Google’s New AI Can Predict Heart Disease by Analyzing Your Eyes
Cernescu Andrei / 5 years ago
It’s almost as good as traditional methods.
Google is making great progress with its machine learning tech. More specifically, the company has recently showcased a software that can predict a person’s age, smoking habits, and blood pressure. What’s even more impressive is that they can obtain the information by analyzing the subject’s eye. After the information is collected, machine learning techniques can extract other important data, such as the probability of cardiac problems. Sure, there are other methods that can extract this information, but those take significantly more time. Google‘s solution is nearly instant, and the best part is that it doesn’t require any bloodwork.
What about accuracy?
At the time of writing, the technology boasts an accuracy rating of about 70%, which is just 2% lower than traditional methods. A dataset consisting of 500,000 patients from across the UK contributed to the algorithm’s training. By comparing scans from ten years ago with the subject’s cardiovascular incidents, the algorithm gradually evolved. So where does the eye come in? Well, there are various patterns in the eye’s blood vessels that point to an increased cardiovascular risk. Neural networks in the system detect these patterns and provide risk assessments.
In the image below, you can see a raw retinal fundus photograph on the left, as well as the patient’s blood vessels in a computer analysis on the right.
By supporting eTeknix, you help us grow and continue to bring you the latest news, reviews, and competitions. Follow us on Facebook and Twitter to keep up with the latest technology, share your favourite articles, chat with the team and more. Also check out eTeknix YouTube, where you’ll find our latest video reviews, event coverage and features in 4K!