Your privacy, your choice

We use essential cookies to make sure the site can function. We also use optional cookies for advertising, personalisation of content, usage analysis, and social media.

By accepting optional cookies, you consent to the processing of your personal data - including transfers to third parties. Some third parties are outside of the European Economic Area, with varying standards of data protection.

See our privacy policy for more information on the use of your personal data.

for further information and to change your choices.
Skip to main content

Table 3 Model Performance Comparison with Varying Features for acute GvHD grades 0 and 1 vs 2 vs 3 and 4

From: Leveraging machine learning for predicting acute graft-versus-host disease grades in allogeneic hematopoietic cell transplantation for T-cell prolymphocytic leukaemia

Model

Number of features

Training Balanced accuracy

Testing Balanced accuracy

Testing F1 score

Testing ROC AUC

KNeighborsClassifier

5

0.51

0.36

0.35

0.50

LinearDiscriminantAnalysis

5

0.34

0.38

0.35

0.54

MLPClassifier

5

0.34

0.37

0.36

0.55

KNeighborsClassifier

6

0.52

0.35

0.34

0.49

LinearDiscriminantAnalysis

6

0.34

0.40

0.38

0.56

MLPClassifier

6

0.34

0.45

0.42

0.56

KNeighborsClassifier

7

0.52

0.32

0.31

0.52

LinearDiscriminantAnalysis

7

0.34

0.41

0.38

0.55

MLPClassifier

7

0.35

0.40

0.38

0.55

Back to article page

BMC Medical Research Methodology

ISSN: 1471-2288

Contact us