An artificial intelligence (AI) system can spot pancreatic cancer long before it shows up on scans, raising the prospect of catching one of the deadliest tumours early enough to successfully treat it, a study found.
The model, developed by researchers at Mayo Clinic and collaborators, identified subtle changes in routine computerised tomography scans, or CT scans, an average of about 475 days before patients were diagnosed, according to the study, published on April 28 in the journal Gut.
Pancreatic cancer is rarely detected early because tumours typically do not cause symptoms and often are not visible on imaging until the disease is advanced.
More than 85 per cent of cases are found at a stage where treatment is largely limited to easing symptoms, helping explain why the five-year survival rate is about 10 per cent globally.
The findings point to a potential shift in how pancreatic cancer is diagnosed – from reacting to symptoms late in the disease to identifying patients at risk years earlier.
“This temporal window holds profound significance, as attaining such early detection would substantially augment the probability of cure and improve survival,” the researchers wrote.
If confirmed in real-world screening, such tools could help move more cases into a window where surgery or other treatments are possible, which modelling studies suggest could significantly improve survival.
“Modelling studies indicate that increasing the proportion of localised pancreatic ductal carcinomas from 10 per cent to 50 per cent would more than double survival rates, thereby underscoring that the timing of diagnosis is the single most critical determinant of survival outcomes.”
The system, called Redmod, analyses patterns in CT images that are not visible to the human eye.
It was trained and tested on scans from more than 1,400 people, including 219 patients whose earlier scans had been read as normal but who later developed pancreatic cancer.
In a head-to-head comparison, the AI was markedly better than radiologists at picking up these early signs.
It correctly identified 73 per cent of cases, compared with about 39 per cent for doctors reviewing the same images. The advantage widened for scans taken more than two years before diagnosis, where the system detected 68 per cent of cases versus 23 per cent for radiologists.
The model also performed consistently across different hospitals and scanners, and correctly classified more than 80 per cent of scans from people who did not develop cancer.
The tool could eventually be used to flag high-risk patients – such as older adults with unexplained weight loss and new-onset diabetes – for closer follow-up, the researchers said, but it needs prospective testing to confirm it improves outcomes before routine use. BLOOMBERG
