Video game cameras accurately monitor hand hygiene, PPE adherence
Click Here to Manage Email Alerts
Reprogramming motion-tracking cameras initially designed to control video games could be an effective means to monitor proper hand hygiene and personal protective equipment adherence among health care workers, according to recently published study data.
“Several approaches have been developed to electronically monitor hand hygiene adherence,” researcher Junyang Chen and colleagues at the University of Iowa wrote. “It is relatively straightforward to determine if a health care worker [HCW] has practiced hand hygiene on entering or leaving a room. However, it is much more difficult to monitor what is happening inside a patient room at the bedside, where most of the opportunities to spread pathogens from the hands of health care workers to patients occur.”
To tackle this issue, Chen and colleagues developed unique software for the Microsoft Kinect. A video game peripheral capable of tracking the skeletal movements of multiple simultaneous users, the researchers programmed the cameras to track an individual’s hand movements for potential contact events, and observe personal protective equipment (PPE) use by scanning for colored face, hand and torso obstructions. Two Kinects were placed at opposite ends of the patient’s bed to observe contact events, and a third was placed on a tripod facing the room’s entrance to detect PPE. The cameras’ accuracy was determined by recruiting test individuals to simulate multiple instances of patient care within an empty room and comparing the system’s findings with manual observations.
The majority of events and outcomes reported by the cameras matched those observed by the researchers. The Kinects detected hand contact events at 99.7% sensitivity with a positive predictive value of 98.7%, and 90% of touches’ duration were recorded within 0.25 seconds of that reported by the researchers. Sensitivity for various PPE ranged from 86.21% to 100%, while sensitivity ranged from 98.15% to 98.75%.
Chen and colleagues noted the system’s limitations —which included difficulties in observing behavior away from the bedside, as well as distinguishing between HCWs and patients — but concluded that the devices have great potential to monitor adherence within ICUs.
“Our results demonstrate that we can use computer vision and rangefinding to better understand hand-hygiene opportunities at the patient’s bedside,” the researchers wrote. “Although we cannot yet determine when an [HCW] is compliant with hand hygiene according to the specific WHO five moments, we can estimate how often and for how long a health care worker’s hands are within touching distance of a patient in a bed, and we can do this without the [HCW] wearing any specialized badge or equipment.” – by Dave Muoio
Disclosure: After this project, Chen reports participating in a software engineering internship at Microsoft.