Table 6 AUROC and AUPRC scores for the best CatBoost model for each data subset.

From: Using machine learning to predict deterioration of symptoms in COPD patients within a telemonitoring program

 

AUROC

AUPRC

AUPRC random

Train

0.95

0.79

0.09

Validation

0.89

0.59

0.09

Test

0.91

0.53

0.08

  1. AUPRC random contains the score for random predictions.
Back to article page