Google’s latest foray into healthcare is a web tool that uses artificial intelligence to help people identify skin, hair, or nail conditions. The company previewed the tool at I / O today and hopes to launch a pilot later this year.
People can use their phone’s camera to take three photos of the problem area, such as a rash on their arm. They then answer a series of questions about their skin type and other symptoms. The tool then lists possible conditions from a set of 288 that it has been trained to recognize. It’s not intended to diagnose the problem, the company said in a statement blog post.
Google decided to tackle skin conditions with artificial intelligence because of their prevalence, says Karen DeSalvo, the chief health officer at Google Health. “People come to Google to ask questions about skin conditions. We get about 10 billion questions about skin condition every year,” she said in an interview with The edge. Of course, experts can help people determine if it is something simple or indicates a more serious illness, but there is a shortage of dermatologists around the world. DeSalvo hopes that this tool can help people provide people with accurate information about possible conditions quickly, without having to spend hours on their own online research.
The team trained the model on millions of images of skin problems, thousands of images of healthy skin, and 65,000 images from clinical settings. The model takes into account factors such as age, skin type, gender and race when suggesting possible conditions. When it was tested on about 1,000 images of skin problems from a wide variety of patients, Google said it identified the correct condition in the top three suggestions 84 percent of the time. It included correct condition as one of the potential problems in 97 percent of the cases.
The new system builds on Google’s previous work by using artificial intelligence tools to identify skin conditions. The company published the first iteration of its deep learning system in Nature Medicine last spring. That article showed that the system could identify 26 common skin conditions just as accurately as dermatologists and more accurately than general practitioners. In April the company published another study showing that the system can help non-dermatologists more accurately diagnose skin conditions.
Google is also working with a Stanford University research team to test how well the tool works in healthcare.
The company has obtained a Class I medical device in the European Union identifying it as a low risk medical device. It has not been evaluated by the United States Food and Drug Administration.