Using machine learning methods to predict 28-day mortality in patients with hepatic encephalopathy

BMC Gastroenterology

Table 2 Prediction performance of the machine learning models in the test set

Model	Sensitivity	Specificity	PPV	NPV	AUC	95% CI
NNET	0.909	0.699	0.405	0.971	0.837	(0.774,0.901)
GBM	0.939	0.541	0.316	0.975	0.769	(0.694,0.844)
RF	0.636	0.815	0.438	0.908	0.789	(0.712,0.866)
BT	0.788	0.589	0.302	0.925	0.741	(0.654,0.829)
MELD	0.768	0.579	0.295	0.916	0.728	(0.677,0.779)
MELD-Na	0.607	0.724	0.335	0.889	0.711	(0.658,0.765)

PPV Positive predictive values, NPV Negative predictive values, AUC Area under the curve, CI Confidence interval, NNET Artificial neural network, GBM Gradient boosting machine, RF Random forest, BT bagged trees, MELD Model for End-Stage Liver Disease, MELD-Na the Sodium for End-Stage Liver Disease

ISSN: 1471-230X