Prediction Performance
The PFI score is a method to evaluate the significance each individual
input variable has on the overall model. The results are displayed in
Table 3. The most important features are displayed in ascending order
along with their corresponding importance score. In the creation of the
clinical prediction model, the most important variable was patient
clinical T- classification. This was closely followed by several other
tumor descriptors including primary site of the cancer, clinical N-
classification, grade. The results also indicate that facility type and
facility ID were important variables in the creation of the model.