<code id='CE985CC448'></code><style id='CE985CC448'></style>
    • <acronym id='CE985CC448'></acronym>
      <center id='CE985CC448'><center id='CE985CC448'><tfoot id='CE985CC448'></tfoot></center><abbr id='CE985CC448'><dir id='CE985CC448'><tfoot id='CE985CC448'></tfoot><noframes id='CE985CC448'>

    • <optgroup id='CE985CC448'><strike id='CE985CC448'><sup id='CE985CC448'></sup></strike><code id='CE985CC448'></code></optgroup>
        1. <b id='CE985CC448'><label id='CE985CC448'><select id='CE985CC448'><dt id='CE985CC448'><span id='CE985CC448'></span></dt></select></label></b><u id='CE985CC448'></u>
          <i id='CE985CC448'><strike id='CE985CC448'><tt id='CE985CC448'><pre id='CE985CC448'></pre></tt></strike></i>

          Home / explore / comprehensive

          comprehensive


          comprehensive

          author:fashion    Page View:8485
          A person stands in front of a Google office building -- coverage from STAT
          NOAH SEELAM/AFP via Getty Images

          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