Adding depression, anxiety measures to CVD prediction model has little impact

Inclusion of measures of depression and anxiety in the American Heart Association Predicting Risk of Cardiovascular Disease Events (PREVENT) prediction model has little additional impact on risk classification of cardiovascular disease (CVD), according to a study published online Jan. 13 in the Canadian Medical Association Journal.

Shinya Nakada, M.P.H., from the University of Glasgow in the United Kingdom, and colleagues developed and internally validated risk prediction models using 60 and 40%, respectively, of the cohort data from the U.K. Biobank, to examine whether adding measures of anxiety and depression to the PREVENT predictors improves the prediction of CVD risk. CVD events were identified using hospital admission and death certificate data during a 10-year period. Incremental predictive values were determined by adding the mental health predictors to the PREVENT predictors using Harrell’s C-indices.

The derivation set included 195,489 U.K. Biobank participants, and the validation set included 130,326. The researchers found that the inclusion of all mental health measures, except self-reported anxiety, in the validation set yielded a very modest increase in the C-index and specificity, while there was no change seen in sensitivity. Of the mental health predictors, the depressive symptom score yielded the greatest improvements in C-index and specificity (differences: 0.005 and 0.89%, respectively). Similar small improvements were seen for the depressive symptom scores in female and male validation sets.

“Investigating broader mental health conditions using more established tools or diagnostic interview data could be the focus of future studies to further refine CVD risk classification,” the authors write.

2025 HealthDay. All rights reserved.