Atherosclerotic cardiovascular disease prediction model and prescribing rates of statins : the Korean heart study

Abstract

Background and Aims

The aims of the study were to evaluate the performance of the American College of Cardiology/American Heart Association (ACC/AHA) 2013 Pooled Cohort Equations in the Korean Heart Study (KHS) population, to develop a Korean Risk Prediction Model (KRPM) for atherosclerotic cardiovascular disease (ASCVD) events, and to evaluate the relation between 10-year ASCVD risk score from two different ASCVD prediction equations and actual statin prescriptions in the last 10 years (2004-2013) in Korean general population.

Methods

The KHS cohort included 200,010 Korean adults aged 40-79 years who were free from ASCVD at baseline. Discrimination and calibration of the ACC/AHA 2013 Pooled Cohort Equations in predicting 10-year ASCVD risk in the KHS cohort were evaluated. Recalibration of the ACC/AHA Equations was done using coefficients from the pooled cohorts'' Cox model but mean values of risk factors and ASCVD incidence rates from the KHS cohort. The KRPM was derived using coefficients, mean risk factor values, and mean incidences from the KHS cohort. Per equations, we also calculated the prescribing rates of statins using cumulative incidence.

Results

In the discriminatory analysis, the ACC/AHA Equations for either White or African-American (AA) moderately distinguished cases from non-cases in the KHS cohort, and were similar to the KRPM: For men, the area under the receiver operating characteristic curve (AUROCs) were 0.727 (White model), 0.725 (AA model), and 0.741 (Korean model); for women, the AUROCs were 0.738, 0.739, and 0.745, respectively. Absolute 10-year ASCVD risk for men in the KHS cohort was overestimated by 56.5% in the White model and 74.1% in the AA model, while the risk for women was underestimated by 27.9% in the White model and overestimated by 29.1% in the AA model. Recalibration of the ACC/AHA Equations did not affect discriminatory ability but improved calibration substantially, especially in men in the White model. Of the three ASCVD risk prediction models, the KRPM showed the best calibration, with the lowest Hosmer-Lemeshow X2 for both men and women when used in a validation subsample. During the follow-up period, an overall prescribing rate of statins in women was 33.5% greater than that of men, 26.3%.

Conclusions

The ACC/AHA Equations should not be directly applied for ASCVD risk prediction in a Korean population. The KRPM showed best predictive ability for ASCVD risk. Therefore, utilization of the prediction risk score in deciding on preventive statin therapy is suggested for Korean population.