Breakthrough Study Shows AI Can Predict Pancreatic Cancer Years in Advance

A Mayo Clinic-developed AI system called REDMOD can detect pancreatic cancer on routine CT scans up to three years before clinical diagnosis, identifying 73% of prediagnostic cancers at a median of 16 months before diagnosis—nearly double the detection rate of specialists without AI assistance. The breakthrough addresses a critical need, as more than 85% of pancreatic cancer patients are diagnosed after the disease has spread, contributing to five-year survival rates below 15% and projections that pancreatic cancer will become the second-leading cause of cancer death in the U.S. by 2030. REDMOD analyzes hundreds of quantitative imaging features to detect subtle tissue changes before tumors become visible, running automatically on existing CT scans without manual preparation. Researchers are now advancing REDMOD into clinical testing through the AI-PACED prospective study to evaluate integration into care for high-risk patients.

AI Model's Early Detection Capabilities and Performance

• ▪In patients with multiple CT scans, REDMOD produced consistent results months apart.
• ▪REDMOD measures hundreds of quantitative imaging features that describe tissue texture and structure to capture faint biological changes as pancreatic cancer begins to develop.
• ▪REDMOD identifies subtle signs of pancreatic cancer before tumors are visible on CT scans.
• ▪REDMOD identified 73% of prediagnostic pancreatic cancers at a median of about 16 months before diagnosis in a study of nearly 2,000 CT scans.
• ▪REDMOD runs automatically without time-intensive manual preparation.
• ▪REDMOD's detection rate of prediagnostic pancreatic cancers was nearly double the detection rate of specialists reviewing the same scans without AI assistance.
• ▪In CT scans obtained more than two years before pancreatic cancer diagnosis, REDMOD identified nearly three times as many early cancers as would otherwise go undetected.
• ▪The Mayo Clinic-developed Radiomics-based Early Detection Model (REDMOD) can detect pancreatic cancer on routine abdominal CT scans up to three years before clinical diagnosis.

Clinical Validation and Real-World Application

• ▪The REDMOD study was supported by the National Institutes of Health, the Hoveida Family Foundation, the Mayo Clinic Comprehensive Cancer Center and the Champions for Hope Pancreas Cancer Research Program of the Funk-Zitiello Foundation.
• ▪The REDMOD pancreatic cancer detection study was published in the journal Gut.
• ▪The REDMOD 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 begin.
• ▪Dr. Ajit Goenka is a Mayo Clinic radiologist and nuclear medicine specialist who served as senior author of the REDMOD study.
• ▪Researchers are advancing REDMOD into clinical testing through a prospective study called Artificial Intelligence for Pancreatic Cancer Early Detection (AI-PACED).

Pancreatic Cancer's Deadly Nature and Detection Challenges

• ▪Five-year survival rates for pancreatic cancer remain below 15%, according to the National Cancer Institute.
• ▪Projections show pancreatic cancer will become the second-leading cause of cancer-related death in the U.S. by 2030.
• ▪More than 85% of pancreatic cancer patients receive a diagnosis after the disease has already spread, according to the National Cancer Institute.

Perspective of Mayo Clinic researchers

• ▪REDMOD represents a practical application of Mayo Clinic's Precure initiative to detect disease before symptoms appear.

Perspective of Pancreatic cancer patients and advocacy groups

• ▪Earlier detection of pancreatic cancer through REDMOD could significantly improve survival rates that currently remain below 15% at five years.

3 sources