DeepMind AI Can Predict Kidney Failure 48 Hours Early

DeepMind AI Can Predict Kidney Failure 48 Hours Early

first_img McDonald’s Plans to Serve AI Voice Technology at Drive ThruCIMON Returns to Earth After 14 Months on ISS Artificial intelligence can predict a leading cause of preventable patient harm up to two days before it occurs.Google’s DeepMind, in partnership with the U.S. Department of Veterans Affairs, developed technology that could give doctors a 48-hour head start in treating acute kidney injury (AKI).The condition (previously known as acute renal failure) causes build-up of waste in the blood, making it hard for the kidneys to balance fluid; the result is often a sudden failure or damage that occurs over a few hours or a few days.Affecting up to one in five hospitalized patients in the US and UK, AKI is notoriously difficult to spot, and deterioration can happen quickly.Machine learning to the rescue!Using anonymized health records from the VA network, DeepMind’s AI correctly predicted nine out of 10 patients whose condition deteriorated so severely they required dialysis.“This could provide a window in the future for earlier preventative treatment and avoid the need for more invasive procedures like kidney dialysis,” study co-authors Dominic King and Mustafa Suleyman wrote in a blog post.The team hopes the model will one day be used to identify other major causes of disease and deterioration, including life-threatening infection sepsis.Their research was published this week in the journal Nature.DeepMind wants to use AI to give doctors a 48-hour head start on life-threatening illness (via DeepMind)“This is our team’s biggest healthcare research breakthrough to date, demonstrating the ability to not only spot deterioration more effectively, but actually predict it before it happens,” Suleyman and King said.The technology, however, won’t help anyone without the right tools to alert specialists.“Better technology is desperately needed so that critical information can be delivered to the right specialist at the right time,” DeepMind said.Enter Streams, a mobile medical assistant for clinicians, which has been in use at the Royal Free London NHS Foundation Trust since early 2017.The app allows specialists to review urgent cases in 15 minutes or less—a process that might otherwise take several hours—and helps reduce the number of AKI cases missed at the hospital.“Getting the right information about the right patient at the right time is a huge problem for healthcare systems across the globe,” according to King and Suleyman.“These results comprise the building blocks for our long-term vision of preventative healthcare, helping doctors to intervene in a proactive, rather than reactive, manner,” they added.Research, led by David Feinberg, will continue as part of Google Health.More on Geek.com:New AI Tool Can Help Doctors Detect Brain AneurysmsGoogle Algorithm Detects Lung Cancer Better Than Human DoctorsResearchers Train AI To Feel Emotion, Too Stay on targetlast_img

Leave a Reply

Your email address will not be published. Required fields are marked *