Facial recognition tech can be used to monitor ICU patient safety

An automated system that uses facial recognition to continuously monitor patients in the intensive care unit was able to predict their risk of unsafe behavior with 75 percent accuracy, according to new research presented at the annual Euroanaesthesia conference in Vienna this week.

In the study, scientists at Yokohama City University Hospital in Japan trained facial recognition technology to detect high-risk arm movements in 24 postoperative patients. As a result, the model was able to predict when the patients were about to remove their breathing tube or engage in other accidental unsafe behavior.

The researchers noted that the facial recognition system could be made more accurate by training it on more photos of patients in various positions. Additionally, integrating patient vital signs into the system could help it distinguish between voluntary movement or accidental high-risk behavior by sedated patients.

"Various situations can put patients at risk, so our next step is to include additional high-risk situations in our analysis, and to develop an alert function to warn healthcare professionals of risky behavior," lead researcher Dr. Akane Sato said in a statement. "Our end goal is to combine various sensing data such as vital signs with our images to develop a fully automated risk prediction system."

More articles about AI:
Most oncologists expect AI to improve patient outcomes in coming years, report finds: 3 notes
IBM Watson Health's clinical support in cancer care proven by multiple studies
Startup using AI, AR to detect Alzheimer's 10 years before onset raises $6.3M

© Copyright ASC COMMUNICATIONS 2020. Interested in LINKING to or REPRINTING this content? View our policies by clicking here.


Featured Content

Featured Webinars

Featured Whitepapers