Automated machine learning for early prediction of systemic inflammatory response syndrome in acute pancreatitis

Table 2 Comparison of LR and automl models for early prediction of SIRS in the test cohort

AUC		Sensitivity	Specificity	Accuracy	PPV	NPV	LR+	LR−
AutoML
GBM	0.833	0.936	0.612	0.684	0.407	0.971	2.414	0.104
DRF	0.830	0.979	0.564	0.656	0.390	0.989	2.243	0.038
GLM	0.853	0.957	0.624	0.698	0.421	0.981	2.548	0.068
DL	0.867	0.787	0.812	0.807	0.544	0.931	4.190	0.262
Logistic regression
LASSO	0.856	0.915	0.697	0.745	0.462	0.966	3.019	0.122

LR, Logistic regression; AutoML, Automated machine learning; SIRS, Systemic inflammatory response syndrome; PPV, Positive predictive value; NPV, Negative predictive value; LR+, Positive likelihood ration; LR−, Negative likelihood ratio

ISSN: 1472-6947