Skip to main content

Table 8 Comparison of the predictive performance of the three models

From: Analysis of factors affecting nonalcoholic fatty liver disease in Chinese steel workers and risk assessment studies

Evaluation index

Logistic

Random Forest

XGBoost

Sensitivity

0.607

0.680

0.564

Precision

0.708

0.643

0.701

Accuracy

0.789

0.771

0.778

AUC

0.839

0.839

0.832

Brier

0.150

0.153

0.155

F1

0.654

0.661

0.625

Log loss

0.460

0.471

0.481

R2

0.789

0.771

0.778