AI Can Predict Pancreatic Cancer 3 Years in Advance, Says Study

In a breakthrough development, researchers have created an artificial intelligence (AI) tool that can identify people at high risk for pancreatic cancer up to three years before diagnosis.

The study, published in the journal Nature Medicine, found that the AI algorithm was able to predict which patients were likely to develop pancreatic cancer in the future based on their health records. The researchers trained the AI model on the medical records of over 9 million patients from Denmark and the U.S.

Pancreatic cancer is an aggressive form of cancer with a low survival rate due to difficulties in diagnosis and the lack of effective screening tools. Early diagnosis is key to improving patient outcomes.

The AI tool was found to be as accurate as current genetic tests in identifying high-risk patients. Study co-author Chris Sander from Harvard Medical School said determining who is at high risk for a disease "could improve clinical decision-making, leading to earlier diagnosis, treatment, and better outcomes."

The researchers hope the AI tool can help enable better screening, targeted testing and earlier diagnosis of pancreatic cancer - a leading cause of cancer deaths worldwide. Sander said the AI model could help physicians "make more informed clinical decisions regarding who needs further testing."

The study provides hope that through artificial intelligence, more pancreatic cancer cases could be caught at an early, treatable stage.