Machine learning for the prediction of volume responsiveness in patients with oliguric acute kidney injury in critical care

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

ISSN: 1364-8535