A team of researchers at the University of South Australia (UniSA) is trying to use computer vision technology to monitor the health of babies that were born prematurely. The researchers noted that premature babies are more likely to face health complications, which means that they need to be monitored continuously to make sure that doctors can respond to an adverse event as quickly as possible.
The problem is that that monitoring has historically been carried out with electrodes and adhesive pads that are applied directly to the skin. Those electrodes pose their own health risk, since they can lead to infections and tear the skin of premature infants.
With that in mind, the UniSA researchers set out to develop a contactless health monitoring system. They ended up using high-resolution digital cameras outfitted with an AI system designed to measure the heart and respiratory rates of infants in intensive care. The technology was applied to seven infants at the Flinders Medical Centre Neonatal Intensive Care Unit (NICU) in Adelaide, and was found to be just as accurate as an ECG machine and standard electrodes.
The cameras were deployed at close range to try to overcome environmental issues. The final results of the study were published in the Journal of Imaging.
“In the NICU setting it is very challenging to record clear videos of premature babies. There are many obstructions, and the lighting can also vary, so getting accurate results can be difficult,” said UniSA neonatal critical care specialist Kim Gibson. “However, the detection model has performed beyond our expectations… We believe non-contact monitoring is the way forward.”
As it stands, more than 10 percent of all children are born prematurely. The UniSA system is sensitive enough to capture heart beats and small body movements.
Other researchers have tried using similar camera-based heart rate detection technology to help spot deepfake videos, noting that someone’s heartbeat will create unique color changes in the skin of a real human being. Parsons also released a contactless health screening system to improve public health outcomes in response to COVID-19, though that was a quick screening system geared toward adults rather than a continuous monitoring system for infants.
Source: ZDNet
–
August 26, 2021 – by Eric Weiss
Follow Us