Refining PREVENT prediction models for 10-year risk of cardiovascular disease using measures of anxiety and depression.

Abstract

Background: Anxiety and depression are associated with cardiovascular disease (CVD). We aimed to investigate whether adding measures of anxiety and depression to the American Heart Association Predicting Risk of Cardiovascular Disease Events (PREVENT) predictors improves the prediction of CVD risk.

Methods: We developed and internally validated risk prediction models using 60% and 40% of the cohort data from the UK Biobank, respectively. Mental health predictors included baseline depressive symptom score and self-reported and record-based history of anxiety and depression diagnoses before the baseline. We identified CVD events using hospital admission and death certificate data over a 10-year period from baseline. We determined incremental predictive values by adding the mental health predictors to the PREVENT predictors using Harrell's C-indices, sensitivity, specificity, and net reclassification improvement indices. We used a threshold of 10-year risk of incident CVD of greater than 5%.

Results: Of the 502 366 UK Biobank participants, we included 195 489 in the derivation set and 130 326 in the validation set. In the validation set, the inclusion of all mental health measures, except self-reported anxiety, produced a very modest increase in the C-index and specificity while sensitivity remained unchanged. Among these mental health predictors, depressive symptom score produced the greatest improvements in both C-index (difference of 0.005, 95% confidence interval 0.004-0.006) and specificity (difference of 0.89%). Depressive symptom score showed similar small improvements in female and male validation sets.

Interpretation: Our findings suggest that the inclusion of measures of depression and anxiety in PREVENT would have little additional effect on the risk classification of CVD at the population level and may not be worthwhile.