Skip to main content

Table 3 Performance of different models in the internal and external validations

From: Severity-associated markers and assessment model for predicting the severity of COVID-19: a retrospective study in Hangzhou, China

 

Logistic regression

Ridge regression

Random forest

Support vector machine

Internal validation

 AUROC (95% CI)

0.919 (0.793–0.955)

0.930 (0.914–0.943)

0.973 (0.935–0.993)

0.955 (0.892–0.993)

External validation

 AUROC (95% CI)

0.756 (0.617–0.869)

0.827 (0.716–0.921)

0.795 (0.669–0.905)

0.802 (0.682–0.908)

  1. AUROC Area under the receiver operator characteristic curve, CI Confidence interval