using a method based on a tissue-like light transport model of the skin. The photoplethysmogram (PPG) signals are extracted from the temporal fluctuations in <italic>C</italic><sub>HbO</sub>, <italic>C</italic><sub>HbR</sub>, and <italic>C</italic><sub>HbT</sub> using a finite impulse response (FIR) filter (low and high cut-off frequencies of 0.7 and 3 Hz, respectively). The <italic>PR</italic> is calculated from the PPG signal for <italic>C</italic><sub>HbT</sub>. The ratio of pulse wave amplitude for <italic>C</italic><sub>HbO</sub> and that for <italic>C</italic><sub>HbR</sub> are associated with the reference value of <italic>SpO</italic><sub>2</sub> measured by a commercially available pulse oximeter, which provides an empirical formula to estimate <italic>SpO</italic><sub>2</sub> from videos. The respiration-dependent oscillation in <italic>C</italic><sub>HbT</sub> was extracted from another FIR filter (low and high cut-off frequencies of 0.05 and 0.5 Hz, respectively) and used to calculate the <italic>RR</italic>. <italic>In vivo</italic> experiments with human volunteers while varying the fraction of inspired oxygen were performed to evaluate the comparability of the proposed method with commercially available devices. The Bland–Altman analysis showed that the mean bias for <italic>PR</italic>, <italic>RR</italic>, <italic>SpO</italic><sub>2</sub>, and <italic>StO</italic><sub>2</sub> were -1.4 (bpm), -1.2(rpm), 0.5 (%), and -3.0 (%), respectively. The precisions for <italic>PR</italic>, <italic>RR</italic>, <italic>Sp O</italic><sub>2</sub>, and <italic>StO</italic><sub>2</sub> were ±3.1 (bpm), ±3.5 (rpm), ±4.3 (%), and ±4.8 (%), respectively. The resulting precision and RMSE for <italic>StO</italic><sub>2</sub> were pretty close to the clinical accuracy requirement. The accuracy of the <italic>RR</italic> is considered a little less accurate than clinical requirements. This is the first demonstration of a low-cost RGB camera-based method for contactless simultaneous measurements of the heart rate, percutaneous arterial oxygen saturation, and tissue oxygen saturation in real-time.</p>