Table 2.

Performance of models characterized by AUC value and Brier score for predicting critical in-hospital events using COVID-19-infected patient’s data on hospital admission

Model approach	AUC	Brier score
Logistic regression	0.758 [0.725/0.790]	0.184 [0.175/0.197]
L1 LASSO	0.731 [0.713/0.754]	0.197 [0.193/0.201]
L2 ridge regression	0.745 [0.713/0.775]	0.197 [0.193/0.203]
Elastic Net	0.737 [0.714/0.767]	0.196 [0.185/0.203]
Support vector machine	0.744 [0.710/0.765]	0.194 [0.188/0.207]
Random forest	0.763 [0.740/0.786]	0.186 [0.179/0.194]

Data are displayed as median [first quartile/third quartile]

AUC, Area under the curve