Skip to main content

Table 7 Performance of models trained on the full data set and evaluated on the test set

From: Framework for personalized prediction of treatment response in relapsing remitting multiple sclerosis

Measure

Value

Sample sizea

Response

Model

C-Index

0.554

3354

CDP

predictive

C-Index

0.608

5606

relapse

predictive

Average NLL

0.423

314

CDP

predictive

Average NLL

0.821

314

relapse

predictive

MSE

0.131

314

CDP

predictive

MSE

0.784

314

relapse

predictive

  1. CDP confirmed disability progression, C-Index Harrell’s concordance statistic, MSE mean squared error, NLL negative log-likelihood.
  2. a Refers either to the number of observations (MSE, average NLL) or the number of matched pairs (C-Index)