How AI is making it easier to diagnose disease

Watch and share today’s TED Talk. View it in your browser.

July 24, 2018 Today's TED Talk How AI is making it easier to diagnose disease 04:59 minutes · TEDGlobal 2017 Today's AI algorithms require tens of thousands of expensive medical images to detect a patient's disease. What if we could drastically reduce the amount of data needed to train an AI, making diagnoses low-cost and more effective? TED Fellow Pratik Shah is working on a clever system to do just that. Using an unorthodox AI approach, Shah has developed a technology that requires as few as 50 images to develop a working algorithm -- and can even use photos taken on doctors' cell phones to provide a diagnosis. Learn more about how this new way to analyze medical information could lead to earlier detection of life-threatening illnesses and bring AI-assisted diagnosis to more health care settings worldwide. Watch now »   Playlist of the Day What are we really teaching AI? A glimpse inside what we're teaching artificially intelligent machines and a cautionary tale of what could happen if we get it wrong. Watch » 10 talks · Total run time 2:28:20 NEW ON IDEAS.TED.COM How do you make the world’s biggest connect-the-dots? Phil Hansen ended up using an amazing 52,901 dots to draw this portrait in a process that was anything but child’s play. On the way to setting a Guinness World Record, he had to solve many puzzles — and wrestle with some demons. Read more » Join us on Facebook Follow us @TEDTalks

You are receiving this email because you've subscribed to our mailing list. You might also like our weekly emails, compiling all the week’s TED Talks in one handy mailing. Copyright © 2018 TED, All rights reserved. You're receiving the TED Talks daily email because you subscribed to it on TED.com. (Was this forwarded by a friend? You can sign up here: http://www.ted.com/newsletter ) Our mailing address is: TED 330 Hudson Street 11th Floor New York, NY 10013 Add us to your address book unsubscribe from this list   update subscription preferences   view email in browser