Google I/O 2021: An AI model to diagnose dermatological dilemmas

An AI-powered dermatology assist tool will require users to take photos of their area of concern and have a possible diagnosis returned.

google-skin-ss.png

Image: Google

Google has announced two artificial intelligence-powered advancements, with the first being a dermatology assist tool that aims to help people understand what's going on with their skin, hair, and nails.

Unveiling a preview at Google I/O, with plans to launch a pilot later this year, the AI-powered dermatology assist tool is a web-based application that will show dermatologist-reviewed information and answers to commonly asked questions, along with similar matching images from the web to help people with their dermatological issues, Google said.

To use the tool, users will require a phone's camera to take three images of the skin, hair, or nail concern from different angles.

"You'll then be asked questions about your skin type, how long you've had the issue, and other symptoms that help the tool narrow down the possibilities," Google Health product manager Peggy Bui explained in a blog post written alongside technical lead Yuan Liu.

"The AI model analyses this information and draws from its knowledge of 288 conditions to give you a list of possible matching conditions that you can then research further."

"The tool is not intended to provide a diagnosis nor be a substitute for medical advice as many conditions require clinician review, in-person examination, or additional testing like a biopsy," the blog cautioned. "Rather we hope it gives you access to authoritative information so you can make a more informed decision about your next step."

The company said its new tool is the culmination of over three years of machine learning research and product development. It added it has published several peer-reviewed papers that validate its AI model, with more in the works. 

The next AI-powered health initiative is research that could soon turn into a tuberculosis screening aid.

Tuberculosis, or TB, infects 10 million people per year, Google said, disproportionately affecting people in low-to-middle-income countries. 

"Cost-effective screening, specifically chest X-rays, has been identified as one way to improve the screening process. However, experts aren't always available to interpret results," Google said.

"To help catch the disease early and work toward eventually eradicating it, Google researchers developed an AI-based tool that builds on our existing work in medical imaging to identify potential TB patients for follow-up testing."

Google said "the right" deep learning system can be used to accurately identify patients who are likely to have active TB based on their chest X-ray. By using this screening tool as a preliminary step before ordering a more expensive diagnostic test, it claimed its study showed that effective AI-powered screening could save up to 80% of the cost per positive TB case detected. 

"Our AI-based tool was able to accurately detect active pulmonary TB cases with false-negative and false-positive detection rates that were similar to 14 radiologists," it said. "This accuracy was maintained even when examining patients who were HIV-positive, a population that is at higher risk of developing TB and is challenging to screen because their chest X-rays may differ from typical TB cases."

RELATED COVERAGE