Skip to main content
. 2019 Apr 8;23:112. doi: 10.1186/s13054-019-2411-z

Table 3.

Classification matrix for the XGBoost and logistic regression models in the out-of-sample validation cohort

XGBoost Stepwise Logistic regression
Observed Observed
Non-responsive Responsive Non-responsive Responsive
Predicted
 Non-responsive 846 180 737 228
 Responsive 177 467 286 419

Correct classification (accuracy) of volume responsiveness for the XGBoost and the logistic models were 0.79 (95% CI, 0.77–0.81) and 0.69 (95% CI, 0.67–0.71), respectively