Risk prediction model for cardiovascular diseases in adults initiating pharmacological treatment for attention-deficit/hyperactivity disorder

BACKGROUND: Available prediction models of cardiovascular diseases (CVDs) may not accurately predict outcomes among individuals initiating pharmacological treatment for attention-deficit/hyperactivity disorder (ADHD). OBJECTIVE: To improve the predictive accuracy of traditional CVD risk factors for adults initiating pharmacological treatment of ADHD, by considering novel CVD risk factors associated with ADHD (comorbid psychiatric disorders, sociodemographic factors and psychotropic medication). METHODS: The cohort composed of 24 186 adults residing in Sweden without previous CVDs, born between 1932 and 1990, who started pharmacological treatment of ADHD between 2008 and 2011, and were followed for up to 2 years. CVDs were identified using diagnoses according to the International Classification of Diseases, and dispended medication prescriptions from Swedish national registers. Cox proportional hazards regression was employed to derive the prediction model. FINDINGS: The developed model included eight traditional and four novel CVD risk factors. The model showed acceptable overall discrimination (C index=0.72, 95% CI 0.70 to 0.74) and calibration (Brier score=0.008). The Integrated Discrimination Improvement index showed a significant improvement after adding novel risk factors (0.003 (95% CI 0.001 to 0.007), p<0.001). CONCLUSIONS: The inclusion of the novel CVD risk factors may provide a better prediction of CVDs in this population compared with traditional CVD predictors only, when the model is used with a continuous risk score. External validation studies and studies assessing clinical impact of the model are warranted. CLINICAL IMPLICATIONS: Individuals initiating pharmacological treatment of ADHD at higher risk of developing CVDs should be more closely monitored.