Having security cameras is one thing, but having security cameras equipped with cutting-edge image recognition algorithms is quite another. It means that, instead of having to have a human physically monitoring the camera feed at all times to act on it, the cameras themselves can spot items of interest. Previously, we covered artificial intelligence-equipped cameras that could make construction sites safer, as well as ones which may prove even better than polygraphs at recognizing when a person is lying.
Now, researchers at Stanford University have used similar technology to develop security cameras for hospitals which can automatically identify when people use or skip out on using the provided alcohol-based gel dispensers when they go from ward to ward. The technology could have an important role to play in cutting down on infection rates in hospitals.
The researchers started by training their system on footage of people using the gel (or not, as it happened!) on two wards. Of the 170 people who entered a patient’s room at various times, just 30 used the dispensers. This data was then used to train the system to recognize the difference between a person using the gel or not using it. After a training process, the cameras were able to recognize with an accuracy level of 75 percent whether or not people were using these dispensers. According to the researchers, a human doing the same monitoring job — as a way of testing the camera’s efficacy — managed just 63 percent accuracy.
The pilot program apparently went so well that the researchers are now providing the cameras to three hospitals for a period of one year to study whether or not they can have a positive impact on infection rates.
Although the technology cannot physically make someone use the alco-gel to clean their hands, the information can be used in different ways. For instance, insights gathered could be used by hospital managers to help inform staff training, select new locations for alcohol gels (if some locations have a better “hit rate” than others), prompt the putting up of extra safety posters, and so on. Trained on other hospital-related tasks or actions, it is possible to imagine a similar system could be used to monitor vital signs, look for possible distress among patients, check for falls, and more. The technology would not take away jobs from doctors or nurses but could help them in improving safety among the hospital’s residents.
