Table 3 Comparison of performance metrics of five machine learning models in the training and validation sets.

From: Development of machine learning-based models for predicting sarcopenia risk in stroke patients and analysis of associated factors

Model

Accuracy

Recall

Precision

Specificity

F1Score

A set

B set

A set

B set

A set

B set

A set

B set

A set

B set

LR

0.784

0.861

0.562

0.916

0.750

0.733

0.901

0.833

0.642

0.814

DT

0.827

0.833

0.718

0.833

0.766

0.714

0.885

0.833

0.741

0.769

RF

0.860

0.861

0.843

0.750

0.771

0.818

0.868

0.916

0.805

0.782

NB

0.688

0.916

0.125

0.916

0.800

0.846

0.983

0.916

0.216

0.880

GB

0.881

0.805

0.875

0.750

0.800

0.692

0.885

0.833

0.835

0.720

  1. (1) A set = training set; (2) B set = validation set.
Back to article page