When a patient undergoes surgery to remove their prostate, the biggest question is often whether the cancer will come back. Doctors need reliable ways to predict this risk so they can decide on the best follow-up plan for each individual person.
A large review of data from over 3,600 patients looked at how computer models called radiomics can help. These models analyze specific features in medical images that the human eye might miss. The study found these radiomics models were much better at predicting biochemical recurrence, which is a sign that cancer may have returned, compared to using standard imaging alone.
The results showed high accuracy for these models, with a sensitivity of 0.82 and specificity of 0.80 in testing groups. While these tools show great potential for personalizing how doctors manage patients after surgery, they are still being refined. Experts suggest that combining this data with other types of biological information could make these predictions even more reliable.
