Google’s generative AI system proved it can answer medical exam questions. But now the company is attempting a bigger leap — infusing its model with medical images such as X-rays and mammograms to help it communicate with doctors about data routinely used in patient care.
The effort, unveiled Wednesday, marks the beginning of a quest to make generative AI a more dynamic tool in medicine. While prior iterations of AI could either analyze images, or respond to questions, the company’s new model, known as Med-Palm 2, aims to put those capabilities together in a single system.
advertisement
“Until this year, this was not on the table,” said Greg Corrado, a senior research scientist at Google. “Now you can build a system — and this is amazing to me, honestly, I did not expect this to happen now — but you can build a system where you give it an image, it writes a report, and then you can ask it follow-up questions.”
Unlock this article by subscribing to STAT+ and enjoy your first 30 days free!
GET STARTED Log In
Previous article：
Health tech investors get more selective as pandemic boom fades
Next article： Drug repurposing or repositioning? The language matters
Next article： Drug repurposing or repositioning? The language matters
