AI detects pancreatic cancer up to 3 years earlier, Mayo study shows

ROCHESTER, Minn. (FOX 9) - Mayo Clinic researchers say they have developed an AI tool that can spot pancreatic cancer years before it is typically diagnosed, offering hope for earlier treatment of one of the deadliest cancers.

AI model shows major promise in early pancreatic cancer detection

What we know:

The Mayo Clinic AI, called the Radiomics-based Early Detection Model (REDMOD), can pick up subtle signs of pancreatic cancer on routine abdominal CT scans up to three years before a clinical diagnosis. According to a press release, REDMOD measures hundreds of features describing tissue texture and structure, capturing faint biological changes before tumors are visible.

The study, published in Gut, found that REDMOD identified 73% of prediagnostic cancers at a median of about 16 months before diagnosis — nearly double the detection rate of specialists reviewing the same scans without AI.

In scans taken more than two years before diagnosis, the AI detected nearly three times as many early cancers as specialists.

Dig deeper:

The AI model was validated using nearly 2,000 CT scans from multiple institutions, imaging systems and protocols, mirroring real-world clinical practice. The model's predictions remained stable in patients who had multiple scans months apart, supporting its use for ongoing monitoring and early detection.

The system runs automatically and does not require time-intensive manual preparation.

The backstory:

Mayo Clinic's research is part of a broader effort to enable earlier detection of pancreatic cancer, which is projected to become the second-leading cause of cancer-related death in the U.S. by 2030.

The AI model is designed to analyze CT scans already obtained for other reasons, especially in high-risk patients such as those with new-onset diabetes, and flag elevated risk before any visible mass appears.

Researchers are now advancing this work into clinical testing through the AI-PACED study, which evaluates how clinicians can use AI-guided detection in the care of patients at higher risk for pancreatic cancer. The study combines AI analysis of routine imaging with follow-up to assess early detection rates, false positives and clinical outcomes.

According to a press release, the research is part of Mayo Clinic's Precure initiative, which "aims to predict and prevent disease by identifying the earliest biological changes in the body before symptoms start."

Why you should care:

Pancreatic cancer is especially deadly because it rarely causes symptoms in its early stages. More than 85% of patients are diagnosed after the disease has spread, and five-year survival rates remain below 15%, according to the National Cancer Institute.

"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," said Ajit Goenka, M.D., the study's senior author and a Mayo Clinic radiologist and nuclear medicine specialist, in a statement.

Earlier detection of pancreatic cancer could make curative treatment possible for more patients, potentially improving survival rates for a disease that is often caught too late.

Mayo Clinic says the AI model's ability to work across different hospitals and imaging systems means it could help patients nationwide if adopted widely.