Comparison between the risk models of the present and previous study.

AUC = area under the receiver operating characteristic curve; CI = confidence interval.
a The performance of each risk scoring model was evaluated by 10-fold cross-validation with an equal number of mutually exclusive ten subgroups of our cohort.
b P-values were obtained by DeLong’s method of comparing AUC in study cohort between a given model and the reference model (reference model: risk model of Utsumi et al.).
Comparison between the risk models of the present and previous study.