Artificial intelligence predicts future pancreatic cancer. « Medicine in the Library

An artificial intelligence tool has successfully identified people at highest risk of pancreatic cancer up to three years before diagnosis using only patient medical records, according to new research by researchers at the Harvard Medical School and the University of Copenhagen.

The results, published in “Nature Medicine“, suggest that AI-based population screening could be invaluable in finding people at high risk of contracting the disease and could expedite the diagnosis of a condition found too often in advanced stages when treatment is less effective and results are very bad, the researchers said.

In the new study, the AI ​​algorithm was trained on two separate datasets totaling 9 million patient records from Denmark and the United States. The researchers “asked” the AI ​​model to look for telltale signs based on the data contained in the records.

Based on the combinations of disease codes and the timing of their occurrence, the model was able to predict which patients might develop pancreatic cancer in the future. Notably, many of the symptoms and disease codes were not directly related to or stemming from the pancreas.

Read the full text of the article:
A deep learning algorithm to predict risk of pancreatic cancer from disease trajectories.
Placido, D., Yuan, B., Hjaltelin, JX et al.
Night With (2023).

Source: Harvard Medical School