New AI system can spot hospital staff who don't wash hands

Scientists have developed a new artificial intelligence system that can track medical staff through cameras and detect whether they maintain proper hand hygeine, an advance that could reduce the risk of hospital- acquired infections. Researchers at the Swiss Federal Institute of Technology (EPFL) conducted a study using a combination of depth cameras and computer-vision algorithms. 

They tracked people around two hospital wards and automatically identified when they used gel dispensers. "We're trying to shed light on the dark spaces of healthcare. Understanding the problem is just the first step," said Alexandre Alahi from EPFL. In the initial study, researchers collected images from cameras installed overlooking corridors, patient rooms and alcohol-based gel dispensers, among other places.

Of the 170 people they recorded entering a patient's room, only 30 people correctly used the gel dispensers. The team then used 80 per cent of the images to train their algorithms to detect healthcare staff, track them as they move from one spot to another across different cameras, and monitor their hand hygiene behaviour. Once trained, they tested the system on the remaining 20 per cent, and achieved an accuracy of 75 per cent in telling whether people had used the dispensers.

Although there are privacy concerns related to cameras constantly monitoring hospitals, researchers said that the cameras used capture more information about the position of a person than about how they look. The resulting images consist of unidentifiable human blobs, 'New Scientist' reported. Cameras dotted around hospitals could help with other things too. Artificial intelligence has already demonstrated the ability to detect falls and monitor vital signs. It could do this throughout a hospital.