AI model predicts pancreatic cancer risk three years before diagnosis

Researchers at Mayo Clinic have developed an AI model that can potentially predict an individual’s risk of developing pancreatic cancer years before diagnosis.
Study co-author Cornelius Thiels, a surgical oncologist at Mayo Clinic in Rochester, Minnesota, said: ‘Pancreatic cancer can be curable, but only when we catch it early and fewer than one in five patients is diagnosed in time. As a result, survival for many patients is still measured in months, not years.’
Unfortunately, universal screening for pancreatic cancer isn’t feasible, so his team set out to develop an AI model to identify patients at greatest risk of developing pancreatic cancer.
He said: ‘We know that pancreatic cancer forms over five to seven years, but the things that a clinician or patient sees don’t happen until it’s too late.’
Dr Thiels, lead study author Chris Varghese, and their team developed the model using individual patients’ longitudinal health histories from the Mayo Clinic system. The model combined that data with routine laboratory test results collected over an average of a decade or more.
Dr Varghese, a surgical data scientist at Mayo Clinic in Rochester, said: ‘Our model showed that a greater than 50% risk of pancreatic cancer predicted an 88% likelihood of being diagnosed with pancreatic cancer in one year.’
Dr Varghese said the model relies on data inputs captured almost universally in hospital systems worldwide, adding: ‘If it’s shown to work, it could be used in almost any setting.’