Mayo Clinic AI Detects Pancreatic Cancer Early

Mayo Clinic has developed an artificial intelligence (AI) model, REDMOD (Radiomics-based Early Detection Model), capable of detecting pancreatic cancer on routine abdominal CT scans up to three years before clinical diagnosis. This model identifies subtle signs of the disease before tumors are visible, significantly improving early detection rates compared to specialists alone. The study, published in Gut, validated REDMOD's performance across nearly 2,000 CT scans from multiple institutions, showing it identified 73% of prediagnostic cancers at a median of 16 months before diagnosis. This is crucial as pancreatic cancer is one of the deadliest cancers, with over 85% of patients diagnosed after the disease has spread and a five-year survival rate below 15%. Ajit Goenka, a Mayo Clinic radiologist, highlighted the model's ability to identify the 'signature of cancer from a normal-appearing pancreas.' The research, supported by the United States — National Institutes of Health, Walton Family Foundation, and Funk-Zitiello Foundation, is now advancing into clinical testing through the AI-PACED study, aiming to integrate AI-guided detection into patient care, particularly for high-risk individuals.