A Risk Calculator to Predict Adult Attention-Deficit/Hyperactivity Disorder

Although some risk factors for the persistence or emergence of adult ADHD are known, the clinician is currently unable to correctly predict the course of the disorder based on clinical assessments of children or to propose a preventive intervention for those at risk. One issue might be the inability to combine what is already known about risk factors. This presentation will discuss the approach to generate and validate a multivariable risk calculator to predict adult Attention-Deficit/Hyperactivity Disorder (ADHD) based on childhood clinical and sociodemographic characteristics. The probability model to predict adult ADHD was generated in a birth cohort in the United Kingdom and independently validated in two other birth cohorts from Brazil (1993 Pelotas Birth Cohort) and UK (E-RISK) and one clinical sample from the US (MTA). In the generating sample, the Area Under the Curve (AUC) for predicting adult ADHD was .82 (95% confidence interval [CI], .80 to .83). In the UK birth cohort test sample, AUC was .75 (95% CI, .71 to .78). In the Brazilian birth cohort test sample, AUC was significantly lower – .57 (95% CI, .54 to .60). In the clinical trial test sample, AUC was .76 (95% CI, .73 to .80). The risk calculator based on childhood characteristics specifically predicts adult ADHD in European and North-American population-based and clinical samples with discrimination comparable to commonly used clinical tools in internal medicine and higher than previous attempts for mental and neurological disorders.