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.
“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.”
About the Author Reprints
To submit a correction request, please visit our Contact Us page.
STAT encourages you to share your voice. We welcome your commentary, criticism, and expertise on our subscriber-only platform, STAT+ Connect