Table 18.

Results with standard deviation of predictor classification using h2o in Hospital.

Algorithm	AUC	ACC	Average ACC per class	MSE	Average MSE per class
Hospital with standard variables and without replication
DL	0.628 ± 0.044	0.543 ± 0.095	0.658 ± 0.032	0.146 ± 0.025	0.342 ± 0.032
XGBoost	0.692 ± 0.040	0.789 ± 0.112	0.650 ± 0.022	0.094 ± 0.013	0.349 ± 0.022
GBM	0.658 ± 0.043	0.767 ± 0.054	0.661 ± 0.056	0.106 ± 0.016	0.339 ± 0.056
RF	0.654 ± 0.039	0.763 ± 0.104	0.649 ± 0.027	0.097 ± 0.015	0.351 ± 0.027
Replicated and unbalanced Hospital
DL	0.974 ± 0.002	0.926 ± 0.006	0.911 ± 0.005	0.059 ± 0.002	0.089 ± 0.005
XGBoost	0.964 ± 0.003	0.915 ± 0.006	0.888 ± 0.005	0.065 ± 0.002	0.112 ± 0.005
GBM	0.963 ± 0.003	0.915 ± 0.005	0.882 ± 0.005	0.066 ± 0.002	0.118 ± 0.005
RF	0.961 ± 0.003	0.916 ± 0.005	0.881 ± 0.005	0.069 ± 0.002	0.119 ± 0.005
Replicated and balanced Hospital
DL	0.974 ± 0.003	0.931 ± 0.005	0.917 ± 0.005	0.010 ± 0.003	0.082 ± 0.010
XGBoost	0.966 ± 0.005	0.925 ± 0.005	0.898 ± 0.010	0.061 ± 0.005	0.102 ± 0.010
GBM	0.965 ± 0.006	0.921 ± 0.011	0.889 ± 0.005	0.010 ± 0.006	0.111 ± 0.010
RF	0.965 ± 0.004	0.922 ± 0.007	0.902 ± 0.008	0.067 ± 0.006	0.098 ± 0.008