Non-contact automatic vital signs monitoring of neonates in NICU using video camera imaging

Non-contact vital signs monitoring is desirable in both clinical and non-clinical sectors. However, there are limited camera-based studies to monitor the vital signs of neonatal infants in a clinical setting. In this study, a digital camera was used to remotely monitor the heart rate (HR) and respiratory rate (RR) of seven infants at Flinders Medical Centre Neonatal Intensive Care Unit (NICU). The region-of-interest (ROI) was automatically selected based on a skin detection method using skin hue. The experimental results have been validated with the reference data obtained from an ECG monitor, and they showed a strong correlation using the Pearson correlation coefficient, (PCC) .9836 and .9426 for HR and RR, respectively, and a lower error rate with RMSE 2.66 beats/min and 2.93 breaths/min between measured data and reference data. A Bland Altman analysis of the data also presented a close correlation between measured data and reference data for both HR and RR with a mean bias .69 beats/min and .28 breaths/min, and the lower and upper limit of agreement -4.4 to +5.8 beats/min and -5.5 to +6.1 breaths/min, respectively. Therefore, video camera imaging may replace conventional monitoring in NICU and has potential applications in other contexts such as home health monitoring.