Skip to main content

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

From: Comparison of machine learning methods with logistic regression analysis in creating predictive models for risk of critical in-hospital events in COVID-19 patients 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]

  1. Data are displayed as median [first quartile/third quartile]
  2. AUC, Area under the curve
Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us