An Artificial Neural Networks Model for Early Predicting In-Hospital Mortality in Acute Pancreatitis in MIMIC-III

Table 5

Predictive performance of different models.

	Accuracy	PPV	NPV	Sensitivity	Specificity	AUC
ANN	0.662	0.563	0.916	0.666	0.661	0.769
Logistic regression	0.660	0.360	0.919	0.346	0.923	0.607
Ranson	0.626	0.181	0.934	0.657	0.622	0.652
SOFA	0.415	0.140	0.939	0.815	0.364	0.401

Abbreviations: ANN: artificial neural networks; SOFA: sequential organ failure assessment; PPV: positive predictive value; NPV: negative predictive value; AUC: area under the ROC curve.