Table 2 Performance evaluation results of the XGBoost-RFE model with varying numbers of retained features.

From: The construction of HMME-PDT efficacy prediction model for port-wine stain based on machine learning algorithms

Number of features

Mean test score

Std test score

Split0 test score

Split1 test score

Split2 test score

1

0.692

0.063

0.769

0.615

0.692

2

0.667

0.018

0.654

0.654

0.692

3

0.731

0.054

0.769

0.654

0.769

4

0.756

0.018

0.769

0.769

0.731

5

0.756

0.036

0.808

0.731

0.731

6

0.731

0.000

0.731

0.731

0.731

7

0.731

0.031

0.769

0.692

0.731

8

0.744

0.048

0.808

0.692

0.731

Back to article page