<code id='AB17ABA5BD'></code><style id='AB17ABA5BD'></style>
    • <acronym id='AB17ABA5BD'></acronym>
      <center id='AB17ABA5BD'><center id='AB17ABA5BD'><tfoot id='AB17ABA5BD'></tfoot></center><abbr id='AB17ABA5BD'><dir id='AB17ABA5BD'><tfoot id='AB17ABA5BD'></tfoot><noframes id='AB17ABA5BD'>

    • <optgroup id='AB17ABA5BD'><strike id='AB17ABA5BD'><sup id='AB17ABA5BD'></sup></strike><code id='AB17ABA5BD'></code></optgroup>
        1. <b id='AB17ABA5BD'><label id='AB17ABA5BD'><select id='AB17ABA5BD'><dt id='AB17ABA5BD'><span id='AB17ABA5BD'></span></dt></select></label></b><u id='AB17ABA5BD'></u>
          <i id='AB17ABA5BD'><strike id='AB17ABA5BD'><tt id='AB17ABA5BD'><pre id='AB17ABA5BD'></pre></tt></strike></i>

          00:00
          00:00 00:00 LIVE
          buffering
          Replay
          LIVE
          00:00 / 00:00
          LIVE
          CC
          Opacity :
          Share:
          Close

          hotspot

          author:explore    - browse:28
          Illustration of doctor with an computer text bubble for a face for a story on Chat GPT and AI – health tech coverage from STAT
          Mike Reddy for STAT

          Health care companies are racing to incorporate generative AI tools into their product pipelines and IT systems after the technology displayed an ability to perform many tasks faster, cheaper — and sometimes better — than humans.

          But the rush to harness the power of so-called large language models, which are trained on vast troves of data, is outpacing efforts to assess their value. AI experts are still trying to understand, and explain, how and why they work better than prior systems, and what blind spots might undermine their usefulness in medicine.

          advertisement

          It remains unclear, for example, how well these models will perform, and what privacy and ethical quandaries will arise, when they’re exposed to new types of data, such as genetic sequences, CT scans, and electronic health records. Even knowing exactly how much data must be fed into a model to achieve peak performance on a given task is still largely guesswork.

          Unlock this article by subscribing to STAT+ and enjoy your first 30 days free!

          GET STARTED Log In

          entertainment