WASHINGTON (dpa-AFX) - An artificial intelligence or AI tool developed by Mayo Clinic can help doctors find pancreatic cancer much earlier than usual, even up to three years before it is normally diagnosed.
'The greatest barrier to saving lives from pancreatic cancer has been our inability to see the disease when it is still curable,' said senior author Ajit Goenka, a Mayo Clinic radiologist and nuclear medicine specialist. 'This AI can now identify the signature of cancer from a normal-appearing pancreas, and it can do so reliably over time and across diverse clinical settings.'
In the study, published in Gut, researchers tested the AI using real-world medical data from different hospitals and scanning systems. They analyzed nearly 2,000 CT scans, including scans from people who were later diagnosed with pancreatic cancer but were originally told their scans were normal.
The AI system, called REDMOD, correctly identified about 73% of these hidden cancers around 16 months before diagnosis. This is almost twice as many as doctors could find without AI. For scans taken more than two years before diagnosis, the AI found nearly three times more early cancers.
The researchers explained that the AI works by studying tiny details in the scan, like changes in tissue patterns, to catch early signs of cancer. It can also analyze scans that were done for other reasons, especially in people at higher risk, such as those who recently developed diabetes.
'The demonstrated ability of the framework to consistently detect these occult signals on a large clinically-oriented dataset, combined with its high longitudinal stability and validated specificity, establishes a robust foundation for AI-augmented early detection,' the researchers wrote.
Researchers are now testing this AI in real clinical settings through a study called AI-PACED. This study will check how well the tool works in everyday care, including how early it can detect cancer, how accurate it is, and how it affects patient outcomes.
Copyright(c) 2026 RTTNews.com. All Rights Reserved
Copyright RTT News/dpa-AFX
© 2026 AFX News
