AI discovers a hidden heart signal that could predict sudden death

Researchers at UC Berkeley have developed an AI model that analyzes EKG scans to identify hidden warning signs of sudden cardiac arrest. The system outperformed traditional screening methods by identifying a higher-risk patient group that standard tests often miss.
Why it matters
This technology could significantly improve preventative care and reduce the 300,000 annual sudden cardiac deaths in the U.S. by enabling earlier intervention.
More than 300,000 people in the United States die from sudden cardiac arrest each year. This deadly emergency occurs when the heart's electrical system suddenly fails, causing the heart to stop pumping blood. It can strike older adults with known heart conditions as well as seemingly healthy young athletes. Although implanted defibrillators can prevent some of these deaths, doctors have long struggled to determine which patients need them most.
Now, researchers at UC Berkeley have identified a previously overlooked warning signal in routine heart scans that could make it easier to recognize people at risk before a fatal event occurs.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in