The AI model, called REDMOD, detected pancreatic cancer an average of 475 days before clinical diagnosis with 88% specificity. The system correctly identified patients who did not have the cancer while spotting what researchers described as an "invisible" signature of pre-clinical pancreatic ductal adenocarcinoma.
"The greatest barrier to saving lives from pancreatic cancer has been our inability to see the disease when it is still curable," said Mayo Clinic Radiologist and Nuclear Medicine Specialist Ajit Goenka, M.D., the study's senior author.. "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."
For cases detected more than two years before clinical diagnosis, REDMOD proved nearly three times as accurate as radiologists, achieving 68% accuracy compared to 23% for human specialists reviewing the same imaging.
Mayo's breakthrough arrives amid broader AI advances in pancreatic cancer detection. PanDx, an AI framework for analyzing contrast-enhanced CT scans, recently achieved first place in the PANORAMA challenge with an AUROC of 0.9263.
Mayo Clinic researchers are now conducting AI-PACED, a prospective clinical study evaluating how clinicians can integrate AI-guided detection into care for patients at elevated risk. The study aims to translate REDMOD's laboratory success into real-world clinical applications.
Early detection remains crucial for pancreatic cancer, projected to become the second-leading cause of cancer-related death in the U.S. by 2030. The disease's lethality stems from its late presentation—more than 85% of patients receive a diagnosis after the cancer has already spread, the same report noted.
Around 67,530 Americans are expected to be diagnosed with pancreatic cancer in 2026. Current treatment options remain limited once the disease advances beyond the pancreas. REDMOD emerged from Mayo Clinic's Precure initiative, a program focused on predicting and preventing disease by identifying the earliest biological changes before symptoms appear.
