A new artificial intelligence tool can predict which tumors are more likely to recur after patients have undergone treatment, the Guardian reports.
Researchers and doctors developed the tool using clinical data from 657 non-small cell lung cancer patients from five different hospitals. As they report in eBioMedicine, researchers from the OCTAPUS-AI study used a number of patient, tumor, and treatment-related features to build and then compare various machine-learning approaches to predict recurrence, recurrence-free survival, and overall survival. They homed in on models that could predict recurrence and overall survival better than traditional tools like tumor staging.
"This is an important step forward in being able to use AI to understand which patients are at highest risk of cancer recurrence, and to detect this relapse sooner so that re-treatment can be more effective," study co-author Richard Lee from the Royal Marsden NHS Foundation Trust tells the Guardian.