Imaging vs. Clinical Value Explorer

Predict pathologic tumour size from clinical variables, imaging features, or both, and measure the incremental value with leave-one-out RMSE.

  • incremental value
  • radiomics
  • LOO cross-validation
  • regression

Leave-one-out RMSE comparison

ModelLOO RMSE (cm)vs. clinical (%)n
clinical only0.9120.080
imaging only0.544-40.380
clinical + imaging0.545-40.280

Predicted vs. actual (combined model)

012345678012345678Actual pathologic size (cm)Predicted (cm)

Learning curve

2030405060708000.20.40.60.81Training set size (n)LOO RMSE (cm)
ClinicalImagingCombined
Incremental value must be measured out of sample
Adding imaging features always lowers in-sample residual error; only the leave-one-out RMSE can tell you whether it lowers *prediction* error. Shrink n and the combined model — with the most parameters — is the first to degrade, which is exactly the variance cost of extra predictors in a small cohort.