Availability and performance of image-based, non-contact methods of monitoring heart rate, blood pressure, respiratory rate, and oxygen saturation: a systematic review.
Harford M., Catherall J., Gerry S., Young JD., Watkinson PJ.
BACKGROUND: Over the last 15 years, developments in camera technology have coincided with increased availability and affordability. This has led to an increasing interest in using these technologies in healthcare settings. Image-based monitoring methods allow multiple vital signs to be measured concurrently using a non-contact sensor. We have undertaken a systematic review of these monitoring methods. &#13; Methods: A multiple database search was conducted using Medline, Embase, CINAHL, Cochrane Library, OpenGrey, IEEE Xplore Library, and ACM Digital Library to July 2018. We included studies comparing image-based heart rate, respiratory rate, oxygen saturation, and blood pressure monitoring methods against validated reference device(s). Each included study was assessed using the modified GRRAS criteria. &#13; Results: Of 30279 identified studies, 161 were included in the final analysis. Twenty studies (12%) were carried out on patients in clinical settings, while the remainder were conducted using healthy volunteer populations. The 18 to 40 age group was best represented across the identified studies. 120 studies (74%) estimated heart rate, followed by 62 studies (39%) estimating respiratory rate. Fewer studies focused on oxygen saturation (7%) or blood pressure (4%). 51 heart rate studies and 24 respiratory rate studies used Bland-Altman analysis to report their results. Of the heart rate studies, 28 studies showed agreement within industry standards. Only 2 studies achieved this in clinical settings. 13 respiratory rate studies showed agreement within industry standards but only one achieved this in a clinical setting. The majority of studies (62%) monitored subjects for under 5 minutes.&#13; Discussion: Heart rate and respiratory rate monitoring using images is currently possible and performs within clinically acceptable limits in experimental conditions. Camera-derived estimates were less accurate in the proportion of studies in clinical settings. We would encourage thorough reporting of the population studied, detailed methodology, and the use of appropriate statistical methods in future studies.