Google’s Dermatology Assist Tool is all set to Turn your Phone’s Camera into a Dermatologist

by Meenal Bhatia

Google’s Dermatology Assist Tool is all set to Turn your Phone’s Camera into a Dermatologist

May 19, 2021

Artificial intelligence (AI) has a great potential when it comes to healthcare and tech giants have just started unleashing it. The latest on the list is Google Health's new AI-powered dermatology assist tool that will help us understand what’s going on with issues related to our body’s largest organ: skin, hair and nails.

Most of us find ourselves turning to google to find out what our symptoms mean, even if it is just a headache, only to be greeted with the list of worst possible diseases with the worst possible outcomes.

You aren’t the only one, each year Google sees almost 10 billion searches related to skin, nail and hair issues. About 2 Billion people worldwide suffer from dermatologic issues, but there’s a global shortage of specialists. Google isn’t a doctor but it is planning to use its AI to become better at helping us.

Table of Contents

"Skin diseases as a category are an enormous global burden — people are turning to Google to research their skin concerns. Most cases are curable, but half the world’s population faces a critical shortage of dermatologists."

- Dr Peggy Bui, product manager at Google Health and an internal medicine specialist at the University of California, San Francisco.

How it works

While many people’s first step involves going to a Google Search bar, it can be difficult to describe what you’re seeing on your skin through words alone. This is where AI would step in. Google unveiled a trial “dermatology assist tool”, at its annual developer conference, Google IO.

Users will be able to self-diagnose issues ranging from acne to melanoma by uploading images of their medical condition via the Derm Assist website and answer questions about their symptoms.

9f783b60 b80b 11eb b7bf 80ee2bfcb5d3

Testing its Effectiveness

An AI model will analyse the information and give a list of possible conditions. The AI has been fed with millions of images of skin problems, thousands of images of healthy skin, and 65,000 images from clinical settings. It takes factors like age, skin type, sex, and race into account when suggesting possible conditions.

To determine the effectiveness, it was tested on around 1,000 images of skin problems uploaded by patients and Google claims it identified the correct condition in the top three suggestions 84% of the time. It included the correct condition as one of the possible issues 97% of the time.


Building up on Previous Research

Google’s dermatology assist tool is the culmination of over three years of machine learning research and product development. They have already published several peer-reviewed papers that validate their AI model. 

Their study, featured in Nature Medicine, debuted their deep learning approach to assess skin diseases and showed that the AI system can achieve accuracy that is on par with U.S. board-certified dermatologists.

Another recent paper in JAMA Network Open demonstrated how non-specialist doctors can use AI-based tools to improve their ability to interpret skin conditions. 

To make sure the tool is built for everyone, the model takes in account various factors like age, sex, race and skin types.

The Right Direction

Google hopes this tool can help get people accurate information about potential conditions, quickly, without having to spend hours doing their own online research. 

Google doesn’t intend the tool to provide a full-fledged diagnosis of the issues as many of them may require an in-depth review by a specialist, instead it hopes to provide ample information so users can make an informed decision going further.

The dermatology AI tool has passed clinical validation and has been marked as a Class I medical device in the EU. The AI tool has not been evaluated by other health regulators around the world as of now. The tool will debut later this year. Do you think it will be a time saving tool or just add more to paranoia?


Recommended for you

Leave a Comment

This website uses cookies to improve your experience. We'll assume you're ok with this, but you can opt-out if you wish. Accept Read More