AI predicts pancreatic cancer 3 years before it happens

Re:AI predicts pancreatic cancer 3 years before it happens by htrp on Tuesday May 09, 2023 @02:42PM (#35878665)

> The most effective model, based on a transformer-based architecture, showed that out of the top 1,000 highest-risk patients over 50, about 320 would go on to develop pancreatic cancer. The model is less accurate when trying to predict pancreatic cancer over longer time intervals compared to shorter ones, and for patients younger than 50.

questions abound about model overfitting.

[ Parent | on HN ]

Re:AI predicts pancreatic cancer 3 years before it happens by jschveibinz on Tuesday May 09, 2023 @03:30PM (#35879274)

…and bias:

“Future AI-based screening tools for pancreatic cancer will have to be trained on specific local population data, the study found. A model trained on data from Danish patients, for example, was not as accurate when applied to US patients.”

That’s probsbly because it only works when training data are extracted from the “test” data set.

[ Parent | on HN ]