Skip to main content

Table 2 AUROC for cirrhosis prediction after 1-, 3-, and 5-years of follow up using 2- and 4-year laboratory data windows

From: Adapted time-varying covariates Cox model for predicting future cirrhosis development performs well in a large hepatitis C cohort

 

Follow-up interval

1-year

3-years

5-years

2-year laboratory window (n)

34,185

30,153

28,626

AUROC (95% CI)

0.815 (0.813–0.817)

0.811 (0.810–0.812)

0.794 (0.794–0.795)

4-year laboratory window (n)

25,953

20,915

18,198

AUROC (95% CI)

0.796 (0.794–0.798)

0.781 (0.779–0.783)

0.792 (0.791–0.793)

  1. n represents the average sample size of test data for 30 splits
Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us