Increasing evidence suggests that repeatedly measured cardiovascular disease (CVD) risk factors may have an additive predictive value compared with single measured levels. Thus, we evaluated the incremental predictive value of incorporating periodic health screening data for CVD prediction in a large nationwide cohort with periodic health screening tests.Methods and Results—
A total of 467 708 persons aged 40 to 79 years and free from CVD were randomly divided into development (70%) and validation subcohorts (30%). We developed 3 different CVD prediction models: a single measure model using single time point screening data; a longitudinal average model using average risk factor values from periodic screening data; and a longitudinal summary model using average values and the variability of risk factors. The development subcohort included 327 396 persons who had 3.2 health screenings on average and 25 765 cases of CVD over 12 years. The C statistics (95% confidence interval [CI]) for the single measure, longitudinal average, and longitudinal summary models were 0.690 (95% CI, 0.682–0.698), 0.695 (95% CI, 0.687–0.703), and 0.752 (95% CI, 0.744–0.760) in men and 0.732 (95% CI, 0.722–0.742), 0.735 (95% CI, 0.725–0.745), and 0.790 (95% CI, 0.780–0.800) in women, respectively. The net reclassification index from the single measure model to the longitudinal average model was 1.78% in men and 1.33% in women, and the index from the longitudinal average model to the longitudinal summary model was 32.71% in men and 34.98% in women.Conclusions—
Using averages of repeatedly measured risk factor values modestly improves CVD predictability compared with single measurement values. Incorporating the average and variability information of repeated measurements can lead to great improvements in disease prediction.Clinical Trial Registration—
URL: https://www.clinicaltrials.gov. Unique identifier: NCT02931500.