Skip to main content

Table 4 Pairwise comparison of AUC for LASSO model, XGBoost model, LR model and NEWS 2 model

From: Prediction model of in-hospital mortality in intensive care unit patients with cardiac arrest: a retrospective analysis of MIMIC -IV database based on machine learning

Comparison between models

Z statistic

95% Confidence interval

Significance level (p value)

LASSO model vs XGBoost model

0.8

-0.003 to 0.007

0.40

NEWS 2 model vs LASSO model

-10

-0.114 to -0.075

 < 0.001

NEWS 2 model vs XGBoost model

-9

-0.112 to -0.073

 < 0.001

LASSO model vs LR model

-1

-0.016 to 0.003

0.20

XGBoost model vs LR model

-2

-0.019 to 0.002

0.10

NEWS 2 model vs LR model

-10

-0.121 to -0.081

 < 0.001

  1. AUC Area under curve, LASSO Least absolute shrinkage and selection operator, LR Logistic regression, NEWS 2 the national early warning score 2, XGBoost extreme gradient boosting. P < 0.05 was statistically significant