AI Tool Detecting Skin Conditions Introduced by Google

Google has released an artificial intelligence (AI)-powered dermatology assist tool that uses photographs taken with the user’s phone camera to help diagnose skin, hair, and nail conditions. The new device will detect dermatologic problems such as a rash on your arm using methods similar to those used to detect diabetic eye disease or lung cancer in CT scans. The app’s pilot launch is scheduled for later this year.

The web-based application involves three separate photographs of the skin, hair, or nails taken with a phone camera from different angles. Following that, the consumer must respond to questions about skin type and various symptoms. Following an analysis of these facts, the tool generates a list of possible matches from its database of 288 conditions, allowing the user to conduct additional research.

The tool will include dermatologist-reviewed material, popular questions and answers, and matching images from the web for each matching condition. The new method, according to Google, does not have a diagnosis and is not a substitute for medical advice since some symptoms must be evaluated clinically, in person, or by tests such as biopsies. In Europe, this product was given the CE mark as a Class I medical device.

It has not been approved by the US Food and Drug Administration for protection or efficacy, and it is not available in the United States. The company spent three years researching and developing the tool. It has a de-identified dataset of nearly 65,000 photos of skin disorders that have already been diagnosed, as well as some curated skin issue images and examples of healthy skin from people of different demographics. When creating the tool, Google noted that they considered factors such as age, sex, race, and skin type.