A Mayo Clinic–developed artificial intelligence model can help specialists detect pancreatic cancer on routine abdominal CT scans up to three years before clinical diagnosis by identifying subtle tissue changes before tumours are visible — a period when curative treatment may still be possible.
Published in Gut, the findings represent a major step in Mayo Clinic’s multiyear effort to detect one of the deadliest cancers in the world.
The study validated the next‑generation AI model using data and workflows that reflect actual clinical practice, including CT scans from multiple institutions, different imaging systems and a variety of protocols.
Researchers applied the model, called the Radiomics‑based Early Detection Model (REDMOD), to nearly 2,000 CT scans — including scans that were originally interpreted as normal from patients who were later diagnosed with pancreatic cancer.
REDMOD identified 73% of those prediagnostic cancers at a median of about 16 months before clinical diagnosis, almost doubling the detection rate achieved by specialists reviewing the same scans unaided.
The AI’s advantage was largest at earlier time points, for scans obtained more than two years before diagnosis, REDMOD detected nearly three times as many early cancers that would otherwise have been missed.
Join PPHM Telegram private group for health insiders news, health tips, and latest info
Pancreatic cancer remains one of the deadliest malignancies because it rarely produces detectable signs in its earliest stages. More than 85% of patients are diagnosed after the disease has already spread; five‑year survival rates remain below 15%, according to the National Cancer Institute of the US. Projections indicate it may become the second leading cause of cancer death in the United States by 2030.
In Malaysia, pancreatic cancer is the 14th most common cancer, with over 1,000 new cases reported annually, often presenting at late stages (III/IV). The survival rate is only approximately 3 in 100,000 people—and is frequently diagnosed through jaundice, abdominal pain, and unexplained weight loss.
“The greatest barrier to saving lives from pancreatic cancer has been our inability to see the disease when it is still curable,” says Ajit Goenka, M.D., the study’s senior author and a Mayo Clinic radiologist and nuclear medicine specialist said in the Mayo Clinic news release. “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.”
REDMOD quantifies hundreds of imaging features that describe tissue texture and structure, capturing faint biological changes present as cancer begins to develop.
The model is intended to analyse CT scans already obtained for other reasons — particularly in patients at higher risk, such as those with new‑onset diabetes — and to flag elevated cancer risk before any visible mass appears.
The system runs automatically without time‑consuming manual preparation. The researchers validated REDMOD across CT scans from multiple institutions, imaging platforms and protocols, showing consistent performance beyond a single dataset.
The model’s predictions were also stable over time: in patients with multiple scans, REDMOD produced consistent results months apart, supporting its potential use for longitudinal monitoring and early detection.
“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,” Dr. Goenka said.
The team is moving this work into clinical testing through a prospective study called Artificial Intelligence for Pancreatic Cancer Early Detection (AI‑PACED).
The study will evaluate how clinicians can integrate AI‑guided detection into care for patients at elevated risk, combining AI analysis of routine imaging with longitudinal follow‑up to assess detection performance, false positives and clinical outcomes.
This research is part of Mayo Clinic’s Precure initiative, which aims to predict and prevent disease by identifying the earliest biological changes before symptoms begin. It also aligns with Mayo Clinic’s Clinical Impact strategy to accelerate translation of discovery into patient care.
The post Mayo Clinic’s New AI Identifies Pancreatic Cancer Up to 3 Years Before Clinical Diagnosis — A Breakthrough first appeared on PP Health Malaysia.
