Skip to main content

Did your surgeon wash up effectively? This AI-powered camera can tell

Wassana Sakulrattanapornchai/123RF
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.

Editors' Recommendations

Luke Dormehl
I'm a UK-based tech writer covering Cool Tech at Digital Trends. I've also written for Fast Company, Wired, the Guardian…
The Moorebot Scout is a roving security camera robot that’ll patrol your home
scout moorebot security robot patrols your home

Security cameras are powerful tools for keeping your home protected, but they are limited in what they can see. You have to be careful with the placement of the camera to give it the maximum possible angle. If only there was an indoor security camera that could move around your home as needed -- something like robot maker Moorebot's Scout, perhaps? The Scout is a tiny, artificial intelligence- (A.I.) powered robot that looks a lot like an RC car with a camera.

It has a 1080p camera with night vision capabilities, as well as an IP65 weather resistance rating that allows it to navigate outdoors just as easily as it does indoors. It also has four-wheel drive and Mecanum wheels that let it zip over almost all terrain without getting stuck.

Read more
MIT’s clever robotic basketball hoop will help you level up your game
MIT robot basketball hoop

Researchers from Massachusetts Institute of Technology’s Computer Science & Artificial Intelligence Laboratory might not seem like the folks most likely to help you improve your hoop-shooting basketball skills. But that’s exactly what a new MIT CSAIL project sets out to do with a quirky basketball-training machine featuring a basketball hoop that shrinks and raises when you make shots, thereby shape-shifting to help improve the various facets of your game.

For example, to begin with, the basket can be positioned at a lower height with wider hoop diameter, which gradually shrinks down and also raises to reach regulation proportions as you score more and more baskets. It’s an unusual project from a lab that’s more used to working with the latest cutting-edge artificial intelligence algorithms -- but, as it turns out, it fits perfectly with CSAIL’s areas of expertise.

Read more
A.I. can tell if you’re a good surgeon just by scanning your brain
brain with computer text scrolling artificial intelligence

Could a brain scan be the best way to tell a top-notch surgeon? Well, kind of. Researchers at Rensselaer Polytechnic Institute and the University at Buffalo have developed Brain-NET, a deep learning A.I. tool that can accurately predict a surgeon’s certification scores based on their neuroimaging data.

This certification score, known as the Fundamentals of Laparoscopic Surgery program (FLS), is currently calculated manually using a formula that is extremely time and labor-consuming. The idea behind it is to give an objective assessment of surgical skills, thereby demonstrating effective training.

Read more