ABSTRACT

Although many prediction models for cardiovascular diseases (CVDs) have been developed and validated for Western populations, the development of CVD prediction models for Asians has been slow. Our cohort study retrospectively analyzed the incidence of CVD that occurred between January 1, 2009, and December 31, 2016, in all Koreans who underwent national health screening. This dataset included 21,581,796 adults between the ages of 40 and 79 years (10,412,947 men, 11,168,849 women) without CVD at baseline. The primary outcome, CVD, was defined as the development of any of the following: acute coronary syndrome, cerebral infarction, and cerebral hemorrhage, as defined with health insurance claims data. The prediction model was constructed by Cox proportional hazard regression and validated with tenfold cross-validation. The performance of the models was evaluated through Harrell’s C-index and Brier score. The discrimination of the models was assessed by the area under the receiver operating characteristic curve (AUROC). Our model showed an AUROC of 0.762 in men and 0.811 in women. The Brier score of our model was 0.018 in men and 0.010 in women, which was better than the pooled cohort equation (PCE). Our novel model performed better than the FRS and PCE for Koreans.