AI Tool Can Predict Pancreatic Cancer 3 Years In Advance: Study

Artificial intelligence (AI) has made rapid progress in recent months. From taking baby steps during its early years, the technology has taken a leap and performing complex tasks like solving mathematical problems and writing political speeches. And now, researchers have created an AI tool that can identify people who are at high risk for pancreatic cancer up to three years before a diagnosis. The ground-breaking research has been published in the journal Nature Medicine and is based on the medical records of patients.

Pancreatic cancer is an aggressive disease and its diagnosis is difficult, leading to a low survival rate and need for better screening tools.

The latest research offers hope of early diagnosis and can increase chances of survival.

To get effective results, the team of scientists trained the AI algorithm on six million patients from Denmark and three million from the United States.

The model used disease codes and the timing of their occurrence to predict which patients were likely to develop pancreatic cancer in the future.

Chris Sander, one of the members of the research team and part of the faculty in the Department of Systems Biology at Harvard Medical School, noted in the study that determining who is at high risk for a disease is one of the most important decisions clinicians face.

The researcher also said that an AI tool that can identify those at high risk of pancreatic cancer, "could improve clinical decision-making, leading to earlier diagnosis, treatment, and better outcomes".

The study found the AI tool to be as accurate as current genetic sequencing tests. 

Pancreatic cancer is a leading cause of cancer-related deaths worldwide, with increasing incidence. Approximately 80 per cent of patients with pancreatic cancer are diagnosed with locally advanced or distant metastatic disease, when long-term survival is extremely uncommon.

This new AI tool, said Sanders, can help in better screening, more targeted testing and earlier diagnosis.