Mayo Clinic AI detects pancreatic cancer up to 3 years in advance

The Mayo Clinic's REDMOD model detects early signs of pancreatic cancer on standard abdominal scans, with a detection rate nearly double that of radiologists alone.

Called REDMOD (Radiomics-based Early Detection Model), the tool developed by the Mayo Clinic analyzes the texture and structure of tissues on abdominal scans already routinely performed, looking for biological changes invisible to the naked eye before the appearance of a visible tumor.

In a validation study of nearly 2,000 CT scans — including tests initially considered normal in patients who were later diagnosed — the model detected pancreatic cancer in nearly three out of four cases, on average 16 months before clinical diagnosis, a rate almost double that of specialist radiologists analyzing the same images. The researchers are now preparing a clinical trial called AI-PACED to evaluate the integration of this tool in the follow-up of high-risk patients.