To date, no one has published an independent, comparative performance analysis of AI detection models in imaging, similar to Consumer Reports, the study's authors believe. 

Currently, only about 17% of U.S. Food and Drug Administration-authorized AI medical devices are labeled for use with children. 

A lack of generalizability in the early days of AI development was one of the biggest caveats attached to the technology.

European imaging experts recently conducted an expansive study, involving 10 different AI tools from seven separate vendors, implemented across 20 centers staffed by 58 rads. 

Health and Human Services Secretary Robert Kennedy Jr. said he believes the technology offers the opportunity to “free us from medical tyranny.” 
 

A new analysis of the U.S. Food and Drug Administration’s artificial intelligence-enabled medical device database details how the technology’s regulatory standing has changed in recent years. 

The implementation will span three hospitals in Sweden’s Stockholm Region, supporting between 200,000 and 250,000 breast imaging exams annually. 

Persistent organ failure is among the most serious complications of acute pancreatitis and is associated with mortality rates of 30% to 50%. 

Researchers believe the approach could eventually help reduce unnecessary gadolinium exposure for some patients while maintaining useful information for diagnosis and treatment planning. 

Radiology departments need to think about long-term management of AI, not just which algorithms may help them currently.