Machine Learning Models of Acute Kidney Injury Prediction in Acute Pancreatitis Patients

Table 3

The detailed performance metrics for the 5 models.

	LR	CART	XGBoost	SVM	RF
AUC	0.8728	0.8033	0.9193	0.8625	0.8821
Sensitivity	0.6071	0.6190	0.6190	0.5357	0.4761
Specificity	0.8642	0.8333	0.8815	0.8488	0.8472
Accuracy	0.8614	0.7910	0.8631	0.8713	0.8452

Abbreviations: AUC: area under the receiver operating characteristic curve; LR: logistic regression; XGBoost: extreme gradient boosting; SVM: support vector machine; RF: random forest.