A Mayo Clinic-developed artificial intelligence (AI) model can help detect pancreatic cancer on routine abdominal CT scans up to three years before it is diagnosed, research has shown.
In what could be a major breakthrough, the model identifies subtle signs of the disease before tumours are visible when treatment to eradicate it could be possible.
The findings, announced on Wednesday and published in leading journal Gut, comes after Mayo Clinic's multiyear research effort to enable earlier detection of one of the world's most lethal cancers.
The study validated the AI model using data and workflows that mirror clinical practice, including CT scans.
Researchers used the model to analyse nearly 2,000 CT scans, including scans from patients later diagnosed with pancreatic cancer – all originally interpreted as normal.
The system, called the Radiomics-based Early Detection Model (REDMOD), identified 73 per cent of those prediagnostic cancers at a median of about 16 months before diagnosis – nearly double the detection rate of specialists reviewing the same scans without the assistance of artificial intelligence, the study showed.
It further underlined the advantage was even greater at earlier time points. In scans obtained more than two years before diagnosis, the AI identified nearly three times as many early cancers that would otherwise go undetected.
Pancreatic cancer remains one of the deadliest cancers because it often eludes detection until it has begun spreading, resulting in a survival rate of less than five per cent.
Projections show it will become the second-leading cause of cancer-related death in the US by 2030.
"The greatest barrier to saving lives from pancreatic cancer has been our inability to see the disease when it is still curable," said Ajit Goenka, the study's senior author, and a Mayo Clinic radiologist and nuclear medicine specialist.
"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 measures hundreds of quantitative imaging features that describe tissue texture and structure, capturing faint biological changes as cancer begins to develop.
The model is designed to analyse CT scans already obtained for other reasons – particularly in high-risk patients, such as those with new-onset diabetes – and flag elevated risk before any visible mass appears.
The model's predictions also remained stable over time, the study showed. In patients with multiple scans, the AI produced consistent results months apart, supporting its use for longitudinal monitoring and early detection.
Researchers are now advancing this work into clinical testing.
This 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.
The 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.
