Artificial intelligence (AI) software that could potentially revolutionize the treatment of pancreatic cancer through early diagnosis, even before the tumor becomes visible on a CT scan, is currently being evaluated in a clinical trial.
An AI tool from the Mayo Clinic detected abnormalities on scans up to three years before patients were diagnosed.
According to a research article published in the journal IntestineAn AI model developed by a Minnesota-based clinic was trained using CT scans of patients who had previously been examined for other diseases but were later diagnosed with pancreatic cancer.
The research team then asked radiologists and AI software to review the scans and found that the AI system was three times more effective than radiologists at detecting early signs of disease.
A Mayo Clinic radiologist and study author said they knew pancreatic cancer didn’t occur all at once in three months, adding: “We knew this signal was there. We just had to find a way to detect it.”
Pancreatic cancer has a five-year survival rate of approximately 13% and is on track to become the second leading cause of cancer death by 2030; however, if successful, deployment of Mayo Clinic’s AI software could improve early detection and treatment outcomes.
Early detection of the disease has been rare until now, but stage I patients had a survival rate of up to 40%.
